{"id":"9eb808c7-a201-432f-a535-bc45fb8b2569","shortId":"dTDuuT","kind":"skill","title":"zipai-optimizer","tagline":"Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware.","description":"# ZipAI: Context & Token Optimizer\n\n<rules>\n  <rule id=\"1\" name=\"Adaptive Verbosity\">\n    <instruction>\n      - **Ops/Fixes:** technical content only. No filler, no echo, no meta.\n      - **Architecture/Analysis:** full reasoning authorized and encouraged.\n      - **Direct questions:** one paragraph max unless exhaustive enumeration explicitly required.\n      - **Long sessions:** never re-summarize prior context. Assume developer retains full thread memory.\n    </instruction>\n  </rule>\n\n  <rule id=\"2\" name=\"Ambiguity-First Execution\">\n    <instruction>\n      Before producing output on any request with 2+ divergent interpretations: ask exactly ONE targeted question.\n      Never ask about obvious intent. Never stack multiple questions.\n      When uncertain between a minor variant and a full rewrite: default to minimal intervention and state the assumption made.\n    </instruction>\n  </rule>\n\n  <rule id=\"3\" name=\"Intelligent Input Filtering\">\n    <instruction>\n      Classify before ingesting — never read raw:\n\n      - **Builds/Installs (pip, npm, make, docker):** `grep -A 10 -B 10 -iE \"(error|fail|warn|fatal)\"`\n      - **Errors/Stacktraces (pytest, crashes, stderr):** `grep -A 10 -B 5 -iE \"(error|exception|traceback|failed|assert)\"`\n      - **Large source files (>300 lines):** locate with `grep -n \"def \\|class \"`, read with `view_range`.\n      - **JSON/YAML payloads:** `jq 'keys'` or `head -n 40` before committing to full read.\n      - **Files already read this session:** use cached in-context version. Do not re-read unless explicitly modified.\n      - **VCS Operations (git, gh):**\n        - `git log` → `| head -n 20` unless a specific range is requested.\n        - `git diff` >50 lines → `| grep -E \"^(\\+\\+\\+|---|@@|\\+|-)\"` to extract hunks only without artificial truncation.\n        - `git status` → read as-is.\n        - `git pull/push` with conflicts/errors → `grep -A 5 -B 2 \"CONFLICT\\|error\\|rejected\\|denied\"`.\n        - `git log --graph` → `| head -n 40`.\n      - **Context window pressure (session >80% capacity):** summarize resolved sub-problems into a single anchor block, drop their raw detail from active reasoning.\n    </instruction>\n  </rule>\n\n  <rule id=\"4\" name=\"Surgical Output\">\n    <instruction>\n      - Single-line fix → str_replace only, no reprint.\n      - Multi-location changes in one file → batch str_replace calls in dependency order within single response.\n      - Cross-file refactor → one file per response turn, labeled, in dependency order (leaf dependencies first).\n      - Complex structural diffs → unified diff format (`--- a/file / +++ b/file`) when str_replace would be ambiguous.\n      - Never silently bundle unrelated changes.\n    </instruction>\n  </rule>\n\n  <rule id=\"5\" name=\"Context Pruning & Response Structure\">\n    <instruction>\n      - Never restate the user's input.\n      - Lead with conclusion, follow with reasoning (inverted pyramid).\n      - Distinguish when relevant: `[FACT]` (verified) vs `[ASSUMPTION]` (inferred) vs `[RISK]` (potential side effect).\n      - If a response requires more than 3 sections, provide a structured summary at the top.\n    </instruction>\n  </rule>\n</rules>\n\n<negative_constraints>\n  - No filler: \"Here is\", \"I understand\", \"Let me\", \"Great question\", \"Certainly\", \"Of course\", \"Happy to help\".\n  - No blind truncation of stacktraces or error logs.\n  - No full-file reads when targeted grep/view_range suffices.\n  - No re-reading files already in context.\n  - No multi-question clarification dumps.\n  - No silent bundling of unrelated changes.\n  - No full git diff ingestion on large changesets — extract hunks only.\n  - No git log beyond 20 entries unless a specific range is requested.\n</negative_constraints>\n\n## Limitations\n- **Ideation Constrained:** Do not use this protocol during pure creative brainstorming or open-ended design phases where exhaustive exploration and maximum token verbosity are required.\n- **Log Blindness Risk:** Intelligent truncation via `grep` and `tail` may occasionally hide underlying root causes located outside the captured error boundaries.\n- **Context Overshadowing:** In extremely long sessions, aggressive anchor summarization might cause the agent to lose track of microscopic variable states dropped during context pruning.","tags":["zipai","optimizer","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows"],"capabilities":["skill","source-sickn33","skill-zipai-optimizer","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/zipai-optimizer","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 · 34404 github stars · SKILL.md body (4,274 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":"2026-04-22T00:52:02.028Z","embedding":null,"createdAt":"2026-04-18T21:48:00.224Z","updatedAt":"2026-04-22T00:52:02.028Z","lastSeenAt":"2026-04-22T00:52:02.028Z","tsv":"'10':121,123,135 '2':72,233 '20':199,438 '3':361 '300':147 '40':166,243 '5':137,231 '50':208 '80':248 'a/file':315 'activ':265 'adapt':4 'agent':506 'aggress':500 'alreadi':173,408 'ambigu':12,322 'ambiguity-first':11 'anchor':258,501 'architecture/analysis':35 'artifici':217 'as-i':222 'ask':75,81 'assert':143 'assum':59 'assumpt':106,348 'author':38 'awar':17,20 'b':122,136,232 'b/file':316 'batch':283 'beyond':437 'blind':387,474 'block':259 'boundari':493 'brainstorm':457 'builds/installs':114 'bundl':325,419 'cach':178 'call':286 'capac':249 'captur':491 'caus':487,504 'certain':380 'chang':279,327,422 'changeset':430 'clarif':415 'class':154 'classifi':108 'commit':168 'complex':309 'conclus':336 'conflict':234 'conflicts/errors':228 'constrain':448 'content':27 'context':15,22,58,181,244,410,494,516 'context-window-awar':14 'cours':382 'crash':131 'creativ':456 'cross':294 'cross-fil':293 'def':153 'default':99 'deni':237 'depend':288,304,307 'design':462 'detail':263 'develop':60 'diff':207,311,313,426 'direct':41 'distinguish':342 'diverg':73 'docker':118 'drop':260,514 'dump':416 'e':211 'echo':32 'effect':354 'encourag':40 'end':461 'entri':439 'enumer':48 'error':125,139,235,392,492 'errors/stacktraces':129 'exact':76 'except':140 'exhaust':47,465 'explicit':49,189 'explor':466 'extract':213,431 'extrem':497 'fact':345 'fail':126,142 'fatal':128 'file':146,172,282,295,298,397,407 'filler':30,371 'filter':8 'first':13,308 'fix':270 'follow':337 'format':314 'full':36,62,97,170,396,424 'full-fil':395 'gh':194 'git':193,195,206,219,225,238,425,435 'graph':240 'great':378 'grep':119,133,151,210,229,479 'grep/view_range':401 'happi':383 'head':164,197,241 'help':385 'hide':484 'hunk':214,432 'ideat':447 'ie':124,138 'in-context':179 'infer':349 'ingest':110,427 'input':333 'intellig':7,476 'intent':84 'interpret':74 'intervent':102 'invert':340 'jq':161 'json/yaml':159 'key':162 'label':302 'larg':144,429 'lead':334 'leaf':306 'let':376 'limit':446 'line':148,209,269 'locat':149,278,488 'log':196,239,393,436,473 'long':51,498 'lose':508 'made':107 'make':117 'max':45 'maximum':468 'may':482 'memori':64 'meta':34 'microscop':511 'might':503 'minim':101 'minor':93 'modifi':190 'multi':277,413 'multi-loc':276 'multi-quest':412 'multipl':87 'n':152,165,198,242 'never':53,80,85,111,323,328 'npm':116 'obvious':83 'occasion':483 'one':43,77,281,297 'open':460 'open-end':459 'oper':192 'ops/fixes':25 'optim':3,6,24 'order':289,305 'output':10,67 'outsid':489 'overshadow':495 'paragraph':44 'payload':160 'per':299 'phase':463 'pip':115 'potenti':352 'pressur':246 'prior':57 'problem':254 'produc':66 'protocol':453 'provid':363 'prune':517 'pull/push':226 'pure':455 'pyramid':341 'pytest':130 'question':42,79,88,379,414 'rang':158,203,443 'raw':113,262 're':55,186,405 're-read':185,404 're-summar':54 'read':112,155,171,174,187,221,398,406 'reason':37,266,339 'refactor':296 'reject':236 'relev':344 'replac':272,285,319 'reprint':275 'request':70,205,445 'requir':50,358,472 'resolv':251 'respons':292,300,357 'restat':329 'retain':61 'rewrit':98 'risk':351,475 'root':486 'section':362 'session':52,176,247,499 'side':353 'silent':324,418 'singl':257,268,291 'single-lin':267 'skill' 'skill-zipai-optimizer' 'sourc':145 'source-sickn33' 'specif':202,442 'stack':86 'stacktrac':390 'state':104,513 'status':220 'stderr':132 'str':271,284,318 'structur':310,365 'sub':253 'sub-problem':252 'suffic':402 'summar':56,250,502 'summari':366 'surgic':9 'tail':481 'target':78,400 'technic':26 'thread':63 'token':5,23,469 'top':369 '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' 'traceback':141 'track':509 'truncat':218,388,477 'turn':301 'uncertain':90 'under':485 'understand':375 'unifi':312 'unless':46,188,200,440 'unrel':326,421 'use':177,451 'user':331 'variabl':512 'variant':94 'vcs':19,191 'vcs-awar':18 'verbos':470 'verifi':346 'version':182 'via':478 'view':157 'vs':347,350 'warn':127 'window':16,245 'within':290 'without':216 'would':320 'zipai':2,21 'zipai-optim':1","prices":[{"id":"e0407a96-37a0-4793-9d58-b01ae60f6dc3","listingId":"9eb808c7-a201-432f-a535-bc45fb8b2569","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":"2026-04-18T21:48:00.224Z"}],"sources":[{"listingId":"9eb808c7-a201-432f-a535-bc45fb8b2569","source":"github","sourceId":"sickn33/antigravity-awesome-skills/zipai-optimizer","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/zipai-optimizer","isPrimary":false,"firstSeenAt":"2026-04-18T21:48:00.224Z","lastSeenAt":"2026-04-22T00:52:02.028Z"}],"details":{"listingId":"9eb808c7-a201-432f-a535-bc45fb8b2569","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"zipai-optimizer","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34404,"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":"2026-04-21T16:43:40Z","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":"5ed6ee20ff7241f77f4df317768035abb424a8fc","skill_md_path":"skills/zipai-optimizer/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/zipai-optimizer"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"zipai-optimizer","description":"Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/zipai-optimizer"},"updatedAt":"2026-04-22T00:52:02.028Z"}}