{"id":"875ce989-cee3-4114-a96e-9a1543a7bb8d","shortId":"Tjtezg","kind":"skill","title":"clarity-gate","tagline":"Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases. Produces CGD (Clarity-Gated Documents) and validates SOT (Source of Truth) files.","description":"# Clarity Gate v2.1\n\n**Purpose:** Pre-ingestion verification system that enforces epistemic quality before documents enter RAG knowledge bases. Produces Clarity-Gated Documents (CGD) compliant with the Clarity Gate Format Specification v2.1.\n\n**Core Question:** \"If another LLM reads this document, will it mistake assumptions for facts?\"\n\n**Core Principle:** *\"Detection finds what is; enforcement ensures what should be. In practice: find the missing uncertainty markers before they become confident hallucinations.\"*\n\n---\n\n## What's New in v2.1\n\n| Feature | Description |\n|---------|-------------|\n| **Claim Completion Status** | PENDING/VERIFIED determined by field presence (no explicit status field) |\n| **Source Field Semantics** | Actionable source (PENDING) vs. what-was-found (VERIFIED) |\n| **Claim ID Format Guidance** | Hash-based IDs preferred, collision analysis for scale |\n| **Body Structure Requirements** | HITL Verification Record section mandatory when claims exist |\n| **New Validation Codes** | E-ST10, W-ST11, W-HC01, W-HC02, E-SC06 (FORMAT_SPEC); E-TB01-07 (SOT validation) |\n| **Bundled Scripts** | `claim_id.py` and `document_hash.py` for deterministic computations |\n\n---\n\n## Specifications\n\nThis skill implements and references:\n\n| Specification | Version | Location |\n|---------------|---------|----------|\n| Clarity Gate Format (Unified) | v2.1 | docs/CLARITY_GATE_FORMAT_SPEC.md |\n\n**Note:** v2.0 unifies CGD and SOT into a single `.cgd.md` format. SOT is now a CGD with an optional `tier:` block.\n\n---\n\n## Validation Codes\n\nClarity Gate defines validation codes for structural and semantic checks per FORMAT_SPEC v2.1:\n\n### HITL Claim Validation (§1.3.2-1.3.3)\n| Code | Check | Severity |\n|------|-------|----------|\n| **W-HC01** | Partial `confirmed-by`/`confirmed-date` fields | WARNING |\n| **W-HC02** | Vague source (e.g., \"industry reports\", \"TBD\") | WARNING |\n| **E-SC06** | Schema error in `hitl-claims` structure | ERROR |\n\n### Body Structure (§1.2.1)\n| Code | Check | Severity |\n|------|-------|----------|\n| **E-ST10** | Missing `## HITL Verification Record` when claims exist | ERROR |\n| **W-ST11** | Table rows don't match `hitl-claims` count | WARNING |\n\n### SOT Table Validation (§3.1)\n| Code | Check | Severity |\n|------|-------|----------|\n| **E-TB01** | No `## Verified Claims` section | ERROR |\n| **E-TB02** | Table has no data rows | ERROR |\n| **E-TB03** | Required columns missing | ERROR |\n| **E-TB04** | Column order wrong | ERROR |\n| **E-TB05** | Empty cell in required column | ERROR |\n| **E-TB06** | Invalid date format in Verified column | ERROR |\n| **E-TB07** | Verified date in future (beyond 24h grace) | ERROR |\n\n**Note:** Additional validation codes may be defined in RFC-001 (clarification document) but are not part of the normative FORMAT_SPEC.\n\n---\n\n## Bundled Scripts\n\nThis skill includes Python scripts for deterministic computations per FORMAT_SPEC.\n\n### scripts/claim_id.py\n\nComputes stable, hash-based claim IDs for HITL tracking (per §1.3.4).\n\n```bash\n# Generate claim ID\npython scripts/claim_id.py \"Base price is $99/mo\" \"api-pricing/1\"\n# Output: claim-75fb137a\n\n# Run test vectors\npython scripts/claim_id.py --test\n```\n\n**Algorithm:**\n1. Normalize text (strip + collapse whitespace)\n2. Concatenate with location using pipe delimiter\n3. SHA-256 hash, take first 8 hex chars\n4. Prefix with \"claim-\"\n\n**Test vectors:**\n- `claim_id(\"Base price is $99/mo\", \"api-pricing/1\")` → `claim-75fb137a`\n- `claim_id(\"The API supports GraphQL\", \"features/1\")` → `claim-eb357742`\n\n### scripts/document_hash.py\n\nComputes document SHA-256 hash per FORMAT_SPEC §2.2-2.4 with full canonicalization.\n\n```bash\n# Compute hash\npython scripts/document_hash.py my-doc.cgd.md\n# Output: 7d865e959b2466918c9863afca942d0fb89d7c9ac0c99bafc3749504ded97730\n\n# Verify existing hash\npython scripts/document_hash.py --verify my-doc.cgd.md\n# Output: PASS: Hash verified: 7d865e...\n\n# Run normalization tests\npython scripts/document_hash.py --test\n```\n\n**Algorithm (per §2.2-2.4):**\n1. Extract content between opening `---\\n` and `<!-- CLARITY_GATE_END -->`\n2. Remove `document-sha256` line from YAML frontmatter ONLY (with multiline continuation support)\n3. Canonicalize:\n   - Strip trailing whitespace per line\n   - Collapse 3+ consecutive newlines to 2\n   - Normalize final newline (exactly 1 LF)\n   - UTF-8 NFC normalization\n4. Compute SHA-256\n\n**Cross-platform normalization:**\n- BOM removed if present\n- CRLF to LF (Windows)\n- CR to LF (old Mac)\n- Boundary detection (prevents hash computation on content outside CGD structure)\n- Whitespace variations produce identical hashes (deterministic across platforms)\n\n---\n\n## The Key Distinction\n\nExisting tools like UnScientify and HedgeHunter (CoNLL-2010) **detect** uncertainty markers already present in text (\"Is uncertainty expressed?\").\n\nClarity Gate **enforces** their presence where epistemically required (\"Should uncertainty be expressed but isn't?\").\n\n| Tool Type | Question | Example |\n|-----------|----------|---------|\n| **Detection** | \"Does this text contain hedges?\" | UnScientify/HedgeHunter find \"may\", \"possibly\" |\n| **Enforcement** | \"Should this claim be hedged but isn't?\" | Clarity Gate flags \"Revenue will be $50M\" |\n\n---\n\n## Critical Limitation\n\n> **Clarity Gate verifies FORM, not TRUTH.**\n>\n> This skill checks whether claims are properly marked as uncertain—it cannot verify if claims are actually true. \n>\n> **Risk:** An LLM can hallucinate facts INTO a document, then \"pass\" Clarity Gate by adding source markers to false claims.\n>\n> **Solution:** HITL (Human-In-The-Loop) verification is **MANDATORY** before declaring PASS.\n\n---\n\n## When to Use\n- Before ingesting documents into RAG systems\n- Before sharing documents with other AI systems\n- After writing specifications, state docs, or methodology descriptions\n- When a document contains projections, estimates, or hypotheses\n- Before publishing claims that haven't been validated\n- When handing off documentation between LLM sessions\n\n---\n\n## The 9 Verification Points\n\n### Relationship to Spec Suite\n\nThe 9 Verification Points guide **semantic review** — content quality checks that require judgment (human or AI). They answer questions like \"Should this claim be hedged?\" and \"Are these numbers consistent?\"\n\nWhen review completes, output a CGD file conforming to CLARITY_GATE_FORMAT_SPEC.md. The C/S rules in CLARITY_GATE_FORMAT_SPEC.md validate **file structure**, not semantic content.\n\n**The connection:**\n1. Semantic findings (9 points) determine what issues exist\n2. Issues are recorded in CGD state fields (`clarity-status`, `hitl-status`, `hitl-pending-count`)\n3. State consistency is enforced by structural rules (C7-C10)\n\n*Example: If Point 5 (Data Consistency) finds conflicting numbers, you'd mark `clarity-status: UNCLEAR` until resolved. Rule C7 then ensures you can't claim `REVIEWED` while still `UNCLEAR`.*\n\n---\n\n### Epistemic Checks (Core Focus: Points 1-4)\n\n**1. HYPOTHESIS vs FACT LABELING**\nEvery claim must be clearly marked as validated or hypothetical.\n\n| Fails | Passes |\n|-------|--------|\n| \"Our architecture outperforms competitors\" | \"Our architecture outperforms competitors [benchmark data in Table 3]\" |\n| \"The model achieves 40% improvement\" | \"The model achieves 40% improvement [measured on dataset X]\" |\n\n**Fix:** Add markers: \"PROJECTED:\", \"HYPOTHESIS:\", \"UNTESTED:\", \"(estimated)\", \"~\", \"?\"\n\n---\n\n**2. UNCERTAINTY MARKER ENFORCEMENT**\nForward-looking statements require qualifiers.\n\n| Fails | Passes |\n|-------|--------|\n| \"Revenue will be $50M by Q4\" | \"Revenue is **projected** to be $50M by Q4\" |\n| \"The feature will reduce churn\" | \"The feature is **expected** to reduce churn\" |\n\n**Fix:** Add \"projected\", \"estimated\", \"expected\", \"designed to\", \"intended to\"\n\n---\n\n**3. ASSUMPTION VISIBILITY**\nImplicit assumptions that affect interpretation must be explicit.\n\n| Fails | Passes |\n|-------|--------|\n| \"The system scales linearly\" | \"The system scales linearly [assuming <1000 concurrent users]\" |\n| \"Response time is 50ms\" | \"Response time is 50ms [under standard load conditions]\" |\n\n**Fix:** Add bracketed conditions: \"[assuming X]\", \"[under conditions Y]\", \"[when Z]\"\n\n---\n\n**4. AUTHORITATIVE-LOOKING UNVALIDATED DATA**\nTables with specific percentages and checkmarks look like measured data.\n\n**Red flag:** Tables with specific numbers (89%, 95%, 100%) without sources\n\n**Fix:** Add \"(guess)\", \"(est.)\", \"?\" to numbers. Add explicit warning: \"PROJECTED VALUES - NOT MEASURED\"\n\n---\n\n### Data Quality Checks (Complementary: Points 5-7)\n\n**5. DATA CONSISTENCY**\nScan for conflicting numbers, dates, or facts within the document.\n\n**Red flag:** \"500 users\" in one section, \"750 users\" in another\n\n**Fix:** Reconcile conflicts or explicitly note the discrepancy with explanation.\n\n---\n\n**6. IMPLICIT CAUSATION**\nClaims that imply causation without evidence.\n\n**Red flag:** \"Shorter prompts improve response quality\" (plausible but unproven)\n\n**Fix:** Reframe as hypothesis: \"Shorter prompts MAY improve response quality (hypothesis, not validated)\"\n\n---\n\n**7. FUTURE STATE AS PRESENT**\nDescribing planned/hoped outcomes as if already achieved.\n\n**Red flag:** \"The system processes 10,000 requests per second\" (when it hasn't been built)\n\n**Fix:** Use future/conditional: \"The system is DESIGNED TO process...\" or \"TARGET: 10,000 rps\"\n\n---\n\n### Verification Routing (Points 8-9)\n\n**8. TEMPORAL COHERENCE**\nDocument dates and timestamps must be internally consistent and plausible.\n\n| Fails | Passes |\n|-------|--------|\n| \"Last Updated: December 2024\" (when current is 2026) | \"Last Updated: January 2026\" |\n| v1.0.0 dated 2024-12-23, v1.1.0 dated 2024-12-20 | Versions in chronological order |\n\n**Sub-checks:**\n1. Document date vs current date\n2. Internal chronology (versions, events in order)\n3. Reference freshness (\"current\", \"now\", \"today\" claims)\n\n**Fix:** Update dates, add \"as of [date]\" qualifiers, flag stale claims\n\n---\n\n**9. EXTERNALLY VERIFIABLE CLAIMS**\nSpecific numbers that could be fact-checked should be flagged for verification.\n\n| Type | Example | Risk |\n|------|---------|------|\n| Pricing | \"Costs ~$0.005 per call\" | API pricing changes |\n| Statistics | \"Papers average 15-30 equations\" | May be wildly off |\n| Rates/ratios | \"40% of researchers use X\" | Needs citation |\n| Competitor claims | \"No competitor offers Y\" | May be outdated |\n\n**Fix options:**\n1. Add source with date\n2. Add uncertainty marker\n3. Route to HITL or external search\n4. Generalize (\"low cost\" instead of \"$0.005\")\n\n---\n\n## The Verification Hierarchy\n\n```\nClaim Extracted --> Does Source of Truth Exist?\n                           |\n           +---------------+---------------+\n           YES                             NO\n           |                               |\n   Tier 1: Automated              Tier 2: HITL\n   Consistency & Verification     Two-Round Verification\n           |                               |\n   PASS / BLOCK                   Round A → Round B → APPROVE / REJECT\n```\n\n### Tier 1: Automated Verification\n\n**A. Internal Consistency**\n- Figure vs. Text contradictions\n- Abstract vs. Body mismatches\n- Table vs. Prose conflicts\n- Numerical consistency\n\n**B. External Verification (Extension Interface)**\n- User-provided connectors to structured sources\n- Financial systems, Git commits, CRM, etc.\n\n### Tier 2: Two-Round HITL Verification — MANDATORY\n\n**Round A: Derived Data Confirmation**\n- Claims from sources found in session\n- Human confirms interpretation, not truth\n\n**Round B: True HITL Verification**\n- Claims needing actual verification\n- No source found, human's own data, extrapolations\n\n---\n\n## CGD Output Format\n\nWhen producing a Clarity-Gated Document, use this format per CLARITY_GATE_FORMAT_SPEC.md v2.1:\n\n```yaml\n---\nclarity-gate-version: 2.1\nprocessed-date: 2026-01-12\nprocessed-by: Claude + Human Review\nclarity-status: CLEAR\nhitl-status: REVIEWED\nhitl-pending-count: 0\npoints-passed: 1-9\nrag-ingestable: true          # computed by validator - do not set manually\ndocument-sha256: 7d865e959b2466918c9863afca942d0fb89d7c9ac0c99bafc3749504ded97730\nhitl-claims:\n  - id: claim-75fb137a\n    text: \"Revenue projection is $50M\"\n    value: \"$50M\"\n    source: \"Q3 planning doc\"\n    location: \"revenue-projections/1\"\n    round: B\n    confirmed-by: Francesco\n    confirmed-date: 2026-01-12\n---\n\n# Document Title\n\n[Document body with epistemic markers applied]\n\nClaims like \"Revenue will be $50M\" become \"Revenue is **projected** to be $50M *(unverified projection)*\"\n\n---\n\n## HITL Verification Record\n\n### Round A: Derived Data Confirmation\n- Claim 1 (source) ✓\n- Claim 2 (source) ✓\n\n### Round B: True HITL Verification\n| # | Claim | Status | Verified By | Date |\n|---|-------|--------|-------------|------|\n| 1 | [claim] | ✓ Confirmed | [name] | [date] |\n\n<!-- CLARITY_GATE_END -->\nClarity Gate: CLEAR | REVIEWED\n```\n\n**Required CGD Elements (per spec):**\n- YAML frontmatter with all required fields:\n  - `clarity-gate-version` — Tool version (no \"v\" prefix)\n  - `processed-date` — YYYY-MM-DD format\n  - `processed-by` — Processor name\n  - `clarity-status` — CLEAR or UNCLEAR\n  - `hitl-status` — PENDING, REVIEWED, or REVIEWED_WITH_EXCEPTIONS\n  - `hitl-pending-count` — Integer ≥ 0\n  - `points-passed` — e.g., `1-9` or `1-4,7,9`\n  - `hitl-claims` — List of verified claims (may be empty `[]`)\n- End marker (HTML comment + status line):\n  ```\n  <!-- CLARITY_GATE_END -->\n  Clarity Gate: <clarity-status> | <hitl-status>\n  ```\n- HITL verification record (if status is REVIEWED)\n\n**Optional/Computed Fields:**\n- `rag-ingestable` — **Computed by validators**, not manually set. Shows `true` only when `CLEAR | REVIEWED` with no exclusion blocks.\n- `document-sha256` — Required. 64-char lowercase hex hash for integrity verification. See spec §2 for computation rules.\n- `exclusions-coverage` — Optional. Fraction of body inside exclusion blocks (0.0–1.0).\n\n**Escape Mechanism:** To write about markers like `*(estimated)*` without triggering parsing, wrap in backticks: `` `*(estimated)*` ``\n\n### Claim Completion Status (v2.1)\n\nClaim verification status is determined by field **presence**, not an explicit status field:\n\n| State | `confirmed-by` | `confirmed-date` | Meaning |\n|-------|----------------|------------------|----------|\n| **PENDING** | absent | absent | Awaiting human verification |\n| **VERIFIED** | present | present | Human has confirmed |\n| *(invalid)* | present | absent | W-HC01: partial fields |\n| *(invalid)* | absent | present | W-HC01: partial fields |\n\n**Why no explicit status field?** Field presence is self-enforcing—you can't accidentally set status without providing who/when.\n\n### Source Field Semantics (v2.1)\n\nThe `source` field meaning changes based on claim state:\n\n| State | `source` Contains | Example |\n|-------|-------------------|----------|\n| **PENDING** | Where to verify (actionable) | `\"Check Q3 planning doc\"` |\n| **VERIFIED** | What was found (evidence) | `\"Q3 planning doc, page 12\"` |\n\n**Vague source detection (W-HC02):** Sources like `\"industry reports\"`, `\"research\"`, `\"TBD\"` trigger warnings.\n\n### Claim ID Format (v2.1)\n\n**General pattern:** `claim-[a-z0-9._-]{1,64}` (alphanumeric, dots, underscores, hyphens)\n\n| Approach | Pattern | Example | Use Case |\n|----------|---------|---------|----------|\n| **Hash-based** (preferred) | `claim-[a-f0-9]{8,}` | `claim-75fb137a` | Deterministic, collision-resistant |\n| **Sequential** | `claim-[0-9]+` | `claim-1`, `claim-2` | Simple documents |\n| **Semantic** | `claim-[a-z0-9-]+` | `claim-revenue-q3` | Human-friendly |\n\n**Collision probability:** At 1,000 claims with 8-char hex IDs: ~0.012%. For >1,000 claims, use 12+ hex characters.\n\n**Recommendation:** Use hash-based IDs generated by `scripts/claim_id.py` for consistency and collision resistance.\n\n---\n\n## Exclusion Blocks\n\nWhen content cannot be resolved (no SME available, legacy prose, etc.), mark it as excluded rather than leaving it ambiguous:\n\n```markdown\n<!-- CG-EXCLUSION:BEGIN id=auth-legacy-1 -->\nLegacy authentication details that require SME review...\n<!-- CG-EXCLUSION:END id=auth-legacy-1 -->\n```\n\n**Rules:**\n- IDs must match: `[A-Za-z0-9][A-Za-z0-9._-]{0,63}`\n- No nesting or overlapping blocks\n- Each ID used only once\n- Requires `hitl-status: REVIEWED_WITH_EXCEPTIONS`\n- Must document `exceptions-reason` and `exceptions-ids` in frontmatter\n\n**Important:** Documents with exclusion blocks are **not RAG-ingestable**. They're rejected entirely (no partial ingestion).\n\nSee CLARITY_GATE_FORMAT_SPEC.md §4 for complete rules.\n\n---\n\n## SOT Validation\n\nWhen validating a Source of Truth file, the skill checks both **format compliance** (per CLARITY_GATE_FORMAT_SPEC.md) and **content quality** (the 9 points).\n\n### Format Compliance (Structural Rules)\n\nSOT documents are CGDs with a `tier:` block. They require a `## Verified Claims` section with a valid table.\n\n| Code | Check | Severity |\n|------|-------|----------|\n| E-TB01 | No `## Verified Claims` section | ERROR |\n| E-TB02 | Table has no data rows | ERROR |\n| E-TB03 | Required columns missing (Claim, Value, Source, Verified) | ERROR |\n| E-TB04 | Column order wrong (Claim not first or Verified not last) | ERROR |\n| E-TB05 | Empty cell in required column | ERROR |\n| E-TB06 | Invalid date format in Verified column | ERROR |\n| E-TB07 | Verified date in future (beyond 24h grace) | ERROR |\n\n### Content Quality (9 Points)\n\nThe 9 Verification Points apply to SOT content:\n\n| Point | SOT Application |\n|-------|-----------------|\n| 1-4 | Check claims in `## Verified Claims` are actually verified |\n| 5 | Check for conflicting values across tables |\n| 6 | Check claims don't imply unsupported causation |\n| 7 | Check table doesn't state futures as present |\n| 8 | Check dates are chronologically consistent |\n| 9 | Flag specific numbers for external check |\n\n### SOT-Specific Requirements\n\n- **Tier block required:** SOT is a CGD with `tier:` block containing `level`, `owner`, `version`, `promoted-date`, `promoted-by`\n- **Structured claims table:** `## Verified Claims` section with columns: Claim, Value, Source, Verified\n- **Table outside exclusions:** The verified claims table must NOT be inside an exclusion block\n- **Staleness markers:** Use `[STABLE]`, `[CHECK]`, `[VOLATILE]`, `[SNAPSHOT]` in content\n  - `[STABLE]` — Safe to cite without rechecking\n  - `[CHECK]` — Verify before citing\n  - `[VOLATILE]` — Changes frequently; always verify\n  - `[SNAPSHOT]` — Point-in-time data; include date when citing\n\n---\n\n## Output Format\n\nAfter running Clarity Gate, report:\n\n```\n## Clarity Gate Results\n\n**Document:** [filename]\n**Issues Found:** [number]\n\n### Critical (will cause hallucination)\n- [issue + location + fix]\n\n### Warning (could cause equivocation)  \n- [issue + location + fix]\n\n### Temporal (date/time issues)\n- [issue + location + fix]\n\n### Externally Verifiable Claims\n| # | Claim | Type | Suggested Verification |\n|---|-------|------|------------------------|\n| 1 | [claim] | Pricing | [where to verify] |\n\n---\n\n## Round A: Derived Data Confirmation\n\n- [claim] ([source])\n\nReply \"confirmed\" or flag any I misread.\n\n---\n\n## Round B: HITL Verification Required\n\n| # | Claim | Why HITL Needed | Human Confirms |\n|---|-------|-----------------|----------------|\n| 1 | [claim] | [reason] | [ ] True / [ ] False |\n\n---\n\n**Would you like me to produce an annotated CGD version?**\n\n---\n\n**Verdict:** PENDING CONFIRMATION\n```\n\n---\n\n## Severity Levels\n\n| Level | Definition | Action |\n|-------|------------|--------|\n| **CRITICAL** | LLM will likely treat hypothesis as fact | Must fix before use |\n| **WARNING** | LLM might misinterpret | Should fix |\n| **TEMPORAL** | Date/time inconsistency detected | Verify and update |\n| **VERIFIABLE** | Specific claim that could be fact-checked | Route to HITL or external search |\n| **ROUND A** | Derived from witnessed source | Quick confirmation |\n| **ROUND B** | Requires true verification | Cannot pass without confirmation |\n| **PASS** | Clearly marked, no ambiguity, verified | No action needed |\n\n---\n\n## Quick Scan Checklist\n\n| Pattern | Action |\n|---------|--------|\n| Specific percentages (89%, 73%) | Add source or mark as estimate |\n| Comparison tables | Add \"PROJECTED\" header |\n| \"Achieves\", \"delivers\", \"provides\" | Use \"designed to\", \"intended to\" if not validated |\n| Checkmarks | Verify these are confirmed |\n| \"100%\" anything | Almost always needs qualification |\n| \"Last Updated: [date]\" | Check against current date |\n| Version numbers with dates | Verify chronological order |\n| \"$X.XX\" or \"~$X\" (pricing) | Flag for external verification |\n| \"averages\", \"typically\" | Flag for source/citation |\n| Competitor capability claims | Flag for external verification |\n\n---\n\n## What This Skill Does NOT Do\n\n- Does not classify document types (use Stream Coding for that)\n- Does not restructure documents \n- Does not add deep links or references\n- Does not evaluate writing quality\n- **Does not check factual accuracy autonomously** (requires HITL)\n\n---\n\n## Related Projects\n\n| Project | Purpose | URL |\n|---------|---------|-----|\n| Source of Truth Creator | Create epistemically calibrated docs | github.com/frmoretto/source-of-truth-creator |\n| Stream Coding | Documentation-first methodology | github.com/frmoretto/stream-coding |\n| ArXiParse | Scientific paper verification | arxiparse.org |\n\n---\n\n## Changelog\n\n### v2.1.3 (2026-03-02)\n- **FIXED:** `document_hash.py` now implements full FORMAT_SPEC §2.1-2.4 compliance\n- **FIXED:** Fence-aware end marker detection (Quine Protection per §2.3/§8.5)\n- **FIXED:** All 4 deployment copies converged to single canonical implementation\n- **ADDED:** `canonicalize()` function: trailing whitespace stripping, newline collapsing, NFC normalization\n- **ADDED:** YAML-aware `document-sha256` removal with multiline continuation support (§2.2)\n- **ADDED:** Fence-tracking test vectors (7 new tests, 15 total)\n\n### v2.1.0 (2026-01-27)\n- **ADDED:** Claim Completion Status semantics (PENDING/VERIFIED by field presence)\n- **ADDED:** Source Field Semantics (actionable vs. what-was-found)\n- **ADDED:** Claim ID Format guidance with collision analysis\n- **ADDED:** Body Structure Requirements (HITL Verification Record mandatory when claims exist)\n- **ADDED:** New validation codes: E-ST10, W-ST11, W-HC01, W-HC02, E-SC06 (FORMAT_SPEC §1.2-1.3)\n- **ADDED:** Bundled scripts: `claim_id.py`, `document_hash.py`\n- **UPDATED:** References to FORMAT_SPEC v2.1\n- **UPDATED:** CGD output example to version 2.1\n\n### v2.0.0 (2026-01-13)\n- **ADDED:** agentskills.io compliant YAML frontmatter\n- **ADDED:** Clarity Gate Format Specification v2.0 compliance (unified CGD/SOT)\n- **ADDED:** SOT validation support with E-TB* error codes\n- **ADDED:** Validation rules mapping (9 points → rule codes)\n- **ADDED:** CGD output format template with `<!-- CLARITY_GATE_END -->` markers\n- **ADDED:** Quine Protection note (§2.3 fence-aware marker detection)\n- **ADDED:** Redacted Export feature (§8.11)\n- **UPDATED:** `hitl-claims` format to v2.0 schema (id, text, value, source, location, round)\n- **UPDATED:** End marker format to HTML comment style\n- **UPDATED:** Unified format spec v2.0 (single `.cgd.md` extension)\n- **RESTRUCTURED:** For multi-platform skill discovery\n\n### v1.6 (2025-12-31)\n- Added Two-Round HITL verification system\n- Round A: Derived Data Confirmation\n- Round B: True HITL Verification\n\n### v1.5 (2025-12-28)\n- Added Point 8: Temporal Coherence\n- Added Point 9: Externally Verifiable Claims\n\n### v1.4 (2025-12-23)\n- Added CGD annotation output mode\n\n### v1.3 (2025-12-21)\n- Restructured points into Epistemic (1-4) and Data Quality (5-7)\n\n### v1.2 (2025-12-21)\n- Added Source of Truth request step\n\n### v1.1 (2025-12-21)\n- Added HITL Fact Verification (mandatory)\n\n### v1.0 (2025-11)\n- Initial release with 6-point verification\n\n---\n\n**Version:** 2.1.3\n**Spec Version:** 2.1\n**Author:** Francesco Marinoni Moretto\n**License:** CC-BY-4.0","tags":["clarity","gate","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows"],"capabilities":["skill","source-sickn33","skill-clarity-gate","topic-agent-skills","topic-agentic-skills","topic-ai-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workflows","topic-antigravity","topic-antigravity-skills","topic-claude-code","topic-claude-code-skills","topic-codex-cli","topic-codex-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/clarity-gate","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sickn33/antigravity-awesome-skills","source_repo":"https://github.com/sickn33/antigravity-awesome-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 34882 github stars · SKILL.md body (23,917 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-24T12:50:45.373Z","embedding":null,"createdAt":"2026-04-18T21:34:16.366Z","updatedAt":"2026-04-24T12:50:45.373Z","lastSeenAt":"2026-04-24T12:50:45.373Z","tsv":"'-001':395 '-01':1543,1617,2794,2877 '-02':2725 '-03':2724 '-1':1998 '-1.3':2856 '-11':3051 '-12':1280,1285,1544,1618,2972,2993,3008,3017,3032,3042 '-13':2878 '-2':2000 '-2.4':519,552,2734 '-20':1286 '-2010':646 '-21':3018,3033,3043 '-23':1281,3009 '-256':473,513,600 '-27':2795 '-28':2994 '-30':1357 '-31':2973 '-4':943,1737,2283,3024 '-7':1136,3029 '-8':594 '-9':1249,1568,1734,1996 '/1':446,495,1606 '/frmoretto/source-of-truth-creator':2706 '/frmoretto/stream-coding':2715 '0':1563,1728,1995,2094 '0.0':1814 '0.005':1347,1404 '0.012':2027 '000':1221,1243,2020,2030 '07':184 '1':458,553,591,869,942,944,1294,1382,1418,1438,1567,1651,1666,1733,1736,1965,2019,2029,2282,2455,2486,3023 '1.0':1815 '1.2':2855 '1.2.1':290 '1.3.2':250 '1.3.3':251 '1.3.4':432 '10':1220,1242 '100':1114,2611 '1000':1064 '12':1939,2033 '15':1356,2790 '2':464,560,586,878,995,1300,1387,1421,1477,1654,1800 '2.1':1538,2733,2874,3062 '2.1.3':3059 '2.2':518,551,2780 '2.3':2746,2922 '2024':1268,1279,1284 '2025':2971,2992,3007,3016,3031,3041,3050 '2026':1272,1276,1542,1616,2723,2793,2876 '24h':383,2264 '3':471,574,582,896,973,1042,1307,1391 '3.1':321 '4':480,597,1090,1398,2143,2750 '4.0':3071 '40':977,982,1364 '5':910,1135,1137,2292,3028 '500':1152 '50m':701,1010,1018,1595,1597,1632,1639 '50ms':1070,1074 '6':1171,2299,3055 '63':2095 '64':1790,1966 '7':1203,1738,2307,2787 '73':2583 '750':1157 '75fb137a':450,498,1590,1988 '7d865e':542 '7d865e959b2466918c9863afca942d0fb89d7c9ac0c99bafc3749504ded97730':530,1583 '8':477,1248,1250,1985,2023,2316,2997 '8.11':2932 '8.5':2747 '89':1112,2582 '9':809,817,872,1325,1739,1964,1984,2008,2088,2093,2168,2269,2272,2322,2907,3002 '95':1113 '99/mo':442,491 'a-f0':1981 'a-z0':1961,2005 'a-za-z0':2084,2089 'absent':1857,1858,1870,1877 'abstract':1448 'accident':1898 'accuraci':2687 'achiev':976,981,1214,2595 'across':634,2297 'action':128,1925,2508,2573,2579,2809 'actual':726,1507,2290 'ad':742,2758,2768,2781,2796,2805,2815,2823,2834,2857,2879,2884,2893,2903,2911,2918,2928,2974,2995,3000,3010,3034,3044 'add':989,1034,1080,1118,1123,1317,1383,1388,2584,2592,2673 'addit':387 'affect':1048 'agentskills.io':2880 'ai':775,831 'algorithm':457,549 'almost':2613 'alphanumer':1967 'alreadi':650,1213 'alway':2401,2614 'ambigu':2071,2570 'analysi':147,2822 'annot':2498,3012 'anoth':72,1160 'answer':833 'anyth':2612 'api':444,493,502,1350 'api-pr':443,492 'appli':1626,2275 'applic':2281 'approach':1971 'approv':1435 'architectur':962,966 'arxipars':2716 'arxiparse.org':2720 'assum':1063,1083 'assumpt':80,1043,1046 'authent':2074 'author':3063 'authorit':1092 'authoritative-look':1091 'autom':1419,1439 'autonom':2688 'avail':2059 'averag':1355,2639 'await':1859 'awar':2739,2771,2925 'b':1434,1458,1501,1608,1657,2476,2558,2987 'backtick':1829 'base':22,54,143,425,439,488,1913,1978,2040 'bash':433,523 'becom':103,1633 'benchmark':969 'beyond':382,2263 'block':230,1430,1785,1813,2051,2100,2128,2181,2334,2342,2378 'bodi':150,288,1450,1622,1810,2824 'bom':605 'boundari':618 'bracket':1081 'built':1230 'bundl':187,407,2858 'c/s':857 'c10':906 'c7':905,926 'c7-c10':904 'calibr':2702 'call':1349 'cannot':721,2054,2562 'canon':2756 'canonic':522,575,2759 'capabl':2645 'case':1975 'caus':2430,2437 'causat':1173,1177,2306 'cc':3069 'cc-bi':3068 'cell':360,2241 'cgd':24,60,213,225,626,851,883,1517,1676,2339,2499,2869,2912,3011 'cgd.md':219,2961 'cgd/sot':2892 'cgds':2177 'chang':1352,1912,2399 'changelog':2721 'char':479,1791,2024 'charact':2035 'check':242,253,292,323,712,825,938,1132,1293,1336,1926,2158,2193,2284,2293,2300,2308,2317,2328,2383,2394,2542,2620,2685 'checklist':2577 'checkmark':1101,2606 'chronolog':1289,1302,2320,2629 'churn':1025,1032 'citat':1370 'cite':2391,2397,2412 'claim':113,137,159,248,285,302,315,330,426,435,449,483,486,497,499,507,689,714,724,747,795,838,932,950,1174,1313,1324,1328,1372,1408,1489,1505,1586,1589,1627,1650,1653,1661,1667,1742,1746,1831,1835,1915,1954,1960,1980,1987,1994,1997,1999,2004,2010,2021,2031,2186,2200,2218,2229,2285,2288,2301,2354,2357,2361,2370,2450,2451,2456,2466,2480,2487,2536,2646,2797,2816,2832,2936,3005 'claim-75fb137a':448,496,1588,1986 'claim-eb357742':506 'claim-revenue-q3':2009 'claim_id.py':189,2860 'clarif':396 'clariti':2,26,36,57,64,204,233,657,695,704,739,887,920,1524,1535,1552,1671,1687,1709,1756,2417,2420,2885 'clarity-g':1,25,56,1523 'clarity-gate-vers':1534,1686 'clarity-status':886,919,1551,1708 'clarity_gate_format_spec.md':855,860,1531,2142,2163 'classifi':2659 'claud':1548 'clear':953,1554,1673,1711,1780,2567 'code':163,232,237,252,291,322,389,2192,2664,2708,2837,2902,2910 'coher':1252,2999 'collaps':462,581,2765 'collis':146,1991,2016,2048,2821 'collision-resist':1990 'column':346,352,363,373,2216,2226,2244,2254,2360 'comment':1753,2953 'commit':1473 'comparison':2590 'competitor':964,968,1371,1374,2644 'complementari':1133 'complet':114,848,1832,2145,2798 'complianc':2161,2171,2735,2890 'compliant':61,2881 'comput':194,416,421,510,524,598,622,1573,1770,1802 'concaten':465 'concurr':1065 'condit':1078,1082,1086 'confid':104 'confirm':260,263,1488,1496,1610,1614,1649,1668,1850,1853,1867,2465,2469,2485,2503,2556,2565,2610,2985 'confirmed-bi':259,1609,1849 'confirmed-d':262,1613,1852 'conflict':914,1142,1163,1455,2295 'conform':853 'conll':645 'connect':868 'connector':1466 'consecut':583 'consist':845,898,912,1139,1260,1423,1443,1457,2046,2321 'contain':680,788,1919,2343 'content':555,624,823,866,2053,2165,2267,2278,2387 'continu':572,2778 'contradict':1447 'converg':2753 'copi':2752 'core':69,83,939 'cost':1346,1401 'could':1332,2436,2538 'count':316,895,1562,1726 'coverag':1806 'cr':613 'creat':2700 'creator':2699 'critic':702,2428,2509 'crlf':609 'crm':1474 'cross':602 'cross-platform':601 'current':1270,1298,1310,2622 'd':917 'data':339,911,970,1095,1105,1130,1138,1487,1515,1648,2209,2408,2464,2984,3026 'dataset':986 'date':264,369,379,1144,1254,1278,1283,1296,1299,1316,1320,1386,1541,1615,1665,1670,1697,1854,2250,2260,2318,2349,2410,2619,2623,2627 'date/time':2443,2528 'dd':1701 'decemb':1267 'declar':759 'deep':2674 'defin':235,392 'definit':2507 'delimit':470 'deliv':2596 'deploy':2751 'deriv':1486,1647,2463,2551,2983 'describ':1208 'descript':112,784 'design':1038,1237,2599 'detail':2075 'detect':85,619,647,676,1942,2530,2742,2927 'determin':117,874,1839 'determinist':193,415,633,1989 'discoveri':2969 'discrep':1168 'distinct':638 'doc':781,1601,1929,1937,2703 'docs/clarity_gate_format_spec.md':209 'document':15,28,50,59,76,397,511,563,736,766,772,787,804,1149,1253,1295,1526,1581,1619,1621,1787,2002,2114,2125,2175,2423,2660,2670,2710,2773 'document-sha256':562,1580,1786,2772 'document_hash.py':191,2727,2861 'documentation-first':2709 'doesn':2310 'dot':1968 'e':165,177,182,278,295,326,334,343,350,357,366,376,2196,2204,2213,2224,2238,2247,2257,2839,2851,2899 'e-sc06':176,277,2850 'e-st10':164,294,2838 'e-tb':2898 'e-tb01':181,325,2195 'e-tb02':333,2203 'e-tb03':342,2212 'e-tb04':349,2223 'e-tb05':356,2237 'e-tb06':365,2246 'e-tb07':375,2256 'e.g':272,1732 'eb357742':508 'element':1677 'empti':359,1749,2240 'end':1750,2740,2948 'enforc':46,89,659,686,900,998,1894 'ensur':14,90,928 'enter':20,51 'entir':2137 'epistem':9,47,663,937,1624,2701,3022 'equat':1358 'equivoc':2438 'error':281,287,304,332,341,348,355,364,374,385,2202,2211,2222,2236,2245,2255,2266,2901 'escap':1816 'est':1120 'estim':790,994,1036,1823,1830,2589 'etc':1475,2062 'evalu':2680 'event':1304 'everi':949 'evid':1179,1934 'exact':590 'exampl':675,907,1343,1920,1973,2871 'except':1722,2112,2116,2120 'exceptions-id':2119 'exceptions-reason':2115 'exclud':2066 'exclus':1784,1805,1812,2050,2127,2367,2377 'exclusions-coverag':1804 'exist':160,303,532,639,877,1414,2833 'expect':1029,1037 'explan':1170 'explicit':122,1052,1124,1165,1845,1886 'export':2930 'express':656,668 'extens':1461,2962 'extern':1326,1396,1459,2327,2448,2547,2637,2649,3003 'extract':554,1409 'extrapol':1516 'f0':1983 'fact':82,733,947,1146,1335,2516,2541,3046 'fact-check':1334,2540 'factual':2686 'fail':959,1005,1053,1263 'fals':746,2490 'featur':111,1022,1027,2931 'features/1':505 'fenc':2738,2783,2924 'fence-awar':2737,2923 'fence-track':2782 'field':119,124,126,265,885,1685,1766,1841,1847,1875,1883,1888,1889,1905,1910,2803,2807 'figur':1444 'file':35,852,862,2155 'filenam':2424 'final':588 'financi':1470 'find':86,96,683,871,913 'first':476,2231,2711 'fix':988,1033,1079,1117,1161,1190,1231,1314,1380,2434,2441,2447,2518,2526,2726,2736,2748 'flag':697,1107,1151,1181,1216,1322,1339,2323,2471,2635,2641,2647 'focus':940 'form':707 'format':66,139,179,206,220,244,370,405,418,516,1519,1529,1702,1956,2160,2170,2251,2414,2731,2818,2853,2865,2887,2914,2937,2950,2957 'forward':1000 'forward-look':999 'found':135,1492,1511,1933,2426,2814 'fraction':1808 'francesco':1612,3064 'frequent':2400 'fresh':1309 'friend':2015 'frontmatt':568,1681,2123,2883 'full':521,2730 'function':2760 'futur':381,1204,2262,2313 'future/conditional':1233 'gate':3,27,37,58,65,205,234,658,696,705,740,1525,1536,1672,1688,1757,2418,2421,2886 'general':1399,1958 'generat':434,2042 'git':1472 'github.com':2705,2714 'github.com/frmoretto/source-of-truth-creator':2704 'github.com/frmoretto/stream-coding':2713 'grace':384,2265 'graphql':504 'guess':1119 'guid':820 'guidanc':140,2819 'hallucin':105,732,2431 'hand':802 'hash':142,424,474,514,525,533,540,621,632,1794,1977,2039 'hash-bas':141,423,1976,2038 'hasn':1227 'haven':797 'hc01':172,257,1873,1881,2846 'hc02':175,269,1945,2849 'header':2594 'hedg':681,691,840 'hedgehunt':644 'hex':478,1793,2025,2034 'hierarchi':1407 'hitl':153,247,284,298,314,429,749,890,893,1394,1422,1481,1503,1556,1560,1585,1642,1659,1715,1724,1741,1758,2108,2477,2482,2545,2690,2827,2935,2978,2989,3045 'hitl-claim':283,313,1584,1740,2934 'hitl-pending-count':892,1559,1723 'hitl-status':889,1555,1714,2107 'html':1752,2952 'human':751,829,1495,1512,1549,1860,1865,2014,2484 'human-friend':2013 'human-in-the-loop':750 'hyphen':1970 'hypothes':792 'hypothesi':945,992,1193,1200,2514 'hypothet':958 'id':138,144,427,436,487,500,1587,1955,2026,2041,2081,2102,2121,2817,2941 'ident':631 'implement':198,2729,2757 'impli':1176,2304 'implicit':1045,1172 'import':2124 'improv':978,983,1184,1197 'includ':411,2409 'inconsist':2529 'industri':273,1948 'ingest':6,42,765,1571,1769,2133,2140 'initi':3052 'insid':1811,2375 'instead':1402 'integ':1727 'integr':1796 'intend':1040,2601 'interfac':1462 'intern':1259,1301,1442 'interpret':1049,1497 'invalid':368,1868,1876,2249 'isn':670,693 'issu':876,879,2425,2432,2439,2444,2445 'januari':1275 'judgment':828 'key':637 'knowledg':21,53 'label':948 'last':1265,1273,2235,2617 'leav':2069 'legaci':2060,2073 'level':2344,2505,2506 'lf':592,611,615 'licens':3067 'like':641,835,1103,1628,1822,1947,2493,2512 'limit':703 'line':565,580,1755 'linear':1058,1062 'link':2675 'list':1743 'llm':73,730,806,2510,2522 'load':1077 'locat':203,467,1602,2433,2440,2446,2945 'look':1001,1093,1102 'loop':754 'low':1400 'lowercas':1792 'mac':617 'mandatori':157,757,1483,2830,3048 'manual':1579,1774 'map':2906 'marinoni':3065 'mark':717,918,954,2063,2568,2587 'markdown':2072 'marker':100,649,744,990,997,1390,1625,1751,1821,2380,2741,2917,2926,2949 'match':312,2083 'may':390,684,1196,1359,1377,1747 'mean':1855,1911 'measur':984,1104,1129 'mechan':1817 'methodolog':783,2712 'might':2523 'misinterpret':2524 'mismatch':1451 'misread':2474 'miss':98,297,347,2217 'mistak':79 'mm':1700 'mode':3014 'model':975,980 'moretto':3066 'multi':2966 'multi-platform':2965 'multilin':571,2777 'must':951,1050,1257,2082,2113,2372,2517 'my-doc.cgd.md':528,537 'n':558 'name':1669,1707 'need':1369,1506,2483,2574,2615 'nest':2097 'new':108,161,2788,2835 'newlin':584,589,2764 'nfc':595,2766 'normal':459,544,587,596,604,2767 'normat':404 'note':210,386,1166,2921 'number':844,915,1111,1122,1143,1330,2325,2427,2625 'numer':1456 'offer':1375 'old':616 'one':1155 'open':557 'option':228,1381,1807 'optional/computed':1765 'order':353,1290,1306,2227,2630 'outcom':1210 'outdat':1379 'outperform':963,967 'output':447,529,538,849,1518,2413,2870,2913,3013 'outsid':625,2366 'overlap':2099 'owner':2345 'page':1938 'paper':1354,2718 'pars':1826 'part':401 'partial':258,1874,1882,2139 'pass':539,738,760,960,1006,1054,1264,1429,1566,1731,2563,2566 'pattern':1959,1972,2578 'pend':130,894,1561,1717,1725,1856,1921,2502 'pending/verified':116,2801 'per':243,417,431,515,550,579,1223,1348,1530,1678,2162,2745 'percentag':1099,2581 'pipe':469 'plan':1600,1928,1936 'planned/hoped':1209 'platform':603,635,2967 'plausibl':1187,1262 'point':811,819,873,909,941,1134,1247,1565,1730,2169,2270,2274,2279,2405,2908,2996,3001,3020,3056 'point-in-tim':2404 'points-pass':1564,1729 'possibl':685 'practic':95 'pre':5,41 'pre-ingest':4,40 'prefer':145,1979 'prefix':481,1694 'presenc':120,661,1842,1890,2804 'present':608,651,1207,1863,1864,1869,1878,2315 'prevent':620 'price':440,445,489,494,1345,1351,2457,2634 'principl':84 'probabl':2017 'process':1219,1239,1540,1546,1696,1704 'processed-bi':1545,1703 'processed-d':1539,1695 'processor':1706 'produc':23,55,630,1521,2496 'project':789,991,1015,1035,1126,1593,1605,1636,1641,2593,2692,2693 'promot':2348,2351 'promoted-bi':2350 'promoted-d':2347 'prompt':1183,1195 'proper':17,716 'prose':1454,2061 'protect':2744,2920 'provid':1465,1902,2597 'publish':794 'purpos':39,2694 'python':412,437,454,526,534,546 'q3':1599,1927,1935,2012 'q4':1012,1020 'qualif':2616 'qualifi':18,1004,1321 'qualiti':10,48,824,1131,1186,1199,2166,2268,2682,3027 'question':70,674,834 'quick':2555,2575 'quin':2743,2919 'rag':12,52,768,1570,1768,2132 'rag-ingest':1569,1767,2131 'rates/ratios':1363 'rather':2067 're':2135 'read':74 'reason':2117,2488 'recheck':2393 'recommend':2036 'reconcil':1162 'record':155,300,881,1644,1760,2829 'red':1106,1150,1180,1215 'redact':2929 'reduc':1024,1031 'refer':200,1308,2677,2863 'refram':1191 'reject':1436,2136 'relat':2691 'relationship':812 'releas':3053 'remov':561,606,2775 'repli':2468 'report':274,1949,2419 'request':1222,3038 'requir':152,345,362,664,827,1003,1675,1684,1789,2077,2106,2183,2215,2243,2332,2335,2479,2559,2689,2826 'research':1366,1950 'resist':1992,2049 'resolv':924,2056 'respons':1067,1071,1185,1198 'restructur':2669,2963,3019 'result':2422 'revenu':698,1007,1013,1592,1604,1629,1634,2011 'revenue-project':1603 'review':822,847,933,1550,1558,1674,1718,1720,1764,1781,2079,2110 'rfc':394 'risk':728,1344 'round':1427,1431,1433,1480,1484,1500,1607,1645,1656,2461,2475,2549,2557,2946,2977,2981,2986 'rout':1246,1392,2543 'row':309,340,2210 'rps':1244 'rule':858,903,925,1803,2080,2146,2173,2905,2909 'run':451,543,2416 'safe':2389 'sc06':178,279,2852 'scale':149,1057,1061 'scan':1140,2576 'schema':280,2940 'scientif':2717 'script':188,408,413,2859 'scripts/claim_id.py':420,438,455,2044 'scripts/document_hash.py':509,527,535,547 'search':1397,2548 'second':1224 'section':156,331,1156,2187,2201,2358 'see':1798,2141 'self':1893 'self-enforc':1892 'semant':127,241,821,865,870,1906,2003,2800,2808 'sequenti':1993 'session':807,1494 'set':1578,1775,1899 'sever':254,293,324,2194,2504 'sha':472,512,599 'sha256':564,1582,1788,2774 'share':771 'shorter':1182,1194 'show':1776 'simpl':2001 'singl':218,2755,2960 'skill':197,410,711,2157,2653,2968 'skill-clarity-gate' 'sme':2058,2078 'snapshot':2385,2403 'solut':748 'sot':31,185,215,221,318,2147,2174,2277,2280,2330,2336,2894 'sot-specif':2329 'sourc':32,125,129,271,743,1116,1384,1411,1469,1491,1510,1598,1652,1655,1904,1909,1918,1941,1946,2152,2220,2363,2467,2554,2585,2696,2806,2944,3035 'source-sickn33' 'source/citation':2643 'spec':180,245,406,419,517,814,1679,1799,2732,2854,2866,2958,3060 'specif':67,195,201,779,1098,1110,1329,2324,2331,2535,2580,2888 'st10':166,296,2840 'st11':169,307,2843 'stabl':422,2382,2388 'stale':1323,2379 'standard':1076 'state':780,884,897,1205,1848,1916,1917,2312 'statement':1002 'statist':1353 'status':115,123,888,891,921,1553,1557,1662,1710,1716,1754,1762,1833,1837,1846,1887,1900,2109,2799 'step':3039 'still':935 'stream':2663,2707 'strip':461,576,2763 'structur':151,239,286,289,627,863,902,1468,2172,2353,2825 'style':2954 'sub':1292 'sub-check':1291 'suggest':2453 'suit':815 'support':503,573,2779,2896 'system':13,44,769,776,1056,1060,1218,1235,1471,2980 'tabl':308,319,336,972,1096,1108,1452,2191,2206,2298,2309,2355,2365,2371,2591 'take':475 'target':1241 'tb':2900 'tb01':183,327,2197 'tb02':335,2205 'tb03':344,2214 'tb04':351,2225 'tb05':358,2239 'tb06':367,2248 'tb07':377,2258 'tbd':275,1951 'templat':2915 'tempor':1251,2442,2527,2998 'test':452,456,484,545,548,2785,2789 'text':460,653,679,1446,1591,2942 'tier':229,1417,1420,1437,1476,2180,2333,2341 'time':1068,1072,2407 'timestamp':1256 'titl':1620 'today':1312 'tool':640,672,1690 'topic-agent-skills' 'topic-agentic-skills' 'topic-ai-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workflows' 'topic-antigravity' 'topic-antigravity-skills' 'topic-claude-code' 'topic-claude-code-skills' 'topic-codex-cli' 'topic-codex-skills' 'total':2791 'track':430,2784 'trail':577,2761 'treat':2513 'trigger':1825,1952 'true':727,1502,1572,1658,1777,2489,2560,2988 'truth':34,709,1413,1499,2154,2698,3037 'two':1426,1479,2976 'two-round':1425,1478,2975 'type':673,1342,2452,2661 'typic':2640 'uncertain':719 'uncertainti':99,648,655,666,996,1389 'unclear':922,936,1713 'underscor':1969 'unifi':207,212,2891,2956 'unproven':1189 'unscientifi':642 'unscientify/hedgehunter':682 'unsupport':2305 'untest':993 'unvalid':1094 'unverifi':1640 'updat':1266,1274,1315,2533,2618,2862,2868,2933,2947,2955 'url':2695 'use':468,763,1232,1367,1527,1974,2032,2037,2103,2381,2520,2598,2662 'user':1066,1153,1158,1464 'user-provid':1463 'utf':593 'v':1693 'v1.0':3049 'v1.0.0':1277 'v1.1':3040 'v1.1.0':1282 'v1.2':3030 'v1.3':3015 'v1.4':3006 'v1.5':2991 'v1.6':2970 'v2.0':211,2889,2939,2959 'v2.0.0':2875 'v2.1':38,68,110,208,246,1532,1834,1907,1957,2867 'v2.1.0':2792 'v2.1.3':2722 'vagu':270,1940 'valid':30,162,186,231,236,249,320,388,800,861,956,1202,1575,1772,2148,2150,2190,2605,2836,2895,2904 'valu':1127,1596,2219,2296,2362,2943 'variat':629 'vector':453,485,2786 'verdict':2501 'verif':7,43,154,299,755,810,818,1245,1341,1406,1424,1428,1440,1460,1482,1504,1508,1643,1660,1759,1797,1836,1861,2273,2454,2478,2561,2638,2650,2719,2828,2979,2990,3047,3057 'verifi':136,329,372,378,531,536,541,706,722,1327,1663,1745,1862,1924,1930,2185,2199,2221,2233,2253,2259,2287,2291,2356,2364,2369,2395,2402,2449,2460,2531,2534,2571,2607,2628,3004 'version':202,1287,1303,1537,1689,1691,2346,2500,2624,2873,3058,3061 'visibl':1044 'volatil':2384,2398 'vs':131,946,1297,1445,1449,1453,2810 'w':168,171,174,256,268,306,1872,1880,1944,2842,2845,2848 'w-hc01':170,255,1871,1879,2844 'w-hc02':173,267,1943,2847 'w-st11':167,305,2841 'warn':266,276,317,1125,1953,2435,2521 'what-was-found':132,2811 'whether':713 'whitespac':463,578,628,2762 'who/when':1903 'wild':1361 'window':612 'wit':2553 'within':1147 'without':1115,1178,1824,1901,2392,2564 'would':2491 'wrap':1827 'write':778,1819,2681 'wrong':354,2228 'x':987,1084,1368,2633 'x.xx':2631 'y':1087,1376 'yaml':567,1533,1680,2770,2882 'yaml-awar':2769 'yes':1415 'yyyi':1699 'yyyy-mm-dd':1698 'z':1089 'z0':1963,2007,2087,2092 'za':2086,2091","prices":[{"id":"4287af48-0c2b-4197-93ca-5f8a71d58d9c","listingId":"875ce989-cee3-4114-a96e-9a1543a7bb8d","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sickn33","category":"antigravity-awesome-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:34:16.366Z"}],"sources":[{"listingId":"875ce989-cee3-4114-a96e-9a1543a7bb8d","source":"github","sourceId":"sickn33/antigravity-awesome-skills/clarity-gate","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/clarity-gate","isPrimary":false,"firstSeenAt":"2026-04-18T21:34:16.366Z","lastSeenAt":"2026-04-24T12:50:45.373Z"}],"details":{"listingId":"875ce989-cee3-4114-a96e-9a1543a7bb8d","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"clarity-gate","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34882,"topics":["agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity","antigravity-skills","claude-code","claude-code-skills","codex-cli","codex-skills","cursor","cursor-skills","developer-tools","gemini-cli","gemini-skills","kiro","mcp","skill-library"],"license":"mit","html_url":"https://github.com/sickn33/antigravity-awesome-skills","pushed_at":"2026-04-24T06:41:17Z","description":"Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.","skill_md_sha":"5349701a8f4aec4c77435177202cf468e6e62f4e","skill_md_path":"skills/clarity-gate/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/clarity-gate"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"clarity-gate","license":"CC-BY-4.0","description":"Pre-ingestion verification for epistemic quality in RAG systems. Ensures documents are properly qualified before entering knowledge bases. Produces CGD (Clarity-Gated Documents) and validates SOT (Source of Truth) files."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/clarity-gate"},"updatedAt":"2026-04-24T12:50:45.373Z"}}