セッションログ内の Skill 実行パターンを解析・検証するスキル。 ログフォーマットの変更検出、新パターンの発見、既知パターンとの差分確認に使う。 「ログパターン確認」「skill ログチェック」「ログ構造が変わったか確認」 「セッションログのスキル実行を調べて」と言われたら使う。
Check vendored skills for drift — whether our copy diverged from its baseline (local-drift) and whether upstream moved past our pinned commit (update-available).
Compares the locally installed version of a skill or subagent against its upstream source (sha or semver) and reports whether an update is available. Cache-aware (1-hour TTL).
Validate completed work passes all quality gates (lint, format, tests, docs, journal). Use after finishing implementation tasks to ensure nothing is missed.
Evaluates Claude skills against official best practices from Anthropic documentation. Use when reviewing skill quality, ensuring compliance with guidelines, or improving existing…
当用户明确要求搜索、安装、查看、卸载或创建 Skill，或内置 Skill / 工具出现能力缺口、无法完成当前任务时触发。通过 `mcp__skills__search_skills` 搜索并用 `mcp__skills__install_skill` 安装；已安装 Skill 的查看和删除通过产品清单导航到 Skills UI；没有合适结果时调用内置…
Play a chess game against the user over PGN files with the board rendered to images that Claude reads with vision.
Load when running a scheduled or on-demand skill audit. Reviews, audits, and health-checks all SKILL.md files for quality, duplication, dead links, and structural compliance.
Create or edit a Cindy Skill, search the SkillHub public marketplace or your organization's Skills, upload your own Skill, or publish a new version of a Skill you authored.
Use when verifying citations in a legal brief or document — extracts every citation locally via eyecite (document text never leaves the machine, important for privileged work…
Use when Codex should orchestrate Claude CLI as resumable, scoped subagents with file-backed logs kept out of git.
Report ground-truth Claude token consumption and estimated cost by parsing JSONL session files directly.
Use right after being corrected on something a CLAUDE.md file should already have told you, when explicitly asked to review CLAUDE.md, or periodically after a session with a lot…
Autonomous plan→implement pipeline invoked after a brainstorm has produced a spec. Codex (latest model, via `codex exec`) writes the plan and the implementation; a fresh Opus 4.7…
Control smart home devices via Homebridge Config UI X REST API. Use to list, turn on/off, adjust brightness, color, or temperature of HomeKit-compatible accessories.
Comprehensive backup, update, and restore workflow with dynamic workspace detection
Short-form video for AI agents. Generate videos using the latest models, pay with USDC via x402. — from dvcrn/openclaw-skills-marketplace
Short-form video for AI agents. Generate videos using the latest models, pay with USDC via x402. — from satoshistackalotto/skills
Short-form video for AI agents. Generate videos using the latest models, pay with USDC via x402. — from satoshistackalotto/skills
Search and install agent skills from ClawHub, the public skill registry. Use when the user asks to find, install, update, or list available skills. No API key needed.
Automatic context management with graceful handoff to a continuation subagent at 80% usage
What a master agent owns and can never delegate, and how to pick the model for a delegation from measured scores instead of memory.
Jason's placement, invocation and metadata conventions for creating or editing skills
Build students' capacity to read historical documents closely — attending to word choice, tone, and rhetoric as evidence of perspective.
Skill Chain Engine — compose skills into automated pipelines. One task triggers multi-skill workflows with progress tracking, auto-detection, and step management.
Repair or extend CodyMaster skills with a three-mode loop: FIX, DERIVED, and CAPTURED, grounded in current repo tooling.
Operational health review for CodyMaster skills using current repo signals: validate-skills, suggest, retro logs, memory, and test gates.
Progressive Disclosure skill index — efficient skill loading in 3 layers. Layer 1 (index, ~100 tokens) always loaded. Layer 2 (summary, ~300 tokens) loaded on context need.
Meta-skill for the Cody Master kit — when to invoke skills, how to create new skills, and skill discovery. Use at conversation start to establish skill discipline.
Find the best CodyMaster skill using the shipped indexes, profiles, docs, and contextual suggestions.
Package, review, export, and import CodyMaster skill folders safely across machines or teams.
List all project-local skills, subagents, and reference docs for the jnext repo with one-line descriptions.
Standardized code reading and analysis workflow with attention-driven focus. Provides clear objectives, deliverables, content outline, and token cost estimation.
Use when future codebase work needs a plan before implementation: split requirements into scoped executable tasks with owners, dependencies, validation gates, reject criteria, and…
Use AFTER verifying-spec passes and BEFORE generating-html during the initial-creation iteration loop of -implementation-plan.md ONLY.
Implementation subagent dispatch patterns. Use when independent implementation work is available and subagents can execute it.
Four-phase skill for planning and executing large-scale codebase migrations using full-context AI analysis.
Implement fixes for specific CodeRabbit review issues. Runs in isolated subagent context with focused task. Verifies fixes with tests before returning.
i-Willink 標準開発フローを Codex で実行するための 5 phase adapter。Claude Code の /build と同期し、Codex subagents はユーザーが明示した場合のみ使う。
Codex の使い方、CLI/app/IDE、rules・hooks・AGENTS.md・skills・subagents・config などを案内する。Codex や OpenAI 製品の仕様を答える前に必ず公式ドキュメントを確認し、rules/approval は `codex execpolicy check` で実検証すること。
[DEPRECATED] Run multiple AI agent threads in parallel with bounded concurrency. Use evolving-workflow instead.
Use when improving Codex-style task prompts, AGENTS.md instructions, review briefs, subagent handoffs, or implementation requests so they are precise, scoped, testable, and safe…
Codex-only skill administration for auditing, enabling, disabling, restoring, and verifying local Codex skills.
Curate Codex skills with a Hermes-style maintenance pass: usage telemetry, stale/archive candidates, pins, backups, dry-run reports, and rollback guidance.
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude).
Use after major visual changes to Codex Studio when a screenshot or local URL is available. Judges whether the rendered page reads as a senior 3D design portfolio or a generic…
Launch Codex CLI as an isolated subagent for bounded coding, review, or verification tasks.
Coordinate bounded agent work when delegation helps; define ownership, authority, handoffs, and integration.
Use when watching, monitoring, following, or supervising one or more live Codex tasks or threads by ID, including cursor-based transitions, completion or attention gates, claim…
Use for Codex work with clear excess-cost risk: broad or unpredictable logs and diffs, browser/UI loops, subagents, repeated compaction, or explicit usage audits.
Run OpenAI Codex CLI as a subagent for second opinions, code reviews, and questions. Use when you want a different AI model's perspective.
Co-Fundador Técnico — governança de produto, fases, ADRs, NFRs e delegação de subagentes para o GuitarGPT.
Recognition and mitigation of systematic reasoning errors documented in the heuristics and biases tradition.
Run ComfyUI workflows from any AI agent (Claude Code, OpenClaw, Codex, Hermes) via a single CLI. Import workflows, manage dependencies, execute across multiple servers, a — from…
核心能力: 沟通协作领域的专业化 AI 辅助工具,包含核心基础功能兼容. 面向需要comm skill tool相关能力的开发场景,包含结构化的工作流程和可复用的模板,帮助用户快速完成任务并保持代码质量。沟通助手基础版是 **沟通协作** 领域的 **FREE 版本** AI Skill,专为个人用户与轻量级场景设计。通过自然语言指令驱动 AI Agent…
核心能力: 沟通协作领域的专业化 AI 辅助工具,包含企业级高级功能兼容. 适合需要comm skill tool相关能力的开发场景,提供标准化流程和配置参考。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。适用于独立开发者、企业团队和自动化工作流场景。
Create automation command skills (slash commands) for Claude Code projects. Use when building `/slash-commands` that automate multi-step workflows - deploys, commits, releases,…
基于对话历史与情感线索,生成有同理心的上下文感知消息,提升沟通质量。Helps craft context-aware, empathetic messages by synthesizing conversation。触发关键词: empathetic, context, aware, communication, helps, craft, skill。
沟通辅助基础版(免费)。通过简化的3步流程(GATHER-CRAFT-REFINE)帮助用户快速撰写得体、结构清晰的回应消息. 核心能力:收集对话背景信息、按"承认-过渡-引导"单一结构组织回应、自我审视语气一致性. 适用于客户投诉回复、同事请求婉拒、工作汇报措辞优化等常见文本沟通场景.
Passive detection of EPCI component creation opportunities. Identifies repetitive patterns that could become skills, commands or subagents.