learn
免费[Utilities] Use when teaching Claude a lesson that persists across sessions, including an extra rule for one skill or task kind (routes to project-skill-protocol).
中文简介正在准备中。当前显示原文说明。
[Utilities] Use when teaching Claude a lesson that persists across sessions, including an extra rule for one skill or task kind (routes to project-skill-protocol).
中文简介正在准备中。当前显示原文说明。
[Quality] Use when a workflow step or the user asks for linters, formatters, type checks and static analysis in pre-commit and CI gates.
中文简介正在准备中。当前显示原文说明。
[Decision Support] Use when pressure-testing an irreversible, high-stakes decision with adversarial AI advisors.
中文简介正在准备中。当前显示原文说明。
[Quality] Use when a workflow step or the user asks for an agent quality harness with project guidance and automated/review feedback.
中文简介正在准备中。当前显示原文说明。
[Debugging] Use when a workflow step or the user asks for performance bottleneck analysis and validated fixes: queries, memory, network, rendering and concurrency.
中文简介正在准备中。当前显示原文说明。
[Planning] Use when a workflow step or the user asks for implementation planning. --mode=review supports review-only or --fix-loop; validate interviews, execute implements. --mode=ci plans CI fixes; --mode=cro plans conversion optimization.
中文简介正在准备中。当前显示原文说明。
[Git] Use when generating developer KPI, contribution, effort point, man-day or code-quality reports from git history.
中文简介正在准备中。当前显示原文说明。
[Code Quality] Use when a workflow step or the user asks for service/API readiness: observability, reliability, data integrity and database performance.
中文简介正在准备中。当前显示原文说明。
[Utilities] Use when setting up or re-evaluating portable project context end to end: project-config, reference docs, CLAUDE.md, AGENTS.md. One piece only: project-config, docs-manager --mode=init or ai-context-refresh.
中文简介正在准备中。当前显示原文说明。
[Skill Management] Use when enhancing, compressing or expanding prompts, docs or skills. --op={compress|expand|enhance}.
中文简介正在准备中。当前显示原文说明。
[Research] Use when a workflow step or the user asks for market analysis: competitors, TAM/SAM/SOM, trends, SWOT and customer segments.
中文简介正在准备中。当前显示原文说明。
[Utilities] Use when a project adds, changes, lists or removes its OWN protocol rules layered over a framework skill (additive only). list | add | update | delete.
中文简介正在准备中。当前显示原文说明。
[Research] Use when a workflow step or the user asks for knowledge artifact review: completeness, citation accuracy, confidence and template compliance.
中文简介正在准备中。当前显示原文说明。
[Project Management] Use when a workflow step or the user asks for planned-work prioritization using RICE, MoSCoW or Value-Effort ranking.
中文简介正在准备中。当前显示原文说明。
[Implementation] Use when a workflow step or the user asks for root-cause fixes with regression coverage. --target={ci|issue|logs|review|test|types|ui} scopes the issue.
中文简介正在准备中。当前显示原文说明。
[Git] Use when resolving git merge, cherry-pick, rebase or stash-apply conflicts, with backup and analysis.
中文简介正在准备中。当前显示原文说明。
[Utilities] Use when syncing the project-config file (default docs/project-config.json) with the current workspace structure. Not reference docs (scan) or CLAUDE.md (ai-context-refresh).
中文简介正在准备中。当前显示原文说明。
[Code Quality] Use when analyzing npm package upgrades, outdated dependencies or breaking changes and preparing a phased upgrade plan.
中文简介正在准备中。当前显示原文说明。
[Testing] Use when a workflow step or the user asks for integration test generation, diagnosis or traceability checks. --mode=review checks test quality; --mode=verify runs tests, with optional --fix-loop.
中文简介正在准备中。当前显示原文说明。
[Implementation] Use when the user asks to build a feature from an idea or description with no plan file yet: research and trace the code, create and get the plan approved, build each phase with its tests, review, verify once, sync specs and docs. Existing plan: plan --mode=execute.
中文简介正在准备中。当前显示原文说明。
[Documentation] Use when a workflow step or the user asks for a standalone HTML stakeholder deck combining specs, tasks, initiatives and mockups with journey demos.
中文简介正在准备中。当前显示原文说明。
[Architecture] Use when a workflow step or the user asks for DDD domain modeling: contexts, aggregates, entities, ERD and events. --mode=review checks entity and value-object design.
中文简介正在准备中。当前显示原文说明。
[AI & Tools] Use when creating, verifying, or enhancing Claude Code custom agent files.
中文简介正在准备中。当前显示原文说明。
[Content] Use when a workflow step or the user asks for business viability: Business Model Canvas, financials, risks and go-to-market recommendation.
中文简介正在准备中。当前显示原文说明。