В каталоге 182 820 навыков в 14 категориях.
TDD-based autonomous development loop with checkpoint recovery and observability changelog
Assign, validate, normalize, and explain Luhmann/Zettelkasten-style project-note codes for Chinese book manuscripts, Obs...
Indestructible agent memory — permanently stored, never lost. Save decisions, identity, and context as a memory chain on...
Merge an existing PR after rebasing, running review-pass, ensuring CI passes, and addressing review comments.
在 kobe 仓库内跑 auto-motion——把 transcription.srt 拆成多段 MG 动画镜头并拼接成竖屏视频(storyboard 分镜 + theme.md 全片主题 + 逐镜头 claude -p 子进程 + ff...
Host-agnostic Agent Skill: double-layer workflow for AI-assisted delivery—requirement specification, multi-prompt outer...
Boucle d'auto-amelioration du budget tokens : applique automatiquement les optimisations SURES (reroute Haiku, caveman p...
使用 auto-run-agent 对目标项目进行自动化分析、评估、设计和优化。完整流程包括：探索项目现状 → 识别问题 → 设计任务列表 → 创建 runner 环境 → 启动自主执行。适用于任何需要批量优化的项目。
Intelligent workflow orchestrator that automatically chains the right skills (spec, plan, build, test, review, code-simp...
Automatically activates when detecting complex, multi-task requests that would benefit from parallel execution. Activate...
Sistema de auto-routing que detecta el tipo de tarea y activa el agente especializado correcto automáticamente. Se activ...
仓库 Markdown/JSON 内容自动同步到前端页面，配置 GitHub Actions 定时拉取 + 部署，保持 Google SEO 内容新鲜度。支持日报、博客、Changelog、Landing Page 等多种页面模式。
Autonomously improve a generated paper via GPT-5.4 xhigh review → implement fixes → recompile, for 2 rounds. Use when us...
Enable parallel agent execution for multi-domain features with git worktree isolation
Behavior guide for when the auto-pause hook fires or when starting a long-running operation that needs a timeout excepti...
Post or schedule a provided video directly through Zernio. Input is a local video path or public video URL. If no captio...
Run one named preset one-shot against a target — the Phase-1 headline of addressable step presets. Use when the operator...
CRITICAL: ONLY activate this skill when the user explicitly triggers the `/auto-proceed-plan` slash command. DO NOT auto...
Automatically process reported issues and feature requests through the full development workflow. Roleplay as CTO for de...
Expert prompt engineering assistant that analyzes vague requests, asks clarifying questions, and transforms them into st...
Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a...
Silent quality check after every feature. Fix issues before telling user. Never claim tests passed without running them.
PROACTIVELY activates for ANY task with clear success criteria. This skill should be used when the user provides tasks l...
Rebase feature branches onto target, resolve conflicts, and keep PRs up-to-date with force-push
Use when you need semantic retrieval from perpetual memory at query time. Parses query intent, searches vector store, ra...
Automate version updates and releases for any project type (Node.js, Python, Rust, Unity, Unreal, etc.). Detect project...
Decode an auto repair estimate — what each line actually is, which items are urgent vs upsell, and the questions that se...
Automatic response rules, patterns, and scheduled messages
Autonomous research loop that iteratively improves code through experiments. Runs experiments on local or remote GPUs, t...
Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts, config...
Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthe...
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options an...
Improve any existing Claude Code skill, CLAUDE.md, subagent definition, slash-command, or prompt markdown file by combin...
Use when running or designing a measured self-improvement loop on a YURI subsystem — "climb this metric", "optimize the...
Autonomous experiment/evaluate/iterate loop for code, prompts, skills, or workflows. Use when optimizing a measurable me...
Proactively researches any topic by searching, synthesizing, and presenting well-sourced information — without waiting t...
先にマージされた別の PR と衝突して止まった PR に、デフォルトブランチを取り込んで衝突を解き、push し直すところまでを人間への確認なしに行う。`npm run auto-programmer` が AI 専用 clone の中で起...
Local auto-review of modified code (no GitLab/GitHub). Runs 5 sequential audits and generates a local report. Ideal for...
写入 .md / 代码文件后自动做质量审查与修复闭环，并判断是否属复杂场景，是则接力 challenger 二次质疑。触发：每次 write_to_file / replace_in_file 写入后自动执行。
Manages and monitors the autonomous agent system for code implementation tasks. Provides progress checking, issue diagno...
Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until po...
Autonomous multi-round research review loop. Repeatedly reviews using a secondary Codex agent, implements fixes, and re-...
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment va...
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for...
CRITICAL: ONLY activate this skill when the user explicitly triggers the `/auto-review-pr` slash command. DO NOT auto-tr...
Implement automatic rollback on deployment failure
Error rate monitoring, SLO detection, and notification webhooks for automated rollback triggers. Use when setting up aut...
Auto router patterns for this project. Intelligent model selection via task classification, cost tier diversity, high-st...
CLAUDE.md devteam section — opt-out rules and auto-routing triggers.
Intelligent agent routing and topology selection based on task characteristics
Autonomous dispatch-reconcile loop for batch task processing. Use with /auto-run --through <id> to execute tasks unatten...
Automatically save session tips when user provides important feedback or corrections
Professional Auto Scaler Expert skill. Build robust, automated deployment pipelines and configure cloud infrastructure a...
总领型自动科研 Agent skill。用于统筹地理学+体育学研究中的科研自动化、长期记忆、文献库建设、idea 生成、方法设计、数据分析、机器学习、地理空间/遥感、综述与文献计量、SCI 写作、审稿回复、进化档案维护。触发于 auto-s...
Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate toolin...
Rebase and publish the current branch.
Drives a surveycore implementation plan end-to-end — TDD implementation, spec compliance + code quality review, changelo...
Evaluate current session for skill-worthy workflows and create reusable skills. Triggers on: auto-skill, create skill fr...
Detect drift between the Codex Supercharge plugin pack and installed copies under `$HOME/.codex/skills`, including copie...
Design production agent reliability loops across traces, evals, guardrails, gateways, model budgets, and shadow tests. U...
Append and summarize a lightweight local `.agent-runs/runs.jsonl` ledger (claudetop-inspired) so Codex sessions build du...
Design a repeatable MCP conformance, health-check, and tool-surface regression harness for local or CI use. Use when the...
Use memsearch as an on-demand semantic index for project markdown memory (search → expand → optional deep drill). Use wh...
Synthesize multiple local `sources/` clones into workflow families before creating skills, references, or scripts. Use w...
Generate and refresh a metadata-only inventory of local `sources/` shallow clones (size, git remote, HEAD, commit date,...
Run closed-loop evaluators for Codex Supercharge artifacts and write feedback state for future Codex sessions, subagents...
Automatically creates new skills from complex problem-solving sessions. Triggers at the end of multi-step tasks that re...
自动处理 Agent Skill 的全生命周期：在用户反馈中识别稳定约束以触发技能抽取；合并新增偏好实现版本演进（如 v0.1.0 → v0.1.1）；并在后续相似任务中精准检索并注入对应技能。
Run a deterministic Codex Supercharge maintenance pass (skill audit, plugin discovery audit, helper smoke checks, quick...
Safely inspect and adapt third-party agent/Codex/Claude skill packs before installation. Use when importing external ski...
Prevent secret leakage when adding or reviewing MCP server configs. Use when you see `mcpServers` JSON, `.env`, config s...
Verify current GitHub and agent-skill ecosystem evidence before using trend, popularity, star, topic, or public-discover...
(已禁用) SMTP 邮件发送 — 此 skill 已被禁用，不会被系统触发
Complete issue lifecycle with Task dependencies and Subagents - true zero-pause automation. TRIGGER when: user wants ful...
CTF challenge otomatik cozum pipeline'i. 6 asama: zip'i ac, siniflandir, coz, flag topla, writeup olustur. /auto-solve k...
Show the current auto session status and progress.
Batch populate summary fields using content analysis
Auto-generated skill from cross-repo pattern - Pattern detected in 19 repositories
Automatically analyze and tag untagged [Gorgias](https://composio.dev/toolkits/gorgias) tickets based on content.
Batch auto-tag untagged notes using content analysis
Review a plan or GitHub issue for an `auto_task` before execution
Propagate reviewed changes down an existing PR stack, keeping every PR mergeable
当用户明确要求测试代码、代码审查或代码自检时使用。系统化发现并验证代码问题。⚠️ 不适用：用户只是想实现或优化功能、询问代码问题，或没有明确测试意图。
当用户明确要求"测试项目"、"运行 auto-test-project"或"进行项目级测试"时使用。对完整项目进行多轮 A 轮批判性测试 + B 轮质量检查，系统化发现、记录、修复问题。⚠️ 不适用：用户只是想优化功能（应直接修改）、只是询...
当用户明确要求"测试技能"、"运行 auto-test"或"进行批判性测试"时使用。通过多轮 A 轮批判性测试 + B 轮质量原则检查，系统化发现、记录、修复问题，并沉淀可追溯的 `plans/` 与 `tests/` 文档。⚠️ 不适用：...
Pattern for automated testing with GitHub issue creation and Claude Code auto-fixing. Creates Test → Fail → Issue → Fix...
Automatically generate and run tests after each code change. Use when: any code is generated or modified in the pipeline...
全自动外贸客户开发编排器 — 一句话触发「搜索 → 背调 → 评分 → 写信 → 交付草稿 → 入库 → 日志」端到端流水线
Translate a designed loop (from auto-design) or a workflow (from auto-author-workflow) into an execution tree — ordered...
Workflow automation hooks for agent-playbook skills. This skill defines automatic triggers between skills - DO NOT use d...
Run TypeScript type checking after file edits and immediately flag type errors before moving on. Uses Cursor hooks for a...
Check and update Claude Code to latest version, update plugins, and show changelog.
Automatically update GitHub Issue status to the next stage (Todo→In Progress→Done) in all linked projects.
Automatically update Jira Issue status to the next stage (TODO→進行中→完了). (jira)
Expert in Tauri auto-update implementation with focus on signature verification, rollback mechanisms, staged rollouts, a...
Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and...
Automatically apply improvements to skills and the ecosystem based on system-reviewer findings and best-practices-learne...
Automatically update OpenClaw and selected skills once daily. Runs via cron, checks for updates, applies them, and messa...
Automatically update ONE_SHOT skills from GitHub on session start. Checks once per day and updates silently. Use /update...
Automatic skill update management: check for updates, diff, apply, rollback, version tracking