В каталоге 182 820 навыков в 14 категориях.
每日自动更新 Clawdbot 和所有已安装技能。通过 cron 定时运行，检查更新、应用更新，并向用户发送更新摘要。
Next.js 코드 작성 후 자동 검증 (tsc, lint, build). Use when (1) 코드 구현 완료 후,(2) PR 생성 전, (3) 커밋 전 검증 필요 시. 모든 검증 통과 시에만 다음 단계 진행.
Programmatic asset compliance validation using vision analysis and Northcote scorecard. Eliminates manual validation loo...
Attempt automated verification of criteria before falling back to manual. Parses criterion text for automation hints and...
Run and validate AutoVideo-Agent Markdown-to-video workflows, including the v0.1-compatible deterministic offline comman...
Help Codex plan, generate, reproduce, and refine editable Microsoft Visio scientific diagrams. Use when users ask Codex...
自动为当前项目生成或更新 VitePress 文档网站。
Render the live auto agent tree — driver → work step → do_step fan-out agent — with each node's age against its stall th...
자율 판단 + 자율 발견 워크플로우 (v2.0 - Ralph Wiggum 철학 통합). "할 일 없음 → 종료"가 아닌 "할 일 없음 → 스스로 발견". 5계층 우선순위, 9개 커맨드 자동 트리거, Context 예...
Use when adding or proposing a new test ONLY if the test rules are not present
Classify a red test as a real regression, a flake, or an environment problem before patching.
Carve the unsafe part out of a task up front, then run the safe remainder at full strength instead of running the whole...
Automate Autobound tasks via Rube MCP (Composio). Always search tools first for current schemas.
AutoBoy by The Firm — the pre-launch order book for Bankr launches on Base. Use when an agent wants to buy a token befor...
Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and imp...
Use when the user wants data fetched from a website, a site turned into a CLI, existing browser login state reused throu...
Operate artbyjazi/autoclip, the MIT-licensed local-first AI video clipper that turns long-form video into ranked, captio...
Search autocomplete and type-ahead suggestion optimization for knowledge bases
Run one budgeted research conference: parallel researcher children, adversarial review, synthesis; plus plan, resume, an...
This is the main orchestration skill that combines all other skills to automatically create short-form content from long...
- xUnit AutoFixture 整合
Control Autodesk desktop apps - 3ds Max and friends - from the shell via Flue, without an MCP server.
Autodesk Platform Services (APS/Forge) REST APIs — OAuth, Data Management, Model Derivative, Viewer, Design Automation,...
Use when working with Autodesk Fusion or Fusion 360 through its official local MCP server, including live desktop sessio...
Manage bounded autonomous dev loops.
Feature auto-development — clarify requirements, generate spec, dispatch dev sub-agent to implement and merge into curre...
Investigación profunda de frontera, síntesis de cristales ontológicos, verificación de papers/estudios, falsación Popper...
Use when work in any project needs an AutoDL instance powered on or off in GPU mode (有卡) or non-GPU mode (无卡), switched...
Specialist in Intelligent Codebase Mapping, Polyglot AST Discovery (Top 20 TIOBE), Dynamic C4 Model Architecture (Mermai...
Generate a full code-documentation wiki from a source repo using an ultracode workflow. Clones the repo, scaffolds the a...
Audit one local prospectus PDF, DOC, or DOCX through PDRouter and download the annotated document with AutoDoc NEXT2.0.
Incrementally refresh the autodoc code wiki from new commits. Pulls the source repo, diffs against the last-documented c...
When ending a session, consolidating memory, or when memory files feel stale or contradictory. Use when the user says "d...
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewe...
Guidance for AutoFixture test data generation library. USE FOR: auto-generating test data for unit tests, reducing boile...
- test data generation
協助整合 AutoFixture 與 Bogus 兩套測試資料產生工具。當使用者需要結合匿名測試資料與真實感語意化資料、建立混合產生器、設計 SpecimenBuilder 整合 Bogus、或建立測試資料工廠時使用此技能。
- autofixture customization
協助在 .NET 測試中整合 AutoFixture 與 NSubstitute，實現自動模擬（Auto-Mocking）功能。當使用者需要測試有多個相依性的服務類別、建立自訂 AutoData 屬性、或使用 Frozen 機制確保測試一致...
Build conversational multi-agent systems with Microsoft AutoGen. AssistantAgent, UserProxyAgent, GroupChat, code executi...
Build conversational multi-agent systems with AutoGen (AG2) — define AssistantAgent and UserProxyAgent, set up GroupChat...
Scaffold a basic AutoGen agent with a tool, wired to any OpenAI-compatible endpoint. Run when the user asks to create, g...
Use when autoGen multi-agent conversations — AssistantAgent, UserProxyAgent, group chat, code execution. Use when workin...
Review an AutoGen multi-agent system for inter-agent message spoofing, trust boundary collapse between orchestrator and...
Microsoft AutoGen multi-agent configuration for conversational AI systems
Autogenerate constraint checking code from constraints (C-*) that specify system limits, timeouts, dependencies, or envi...
Autogenerate formula implementations from formula specifications (F-*). Converts mathematical formulas, calculations, an...
Autogenerate production code from disambiguated business rules (BR-*). Converts BR-* specifications into validators, con...
Autogenerate validation functions from business rules (BR-*) that specify formats, patterns, ranges, or constraints. Use...
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, dep...
Auto-advance a multi-phase plan: dispatch a subagent per phase, chain /review + /pitfall-verification at each boundary,...
A self-imposed learning mode where the human directs and you gate. The human is working on a real problem (architecture...
Compound a just-solved problem into a durable in-repo learning doc under docs/solutions/, refresh stale learnings as cod...
Use this when working with DWG file generation features (Tiles, Playground, Symbol Generator). Provides AutoLISP script...
Run a long multi-round task that survives Claude usage limits — set up a shared state file + stop marker, then launch th...
Automate Autom tasks via Rube MCP (Composio). Always search tools first for current schemas.
Design and build a reusable AI automation. Use for automate, create automation, turn this into a skill/command, new work...
Use this skill to create Cursor Automations.
Comprehensive test automation setup. Test Architecture
Autonomous development workflow with iterative self-correction loops and multi-agent team coordination. Orchestrates the...
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skil...
Use when the user wants working preferences captured in a reusable mode skill.
Use for 'automate me', 'create/update/refresh my -mode skill', 'turn/capture my preferences or working style into a skil...
Use when asked to create or refresh a personal mode skill and open a reviewable PR. Mines recent session history for a r...
Generate full hexagonal glue-code for a Zeebe BPMN process across all five layers — inbound workers, inbound/outbound po...
Design a risk-tiered review process for code, design, or approvals. Measures review latency, splits the work between che...
Analyze a screen recording of a manual process and produce targeted, working automation scripts. Extracts frames and aud...
Build WhatsApp automations with Kapso workflows: configure WhatsApp triggers, edit workflow graphs, manage executions, d...
Automate Whatsapp
Use when the user wants GoMarble to keep doing a job on a schedule: a daily brief, anomaly or spend alerts, a weekly cre...
Turn manual cases into Playwright E2E automation run in a browser: page objects, helpers, bug evidence, reports. Not for...
Generates standardized quality control reports by aggregating metrics from FastQC, alignment, and other tools using Mult...
Use when PR review batches need automated addressing. Human reviews auto-launch; bot reviews use pr-review-ai-bots.
Set up automated code quality tools: ESLint, Prettier, pre-commit hooks, and CI linting. Activate whenever the user sets...
Pattern for automated testing with GitHub issue creation and Claude Code auto-fixing. Creates Test → Fail → Issue → Fix...
Produce a standalone test plan by analyzing code for test coverage gaps and edge cases. Use when you need to create, gen...
Write and run automated tests (unit, integration, E2E)
Write automated tests following a pragmatic, integration-focused philosophy. Use when writing tests for new features, wr...
Develop and execute automated tests to validate pilot scripts, workflows, and systems. Use when verifying code reliabili...
Triage Monte Carlo alerts interactively or build an automated workflow. Fetch, score, and troubleshoot alerts using MCP...
How the devbox automatically updates llm-agents (claude-code) via GitHub Actions and systemd timers. Use when debugging...
Open the AutoMates root folder in Finder
Autonomous AutoResearchClaw skill. Actively crawls known WAF vendor documentation (e.g., Cloudflare, Datadome, Akamai) a...
Autonomous CAPTCHA-BypassClaw skill. When visual CAPTCHAs become too heavily obfuscated for standard solvers, this agent...
Autonomous CookieCalibratorClaw skill. Uses Gemini Vision to literally *look* at the screen during a 403-block or CMP ti...
Autonomous CostControllerClaw skill. Tracks API usage (Gemini tokens, CAPTCHA credits) and Proxy bandwidth burn rates. A...
Autonomous DB-VacuumClaw skill. Monitors SQLite fragmentation and Write-Ahead Log (WAL) bloat. During predicted idle tim...
Autonomous ExperimentClaw skill. Real-time A/B testing agent that runs micro-experiments on pre-fill delays and interact...
Autonomous HoneyTrapClaw skill. A specialized vision-and-DOM agent that triggers *intentional* honeypots on dummy creden...
Autonomous LocalLLM-Claw skill. Monitors the latency and up-time of cloud AI APIs (Gemini). If an outage or rate-limit (...
Autonomous MutationClaw skill. Triggers before stealth injection to rewrite the AST of the JavaScript payloads. This ens...
Autonomous PersonaFabricatorClaw skill. When a target requires "warm-up" (e.g., visiting 5 pages before login), this age...
Autonomous PoWSolverClaw skill. Monitors the CPU utilization and latency of Proof-of-Work (PoW) challenges in wicketkeep...
Autonomous PriorityClaw skill. Dynamically rescores the testing queue based on live WAF feedback, putting high-success...
Autonomous ProxyNegotiatorClaw skill. Monitors proxy health via Redis coordinator. If a specific ASN or subnet gets glob...
Daily summary reporting skill that generates comprehensive Markdown reports with success rates, credential coverage, pro...
Proactive research skill that monitors dependency updates, anti-bot landscape changes, and GitHub releases for patchrigh...
Autonomous self-healing skill that analyzes failure patterns, generates targeted code patches, validates them with tests...
Process supervisor skill that monitors the Automati server health via HTTP health-check endpoint. Detects crashes, hangs...