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.
14.533 de skill-uri din 417 depozite · actualizat acum 17 ore
1.543 de skill-uri
- evaluating-machine-learning-modelsforyourhealth111-pixel/Vibe-SkillsEvaluate trained machine learning models with the right metrics and comparison logic. Use for benchmark review, threshold selection, calibration, validation, and model comparison; not for feature engineering or leakage auditing.InginerieFără avertismente★ 3,8 K↓ —
- code-simplifiergetsentry/skillsSimplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up code", "refactor for clarity", "improve readability", or review recently modified code for elegance. Focuses on project-specific best practices.OficialInginerieVerifică întâi★ 1,1 K↓ —
- amc-run-rtsp-calibrationNVIDIA/skillsCalibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.InginerieFără avertismente★ 3,7 K↓ —
- debugging-wizardJeffallan/claude-skillsParses error messages, traces execution flow through stack traces, correlates log entries to identify failure points, and applies systematic hypothesis-driven methodology to isolate and resolve bugs. Use when investigating errors, analyzing stack traces, finding root causes of unexpected behavior, troubleshooting crashes, or performing log analysis, error investigation, or root cause analysis.InginerieVerifică întâi★ 12 K↓ —
- structured-code-reviewrohitg00/skillkitPerforms a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Each stage uses targeted checklists and categorized feedback (Blocker/Major/Minor/Nit) with actionable suggestions and rationale. Use when the user asks for code review, PR feedback, pull request review, or wants their code checked for bugs, style issues, or vulnerabilities — triggered by phrases like "review my code", "check this PR", "review my changes", "pull request review", or "code feedback".InginerieFără avertismente★ 1,6 K↓ —
- red-green-refactorrohitg00/skillkitGuides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like 'make the test pass', 'test coverage', or 'unit tests before implementation'.InginerieFără avertismente★ 1,6 K↓ —
- nv-generate-ct-rflowNVIDIA/skillsUsed for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data without review.InginerieFără avertismente★ 3,7 K↓ —
- obsidian-rest-apidavepoon/buildwithclaudeCall the Obsidian Local REST API directly (over HTTP) for vault operations the mcp__obsidian__* tools do NOT expose — move/rename a note, overwrite a whole file atomically (PUT), act on the currently-open active file, run an Obsidian command, open a note in the UI, list all tags, or do date-specific periodic-note CRUD. Prefer the mcp__obsidian__* tools for plain read/append/patch/delete/search; fall back to this skill only when the required method is missing from MCP.InginerieFără avertismente★ 3,7 K↓ —
- warp-debug-gradientsNVIDIA/skillsUse to diagnose and fix incorrect gradients in differentiable Warp programs. Anything trained, optimized, calibrated, or fit through Warp kernels depends on wp.Tape gradients, so treat any misbehavior of such a workflow as a gradient problem until proven otherwise — use this when training diverges or NaNs, won't train at all, stalls or plateaus above the expected loss, converges to a wrong or biased answer, is worse than a reference implementation, works at small scale but fails at production scale, or fails a QA/validation recheck. Also for explicit symptoms — exploding, NaN/inf, zero, or subtly wrong gradients, suspected wp.Tape/backward issues, gradcheck failures — but users usually describe only the surface symptom ("the sim explodes", "the fit gets dragged toward outliers") without mentioning gradients: make that leap. Not for forward-only Warp work, build/install problems, or autograd issues in other frameworks without Warp.InginerieFără avertismente★ 3,7 K↓ —
- commit-with-reflectionforyourhealth111-pixel/Vibe-SkillsGit提交与调试反思报告生成技能。用于分析开发过程中的错误、调试步骤和解决方案,生成结构化的中文反思报告,并创建包含报告引用的Git提交。显式请求词:反思提交、智能提交、生成调试报告、commit with reflection。InginerieFără avertismente★ 3,8 K↓ —
- codonfm-finetuneNVIDIA/skillsFine-tune public CodonFM Encodon checkpoints on labeled coding-sequence or coding-variant data using LoRA, head-only, or full fine-tuning. Use when a user explicitly asks to fine-tune CodonFM or Encodon for regression or classification. Support generic public-v1 Encodon workflows only; reject Decodon, MissenseDataset, missense_synom_agg, and generation workflows.InginerieFără avertismente★ 3,7 K↓ —
- debuggingcode-yeongyu/oh-my-openagentRuns a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.InginerieFără avertismente★ 70,3 K↓ —
- skill-social-performance-reviewZJU-REAL/Easel生成月度社媒效果复盘报告，分析小红书、抖音、B站、微博等平台的内容表现，输出下月可执行建议。 当用户说"月度复盘""效果复盘""这个月表现""内容复盘""运营总结""下月建议""月报"时使用。 和 skill-publish-analytics 的区别：analytics 从发布日志做四维归因，本 SKILL 做跨平台组合级月度复盘。InginerieFără avertismente★ 4 K↓ —
- cuopt-routing-api-pythonNVIDIA/skillsVehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.InginerieFără avertismente★ 3,7 K↓ —
- coding-agent-sessionscode-yeongyu/oh-my-openagentFinds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs. Use when asked to find or search past sessions, transcripts, or subagent runs, or to recover what an earlier session did.InginerieFără avertismente★ 70,3 K↓ —
- orchestration-teammvschwarz/openrigUse when coordinating assignments, selected review boundaries, or blocked work across a rig.InginerieVerifică întâi★ 8,1 K↓ —Apare și în 1 alt depozit
- skill-post-scorerZJU-REAL/Easel对社媒帖子草稿进行互动潜力评分，基于历史表现数据输出结构化评分卡。 当用户说"帖子打分""评分""这条能火吗""发布前评估""内容质量分""评分卡""草稿评估"时使用。 和 skill-topic-evaluator 的区别：evaluator 评还没做的选题潜力，本 SKILL 评已写好的草稿质量； 和 skill-social-performance-review 的区别：本 SKILL 评单条草稿（发布前），review 做月度组合复盘（发布后）。InginerieFără avertismente★ 4 K↓ —
- detecting-performance-regressionsforyourhealth111-pixel/Vibe-SkillsCompare current benchmark results against historical baselines to spot performance regressions. Use as an explicit/manual helper for build-to-build degradation review, not for broad optimization strategy or low-level profiling ownership.InginerieFără avertismente★ 3,8 K↓ —
- mcp-builderdavepoon/buildwithclaudeGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).InginerieFără avertismente★ 3,7 K↓ —
- show-me-your-workmichael-denyer/pstack-claudeKeep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.InginerieFără avertismente★ 3,3 K↓ —
- ops-packagedavepoon/buildwithclaudeA single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClawInginerieFără avertismente★ 3,7 K↓ —
- dali-dynamic-modeNVIDIA/skillsDALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.InginerieFără avertismente★ 3,7 K↓ —
- review-walkthroughtrailofbits/skillsGenerates an interactive HTML walkthrough for reviewing code changes. Use only when explicitly called.InginerieFără avertismente★ 7,7 K↓ —
- codonfm-embedNVIDIA/skillsValidate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.InginerieFără avertismente★ 3,7 K↓ —