Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
49.492 de skill-uri din 2.391 de depozite · actualizat acum 12 ore
49.492 de skill-uri
- meta-evalagentscope-ai/OpenJudgeUse when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessing RAG accuracy, or wants to compare prompts/models. This skill is the entry router: it asks diagnostic questions then recommends which sub-skill (local workflow) to use next.TestareFără avertismente★ 1 K↓ —
- humanizefcakyon/claude-codex-settingsThis skill should be used when writing or revising text, including responses, documentation, comments, emails, posts, reports, and messages, especially when the user asks to "humanize", "write naturally", "remove AI tone", or "avoid AI writing".RedactareFără avertismente★ 1,2 K↓ —
- debug-extensionmicrosoft/power-platform-skillsDiagnose and fix failures in a built third-party `.ppmplugin` control: crashes, silent no-ops, PCF error outputs, or incorrect behavior. Uses the reported symptom, `shared/error-codes.md`, and file-level evidence to trace the manifest, Android/iOS modules, PCF dispatch, and build configuration. Produces a ranked diagnosis, asks for approval, then applies a surgical fix while keeping the committed manifest and affected contracts synchronized. Re-validates manifest changes through /generate-ppmplugin-manifest.InginerieFără avertismente★ 1,1 K↓ —
- 02-rl-rewardagentscope-ai/OpenJudgeBuild RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.ProductivitateFără avertismente★ 1 K↓ —
- derive-metricmicrosoft/power-platform-skillsUse when a requested measure is missing, a saved custom metric needs reuse, or an ephemeral formula or derived scalar is needed.AlteleFără avertismente★ 1,1 K↓ —
- gentle-ai-comment-writerGentleman-Programming/gentle-shellWrite warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.RedactareFără avertismente★ 1,6 K↓ —
- metric-designagentscope-ai/OpenJudgeUse when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader selection, metric design, judge prompt engineering, rubric design, evaluation pipeline code, or "how to evaluate [X] automatically." Outputs executable OpenJudge pipeline code.DesignFără avertismente★ 1 K↓ —
- gentle-aiGentleman-Programming/gentle-shellUse Gentle AI harness discipline for Pi work: clarify first, track ODD work, use applicable test-first development by default, delegate when useful, and protect review workload.TestareFără avertismente★ 1,6 K↓ —
- 00-academic-routeragentscope-ai/OpenJudgeUse when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.ȘtiințăFără avertismente★ 1 K↓ —
- improve-architecturedaveebbelaar/bamaArchitecture check-in for a growing macOS Swift codebase. Finds hot spots, proposes deeper modules, and refactors one step per commit with behavior proven unchanged. Use at the end of a milestone, before a big feature, when a file passes 600 lines, when one feature touches many files, when bugs repeat in one area, or when the user asks to refactor or clean up the code.PlanificareFără avertismente★ 1,5 K↓ —
- minutes-ingestsilverstein/minutesExtract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", or wants their PARA/Obsidian/wiki profiles updated from conversation data.ProductivitateFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- crabboxopenclaw/crabboxDetect and use Crabbox for repository tests and validation on remote runners. Use when crabbox.yaml or .crabbox.yaml exists, the crabbox CLI is available, or work needs remote compute, a clean or reusable environment, target-platform coverage, or auditable execution evidence.TestareFără avertismente★ 1,5 K↓ —Apare și în 1 alt depozit
- investigate-processmicrosoft/power-platform-skillsUse when a broad Process Mining business question, observed pattern or competing explanation needs investigation across analytical perspectives.FinanțeFără avertismente★ 1,1 K↓ —
- generate-prdhuytieu/COG-second-brainGenerate product requirements documents with optional publishing to Confluence or other wiki platformsPlanificareFără avertismente★ 1,3 K↓ —Apare și în 1 alt depozit
- idea-stormmohitagw15856/pm-claude-skillsGenerate a big, wide spread of ideas for anything by running the prompt through many different lenses at once, then clustering and picking. Use when asked to brainstorm ideas for, give me lots of options, help me come up with, or I need ideas for. Produces a high-volume, deliberately varied idea list generated across multiple angles (safe, wild, cheap, ambitious, weird, opposite), grouped into themes, and a shortlist of the most promising — maximizing range so you're not choosing from three obvious options.PlanificareFără avertismente★ 1,5 K↓ —
- writing-relayflowsAgentWorkforce/relayUse when authoring a Relayflows flow (@relayflows/surface / @relayflows/sdk, the journal-based v2 engine — the CLI is `flows`, package versions 2.0.x) in TypeScript or YAML/JSON. Covers the three-rung ladder (run/llm/agent), the resident verbs (human/dispatch/done), verification gates, TypeScript vs YAML authoring, per-step cli/model selection and its resolution order, flows.json, and `flows check`/`run`/`resume` with their real refusal shapes and exit codes. Not for the older, unrelated `@relayflows/core` WorkflowBuilder engine (`.pattern('dag')`/.agent()/.step() chains) that `writing-agent-relay-workflows` and `migrating-persona-to-relayflow` cover — that's a different product despite the similar name.RedactareFără avertismente★ 1,1 K↓ —
- git-workflowsTencentCloudBase/CloudBase-AI-ToolkitReusable git delivery workflows derived from local slash commands (commit, push, PR, release notes, GitHub Actions failure triage with worktree-based fixes, and isolating your own changes from a shared dirty workspace).InginerieFără avertismente★ 1,2 K↓ —
- setupfcakyon/claude-codex-settingsThis skill should be used when user encounters "ADC not found", "gcloud auth error", "GCloud MCP error", "Application Default Credentials", "project not set", or needs help configuring GCloud integration.AlteleFără avertismente★ 1,2 K↓ —
- jd-decodermohitagw15856/pm-claude-skillsDecode a job description to find what they actually want beneath the buzzwords. Use when asked to analyse a job description, decode a JD, assess fit for a role, or figure out what a posting really means before applying. Produces a decode — the real must-haves vs. nice-to-haves, hidden priorities & culture signals, red flags, an honest fit assessment, and the exact phrases to mirror in your application.AlteleFără avertismente★ 1,5 K↓ —
- k2fcakyon/claude-codex-settingsBuild and troubleshoot Cloudflare K2 or K2 Streams durable logs. Use for stream setup, producing from Workers or HTTP, configuring retention and inputs, and consuming through subscriptions.DevOpsFără avertismente★ 1,2 K↓ —
- compliance-osalirezarezvani/claude-skillsUse when running several compliance frameworks at once: which apply, where controls overlap, a mock audit or one evidence checklist. Runs framework_selector.py, cross_framework_mapper.py, audit_simulator.py and evidence_pool_generator.py.JuridicFără avertismente★ 29,3 K↓ —
- pip-writermohitagw15856/pm-claude-skillsWrite a Performance Improvement Plan a manager can defend and an employee can actually act on — specific concerns, measurable goals, real support, and an honest timeline. Use when asked to write a PIP, put someone on a performance plan, document underperformance, or build a formal improvement plan. Produces the concern statement, the measurable goals with success criteria, the support plan, the check-in cadence, and the consequences — HR/legal-ready. Complements pip-responder (the employee's side).RedactareFără avertismente★ 1,5 K↓ —
- cn-pipl-piamohitagw15856/pm-claude-skillsUse when asked 个人信息保护影响评估怎么做, 写一份 PIA, 处理敏感个人信息要评估吗, 自动化决策评估, PIPL 第五十五条, or assess a processing activity under China's Personal Information Protection Law. Produces a personal information protection impact assessment (个人信息保护影响评估) covering the PIPL Article 55 triggers, the Article 56 questions (lawful, legitimate and necessary; impact and risk; adequacy of protection), a risk register with mitigations and owners, and a record kept for at least three years.JuridicFără avertismente★ 1,5 K↓ —
- quote-cardmohitagw15856/pm-claude-skillsPull the single most shareable quote out of a testimonial, review, interview, or long text and format it as a clean quote card. Use when asked to make a pull-quote, testimonial graphic, or 'quote card' for social/marketing. Produces a tightly-edited quote with attribution and 2-3 alternates, structured to look great exported as a PNG from the playground.MarketingFără avertismente★ 1,5 K↓ —
minimal-web-baas-demo
TencentCloudBase/CloudBase-AI-Toolkit
ActualizatSecuritateActualizat acum 21 de ore
De la autor
Fast path for a minimal CloudBase Web + database demo (最小前后端 / 最小可用 fullstack / Lovable-like BaaS). Defaults to @cloudbase/js-sdk client CRUD (NoSQL app.database / PG app.rdb), MCP-only schema, preview-first, and forbids cloud functions unless secrets, cron/background jobs, or logic that security rules/RLS cannot express. Use for 搭一套 demo、留言板、Todo、Notes、Kanban, or when users say 带云函数+云数据库 but only need CRUD. NOT for production multi-service backends, CloudRun, WeChat Mini Programs, or tasks that truly need server secrets.
Instalare
npx skills add TencentCloudBase/CloudBase-AI-Toolkit --skill minimal-web-baas-demo -a claude-code
Se instalează în .claude/skills/minimal-web-baas-demo/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Doar instrucțiuniFolosește rețeauaLicență: MIT
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență77
Întreținere100
Licență100
Adopție50
Fișiere (2)
- LICENSE.md
- SKILL.md