Catalog
Every x402, MPP, MCP, and skill listing we've indexed, normalized, and enriched.
context-log
Create and update .opencode/context-log.md to preserve issue context and checkpoint history across compaction and session handoffs
code-quality
Load when reviewing a diff, naming a code smell or anti-pattern, deciding refactoring direction, or grading review-comment severity. Required reading when the architecture or code-review capabilities cite a named pattern — load explicitly rather than paraphrasing from memory.
chezmoi
Manage dotfiles via chezmoi — apply safely, destroy files, manage LaunchAgents and externals, config and template gotchas
attention
Energy and spoon check — come up for air, see what needs attention without breaking focus
architecture
Load before designing a new system, choosing between competing implementations, weighing tradeoffs across libraries or frameworks, or escalating an architectural question to a human. Fires at the moment a multi-option design decision appears, not during routine implementation.
majia-guanyuan
观远 BI（Guandata）全链路操作 — 数据查询/建卡/取数（Part A）、ETL 治理/写入/删除（Part B，含 SmartETL 全链路重写 + 字段使用度审计 + ExecPlan 工程化）、自定义图表 HTML/CSS/JS 注入与排障（Part C，含 V2.1.1 新增的 HTML 应用化看板生成 + selector 联动 descriptor patch）。当用户提到 营业额/门店/会员/订单/建卡/取数/报表/ETL/direct-save/payload_json/自定义图表/HTML 看板/应用化/更高级/不限标准看板/
self-review
Run a 4-pillar, 6-dimension alignment audit on the current project. Checks design currency, executes artifact verification, detects skill deposits. Use when the user says "self-review", "审视一下", or "audit". Report-only — never auto-fix.
idx-md
AgentSkill for https://idx.md. Use the index to locate AI agent library topics and fetch HEAD/BODY markdown.
arbitrum-dapp-skill
Opinionated guide for building dApps on Arbitrum using Stylus (Rust) and/or Solidity. Covers local devnode setup, contract development, testing, deployment, and React frontend integration with viem. Use when starting a new Arbitrum project, writing Stylus or Solidity contracts, d
using-arch-compiler
Use when starting architecture work and you need to decide whether to compile/finalise architecture or implement an already-approved architecture.
implementing-architecture
Use when: about to write code and docs/architecture/ exists with STATUS: APPROVED in architecture.yaml. Not when: no approved architecture yet (use compiling-architecture first), or architecture.yaml lacks STATUS: APPROVED header.
compiling-architecture
Use when: user wants to select architecture patterns, compile a spec, iterate on constraints/NFRs, audit why patterns were selected/rejected, or finalise an architecture for implementation. Not when: no repeatable decisions needed, or constraints/NFRs are not yet known (gather th
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
climate-generator
Generate Go CLIs from OpenAPI 3.x specs with climate, inspect generated CLIs, and emit Markdown skill prompts so those CLIs can be attached to agent workflows.
validate-usercontext-instructions
Validate user-context instruction files against schema, section completeness, quality checks, and scoring criteria.
validate-skill
Validate SKILL.md artifacts for schema, quality, safety, portability, and scoring compliance.
validate-project-instructions
Validate project-context AGENTS.md files for required sections, session-state model completeness, role quality, and scoring compliance.
validate-agents-md
Validate AGENTS.md files for structural completeness, operational contract coverage, neutrality, and repository alignment.
restore-checkpoint
Load a checkpoint artifact at session start and restore the session state it describes per spec section 4.4 restore rules. Use only when a checkpoint file is explicitly provided at the beginning of a session.
repository-drift-control
Enforce coordinated updates across specs, templates, prompts, samples, and docs to prevent repository guidance drift.