Evaluates Claude Agent Skills on 10 quality axes with letter grades (A+ through F) and specific improvement recommendations.
Discover, search, and install shared skills from the Skill Hub registry. Use when the user wants to find available skills, share a skill with other bots, or install a skill from…
Score and improve a skill folder (must contain SKILL.md). Triggers on: "评估/inspect/audit/score this skill", "detailed mode/展开", "apply recommendations/应用推荐", "run evals/跑测试",…
**GUIDE SKILL** — Guide to the Skill Manager for Copilot extension. USE FOR: adding/removing skill repos, syncing skills, pushing feedback, configuring sync intervals,…
Migrate legacy .claude/commands/ to .claude/skills/ directory structure. Actions: discover, analyze, migrate, audit, validate, fix.
Обновление SSOT-ссылки, параметров или деактивация существующего скилла. Используй при изменении SSOT-инструкции, переименовании скилла или выводе из эксплуатации.
Instagram 카드뉴스 자동 생성 프로젝트를 현재 폴더에 세팅합니다. 빈 폴더에서 /card-news-setup을 실행하면 팀 에이전트 기반 카드뉴스 파이프라인(리서치→검증→카피→토론→렌더링→검토)이 완성됩니다.
Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert
Creates a new GitHub Copilot skill folder with a valid SKILL.md, a human-readable README.md, and an index entry in the repository root README.
Pick the right Claude Code skill for a task. Ranks installed skills, emits a routing plan, and falls back to web discovery if nothing matches.
Проверка SKILL.md на соответствие стандарту — frontmatter, секции, SSOT-ссылка, размер. Используй после создания или изменения скилла, при code review или массовой валидации всех…
基于文档的项目控制系统，让任何 AI 智能体或人类仅通过读取文件就能恢复项目工作状态——无需外部记忆。当用户需要管理长期项目、跨 session 追踪进度、context 丢失后恢复状态、多智能体协作、审计项目文档健康状况、或避免忘记上次做到哪里时，应使用本 skill。触发场景：'/doc-harness init' 与 '/doc-harness…
Creates Claude subagents equipped with curated skills for solving problems within DAG workflows. Use when designing a specialist subagent, selecting skills for a subagent, writing…
Weekly audit of `.agents/skills/*/SKILL.md` — surfaces duplicate / overlapping / stale skills, inconsistent descriptions, broken cross-references, and merge/delete candidates.
Process unhandled Slack messages as Claudicle with persistent memory. Loads user models and soul state, posts terminal-styled thinking messages, generates cognitive-step…
Audit current sleep pattern, prescribe a 14-day routine + environment + light/caffeine timing protocol, with a re-measurement checklist.
Use when the user invokes /slim-task or requests structured multi-phase task execution (structured task, SOP execution, parallel sub-agent dispatch) with blind-audit quality…
AUTO-TRIGGER: Apply this skill when the user is managing a small team of two to six direct reports in a marketing, demand gen, or RevOps function.
数据分析员工（Data Analyst Agent）的唯一总入口：凡与数据资产、取数、指标、表/视图、 治理职责、知识网络等相关的问题，必须先经本 skill 做编排与路由，再进入找表或问数等子流程。 当用户提出数据类问题、需要知识网络选择、或需要在找表与问数之间切换时使用。
GitHub Issue の実装計画を作成・更新する。コードベースを分析し、影響範囲・実装手順・リスクを整理して Issue コメントまたは新規 Issue として投稿する。 ユーザーが「計画立てて」「実装計画」「設計して」「#123 の計画」「/smart-issue-plan #123」と言ったら起動する。…
GitHub Issue ID を受け取り、Issue を読み込んでブランチを作成・チェックアウトし、実装に着手する。 既存の実装計画（smart-issue-plan が作成したコメント or `[実装計画]` Issue）があれば参照する。 作業完了後に smart-commit の使用を提案する（勝手にコミット・push はしない）。…
現在のブランチから GitHub Pull Request を作成または更新する。作業内容の自動要約・ラベル付与・関連 Issue 紐づけを行う。 必要に応じてデフォルトブランチを現在のブランチへマージしてから push する（副作用あり）。 「PR 作って」「プルリク作成」「PR 更新して」「/smart-pr」と言ったら起動する。…
Build an evidence-rated supplement stack with timing, dose, cycling, and interaction warnings. Food-first; flags risky combinations and pregnancy/medication concerns.
Manage a deferred task queue — add, list, process, remove, batch-execute, schedule, prioritize, and browse history of tasks stored in the vault.
Claude Code plugin to capture screenshots of web pages, components, and extract site assets as optimized PNG+WebP.
Use when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.
Run the full diagnostic pipeline on a foreign system. Intake → Diagnose → Prescribe, with mandatory human gates between each step. Skipping a step is not allowed.
Multi-language SOLID detection rules. Project type detection, interface locations, file size limits per language.
Find files with code duplications in a SonarQube project and inspect duplication blocks for a file (project key optional when MCP integration already defines the default project)
灵魂唤醒室 — 从多源数据中唤醒四维灵魂画像。 当用户说"帮我唤醒/蒸馏/创建一个 Relic"或直接调用 /relic-forge 时触发。 支持人类、宠物、关系、地方、团队、时刻等万物蒸馏。
Run the SPARC Specification phase — gather requirements, define acceptance criteria, identify constraints, and store the spec in memory
Spawn a sandboxed background Claude session in a new git worktree. Filesystem-isolated with network restricted to package registries.
Vocalize Claude's last response using local Qwen3-TTS. Default voice is the Oracle (deep, resonant Dune narrator). Use --preset for emotion-controlled preset speakers.
Closes the spec GitHub Issue and optionally closes its linked task issues. Use when a feature is cancelled or no longer being pursued.
Add specs, conventions, constraints, or learnings to project guidelines interactively or automatically
Backfill @spec annotations on existing code for an APPROVED spec (or --all specs)
Brainstorm and write a design spec for a new feature. Saves to zie-framework/specs/.
Orchestrate session data mining operations through a 7-phase workflow with structural anti-skip enforcement.
Generate self-contained collaboration documents for sharing issues with external AI systems (Gemini, ChatGPT, etc.) with structural anti-skip enforcement (Execute-Verify-Record…
Validate epic-to-story coverage with gap detection and batch story creation using structural anti-skip enforcement.
Validates code quality through spec-driven QA validation with structural anti-skip enforcement. Replicates all 6 phases of the DevForgeAI QA workflow using the Execute-Verify-Gate…
Process QA gap files and create remediation user stories with structural anti-skip enforcement (Execute-Verify-Gate pattern at every step).
Unified root cause analysis with 4-layer anti-skip enforcement for both tactical (dev workflow diagnosis) and strategic (5 Whys RCA documents) modes.
Apply automated and guided fixes to story, epic, and context files based on structured audit findings with 4-layer anti-skip enforcement.
Generate front-end UI specifications, code, and a framework-agnostic Design Source of Truth (design.md) for Web, GUI, or Terminal interfaces through a constraint-aware 9-phase…
W3 compliance scanning with structural anti-skip enforcement. Detects auto-skill chaining violations (skills/commands that auto-invoke other skills without user approval) using…
Use when: enumerating edge cases for a feature spec, user story, or behavior description before implementation: empty and boundary inputs, error paths, permissions, concurrency,…
Execute implementation specs with batched checkpoints. Follows specs exactly, stops on blockers, supports parallelization.
spec-check の Finding を元に仕様書または実装を双方向に自動修正する。修正方向は Finding 種別とヒューリスティクス（堅牢性、テスト存在、git blame 等）で判定。`--loop` で差分0まで反復可能（旧 spec-cycle 後継）。USE WHEN spec-check…
Generate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting th — from…
Orchestrate the implement-review loop for Spec Kitty work packages using any configured agent. Covers agent dispatch, state transitions, rejection cycles, arbiter escalation, and…
Finds the next actionable task for a spec by checking GitHub Issue status. Use when the user wants to know what to work on next.
Initialize project-level state and configure specs via interactive questionnaire.
Translate a foreign spec (GSD or SpecKit) to IronSpec IR vault nodes. Detects source tool automatically, parses to IR, validates, and files to vault.
Deep-dive interview skill for creating comprehensive specifications. Reviews existing code and docs, then interviews the user through multiple rounds of targeted questions…
啟動實作流程。多個 engineer agent 背景並行認領 feature issues，同時 QA agent 根據 spec 撰寫 e2e test。觸發關鍵字："implement", "實作", "開發"。
Write the full patent specification from claims and invention disclosure. Use when user says \"撰写说明书\", \"write specification\", \"写说明书\", \"patent description\", or wants to…
Decompose a single-feature specification into a linear, phase-by-phase implementation plan. Use this for medium-complexity work — single feature, one or two components — where…
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.