菜单
SkillsMP 已收集 ww-w-ai/marketplace 中的 22 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 22 / 22 个已收集 Skill。
Plan and execute multi-feature roadmaps as sequential, concurrent, or mixed sprint clusters. Trigger on sprint planning, run sprints, plan then build, /cowork-sprint, or requests to break an initiative into sprints. Do not use for trivial edits, one-shot…
原文语言：英语
USE for ANY single-feature build request. Trigger when the user asks to implement, build, add, or rework one feature end-to-end, supplies a feature Plan or Design for execution, explicitly requests PDCA, or asks to verify implementation completeness. Runs the…
原文语言：英语
Max plan hit the wall? Report your 5h window data — we're mapping the rate limit formula Anthropic won't publish
原文语言：英语
Cheaper and faster than /compact. Restores previous session context from Claude Code AND Codex transcripts by reading them directly — no LLM calls, no token cost. Also auto-loads a handoff written by /s-compact, if one exists. Triggers on "s-continue",…
原文语言：英语
Live token counter in your CLI. Shows real-time input/output/cache token counts in the Claude Code status bar
原文语言：英语
Know exactly what you spent. Interactive HTML dashboard with cost breakdown, token usage, and 5-hour window timeline across all sessions
原文语言：英语
Trigger whenever the user asks to commit AND wants the commit message enriched with AI collaboration history. Creates a lightweight commit message (key decision highlights + link) and a full directive-log file with conversation transcript + recap. The key…
原文语言：英语
One-time bootstrap of an existing project's docs/ into the cowork-doc-sync taxonomy. Trigger on init doc structure, relocate docs, organize existing docs, doc bootstrap, /cowork-doc-init, or implicit cues like "my docs/ is a mess, set up a structure", "fit…
原文语言：英语
Aligns a project's docs/ with the current code/decision state — call once at the very end, after implementation or refactoring is complete. Trigger on sync docs, align docs, organize docs, doc sync, /cowork-doc-sync, or implicit cues like "clean up the docs…
原文语言：英语
Invoke for "/cowork-insights" or requests to summarize, review, or report on past Claude Code or Codex sessions. Shows key prompts, outcomes, friction, tools, and actionable insights. DO NOT invoke for active tasks or commit-time recaps (use cowork-commit).
原文语言：英语
Compare DevMD files against actual source code. Measures coverage, accuracy, and consistency with deterministic counting and evidence-backed findings.
原文语言：英语
Interactive guide for writing DevMD files from scratch. Walks through files one by one in dependency order, asking the right questions to fill each template.
原文语言：英语
Analyze an existing codebase and generate DevMD spec files. Supports single-file or full-project mode. Language-aware discovery with self-verification.
原文语言：英语
Plan file-driven autonomous PDCA orchestrator. Extracts phases/steps from plan files, sequences bkit agents, and executes the full PDCA cycle. Supports multi-plan sequential execution, session resume, and wave-based parallelism. Not for simple bug fixes,…
原文语言：英语
Detects security vulnerabilities via static pattern matching based on OWASP Top 10
原文语言：英语
Detects inter-layer import rule violations (Clean Architecture)
原文语言：英语
Detects test anti-patterns based on behavior testing principles
原文语言：英语
Comprehensive project audit — runs all available validation skills, identifies gaps, and provides specific improvement recommendations
原文语言：英语
Progressive Discovery — Systematically analyzes project ideas through a structured workflow and transforms them into an actionable master plan
原文语言：英语
Validates CC configuration quality based on discovery (PASS/FAIL + statistics)
原文语言：英语
Validates code comment quality and TODO/FIXME formatting
原文语言：英语
Validates Git branch naming, commit messages, and protection rule compliance
原文语言：英语