В каталоге 182 820 навыков в 14 категориях.
Use when operating solo on a task handed off without the user available for interactive check-ins — ask every clarifying...
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation,...
Design patterns for building autonomous coding agents. Covers agent loops, tool design, permission systems, browser auto...
Assess a codebase's readiness for autonomous agent development and provide tailored recommendations. Use when asked to e...
You are an agent architect who has learned the hard lessons of autonomous AI. You've seen the gap between impressive dem...
Autonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct w...
Plan multi-step browser work using browser-use with an approved model budget.
Converts a plan, idea, or app spec into a complete autonomous multi-session build setup that Claude Code can execute end...
Full-stack software development agent for design, implementation, testing, and deployment. Use when the user explicitly...
Run headless implementation from idea to artifact. Use when user says 'build in background', 'autonomous', 'headless', o...
Autonomous PyWry application building using LLM sampling, elicitation, and progress reporting.
Ensures Claude verifies both local tests AND remote CI before claiming completion. Use BEFORE any completion claims, com...
Run comprehensive code quality checks, tests, and fixes autonomously
Orchestrate self-healing DevOps workflows with telemetry, Kubernetes control, and CI/CD automation; use when asked to de...
自动驾驶 (Autonomous Driving) Master OS — automated mastery of Autonomous Driving: top builders' mental models, tool stack,...
Execute implementation plans or backlog items autonomously with shared-context architecture for maximum accuracy
Run autonomous multi-model code review on a finding. Invokes claude/codex/gemini via reviewd, evaluates consensus, and a...
Use when driving or reviewing an unattended LLM-gated engineering process — enforce "no un-run greens" (reviewers execut...
The protocol behind every investigation skill. Use when AI research must proceed without you: search-plan gate, Fact/Inf...
Autonomous development loop patterns for iterative self-improvement. Auto-triggers when implementing features autonomous...
자율 실행 루프. Plan→Execute→Verify를 반복하여 복잡한 작업을 자율적으로 완성합니다. Ralph(완료 보장) 모드와 Autopilot(병렬 최대 성능) 모드를 지원합니다. Use when the us...
Manages autonomous iterative development loops that repeat until completion. Use when asked to loop, iterate, keep going...
Iterate until success or limit, composing existing skills with Jidoka integration
自主Claude代码循环的模式与架构——从简单的顺序管道到基于RFC的多智能体有向无环图系统。
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent...
Patterns and architectures for autonomous Codex development loops, from simple sequential pipelines to RFC-driven multi-...
Design bounded OpenCode CLI loops and multi-stage pipelines with explicit artifacts, stop conditions, time/cost budgets,...
Execute a single phase from roadmap to working code autonomously
Otonom PR yasam dongusu. PR olustur, CI bekle, hata varsa duzelt, review feedback'i uygula, merge'e hazirla. Budget ve z...
AI-driven dynamic security fuzzing, exploit generation (XSS, SQLi, SSRF, Prompt Injection), and automated patch remediat...
Autonomous deep research agent that reads all files in the active directory, performs exhaustive multi-round literature...
Run, maintain, or extend the paper-only autonomous research workflow for baseline, full experiment, and related comparis...
Use when user requests project-level autonomous development, says "forge", or provides a project description for autonom...
Execute complex long-running tasks across multiple sessions
Use when work must continue across multiple Codex sessions with `.autonomous/` tracking, resumable execution, or autonom...
Empowers the agent to autonomously run tests, read terminal stack traces, and self-heal code until tests pass. Transform...
> Compiler: manual (bootstrap)
Independent reasoning with aligned decision-making - thinks autonomously but remains obedient to user commands
Use this skill when setting up or running autonomous stock trading operations. The system continuously researches stocks...
Give your agent a budget, a target, and a deadline — it does the rest. Orchestrates DSL + Opportunity Scanner + Emerging...
Use when a carrier asks about autonomous trucks — current state of Level 4 development, major programs (Aurora, Kodiak,...
Autonomous UI inspection using a dual channel: (1) visual screenshots via Playwright MCP tools, (2) numeric layout metri...
Rule under the autonomous-work law. Load when the owner has left and asked for unattended work — a chain of branches, a...
Pattern of rule autonomous-work. Load when the owner has left and the work runs through the night — the cycle of one pie...
Execute development workflows through Explore-Plan-Code-Verify phases with task-driven tracking, Tier 1/2/3 action class...
Governs every action. Decide the tier by REVERSIBILITY (not by action type), then act or ask. Nrupal set this boundary o...
運用監査。失敗率やDLQなどをチェックし、結果を workspace に保存する
Use when core autonomy protocol for AI agent operations. Defines how agents operate 24/7 without human prompts — monitor...
Run the full autonomy bootstrap with minimal questions.
Autonomous failure recovery and self-healing loop for tasks, benchmarks, or services. Use when a run fails, dependencies...
Automated pentest pipelines — designing, running, and auditing bash-driven recon-to-report automation
全自动 RPI 执行 — 从想法到可运行代码
Use this to run an ENTIRE hackathon campaign hands-off in ONE session — intake the user's constraints (which steps, demo...
Full autonomous execution from idea to working code
The whole coding loop on one deliberate yes: map, spec, critic-hardened plan, GitHub issues, parallel worktree implement...
diagnose→ship の自律改善ループを1回実行する。Issue がなければ diagnose で起票し、あれば ship-parallel で実装する。「/autopilot」「自律改善」と言った時に使用。
This skill should be used when the user asks to "run autopilot", "autopilot feature N", "implement all phases", "run all...
Orchestrate unattended resolution of open GitHub issues - triage by complexity, dispatch parallel worker agents into iso...
Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan → wave-executo...
Drive an existing wayfinder map, spec, or set of tickets to completion through fresh top-level Claude Code, Codex, or Gr...
Builds an app, site, bot, or feature end-to-end from a dictated idea — requirements, briefing, spec, tickets, subagents,...
Run the idea-to-ship pipeline AUTONOMOUSLY, in character as a grounded founder-persona — composing ideate → deep-dive →...
Hands-off end-to-end delivery pipeline that CHAINS existing ODIN skills — plan → proceed → simplify → review → fix → ato...
Unattended orchestrator for scheduled runs. Each run: follow up on open autopilot PRs (CI / conflicts / owner review com...
当用户说“autopilot”“自己搞定”“直接跑到底”，或委托代理调查、实施并验证一个宽泛任务时使用。仅规划、解释或已有明确窄范围的请求，按用户指定范围处理。
Defines the main NgAutoPilot workflow for understanding a task, detecting project context, selecting the smallest skill,...
Takes the whole task and runs it end to end without stopping to ask, leaving the user to review at the finish line; invo...
Decide which of your recurring rituals to put on autopilot — and which to keep manual. Use when asked what to automate,...
Run one Codex-managed autopilot iteration using Ruflo MCP or CLI state
Use learned patterns and current state to predict the optimal next Codex action
Check campaign autopilot status. Use when: health scores, auto-corrections, guardrail review, campaigns needing attentio...
Automated full review pipeline skill. Use when the user wants to run a complete plan review in one command, automaticall...
Auto-review pipeline — reads the full CEO, design, and eng review skills from disk and runs them sequentially with auto-...
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with a...
Use when the user runs /autoplan on a plan or idea. Runs CEO, design, DX, and engineering review phases over the idea, a...
Use when the user runs /autoplan on a plan or idea. Reviews, amends, and derives task IDs with a final human approval ga...
Route any request to the right skill, command, or agent chain with defaults, so nobody hand-picks from the full catalog....
Fully automated review pipeline: CEO, Design, and Eng reviews with auto-decisions using 6 principles (completeness, boil...
自动化 plan review pipeline。依次加载 CEO、design、eng review， 按 6 条决策原则自动作出大多数判断，只把 taste decisions 和明显冲突 留给用户最终确认。 (gstack)
Self-producing skill system combining ruler enforcement with skill self-evolution. Implements trifurcation-first imperat...
Iteration 7 of Multiplicity Cascade - Self-creating chaos engines
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not a...
Automate authorized forensic analysis in Autopsy with Sleuth Kit ingest modules, evidence-processing pipelines, and sear...
Full codebase health assessment. Use when diagnosing project health or starting a rescue workflow on legacy code — OR wh...
394 production-tested Claude skills for media professionals — TV, journalism, YouTube, podcasts, screenwriting, newslett...
AutoR — human-centered 研究执行框架。8阶段 pipeline，产出可复现 artifact。
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the...
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canoni...
Runs autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style of...
Core autonomous research loop. Reads research.md, proposes hypotheses, runs experiments, evaluates results mechanically,...
Karpathy의 autoresearch 패턴을 스킬 프롬프트 최적화에 적용. 체크리스트(3~6개 예/아니오 기준) 기반 hill-climbing 루프로 SKILL.md를 자동 개선합니다. 한 번에 하나만 바꾸고,...
Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable m...
Autonomous experiment loop — iteratively mutate code, measure a metric, keep only improvements (hill-climbing ratchet)
Bounded improvement loop: one artifact, fixed eval score, keep an edit only if strictly better. Use for AR_DESIGN/AR_FUN...
Autonomous iteration loop: modify, verify, keep/discard against any metric
Autonomous self-improvement loop — iteratively modify a target, evaluate against a scoring function, keep improvements,...
Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated pa...
Use when a task involves running bounded, reproducible experiments that compare candidate approaches against a fixed bas...