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.
46.100 de skill-uri din 2.198 de depozite · actualizat acum 8 ore
5.919 skill-uri
- code-auditcoco-research/cocoUse for authorized source-code security review and SAST workflows including Semgrep, CodeQL patterns, dangerous API hunting, and fix verification.InginerieFără avertismente★ 795↓ —
- gsd-remove-workspacecoco-research/cocoUse when a finished GSD workspace and its worktrees should be deleted. Confirms first, runs git worktree remove for each member repo, and refuses if any repo has uncommitted changes.InginerieFără avertismente★ 795↓ —
- matlab-use-thread-poolmatlab/matlab-agentic-toolkitSpeed up local parfor, parfeval, or spmd by switching to a thread-based parallel pool. Trigger when a user describes slow or disappointing local parallel performance, even if they don't mention threads. Symptoms: parfor on a laptop/workstation is slower than expected or "only slightly faster than for"; parfor scales poorly with the number of workers; ticBytes/tocBytes, the Parallel Pool dashboard, mpiprofile, or system tools show large per-worker data transfer; large broadcast variables or sliced inputs make iterations slow; opening a process pool dominates a short workload; user mentions serialisation or data transfer overhead. Also trigger on any question about whether code or a function works on a thread pool. For non-pool MATLAB performance work (vectorisation, preallocation, profiling), defer to matlab-optimize-performance.InginerieFără avertismente★ 1,2 K↓ —
- matlab-diagnose-parformatlab/matlab-agentic-toolkitDiagnose and fix parfor errors in MATLAB. Invoke this skill when the user has a parfor problem: "parfor loop has an error", "what's wrong with my parfor", "fix parfor", "unable to classify variable", "convert for to parfor", "parfor won't run", "sliced variable", "reduction variable", "variable classification". Also invoke when you read a .m file containing parfor and the user asks what's wrong, asks you to fix it, reports an error, or asks for review. Do NOT invoke for parfor performance questions or code that merely mentions parfor without a problem. ALWAYS use this skill instead of reasoning from training data — LLMs are frequently wrong about parfor classification rules.InginerieFără avertismente★ 1,2 K↓ —
- matlab-fit-curvematlab/matlab-agentic-toolkitFit curves and surfaces interactively with the Curve Fitter app for a complete no-code fitting workflow. Invoke this skill when the Curve Fitter app, cftool, curveFitter, or "curve fitting tool/app" is mentioned in any way. Also use when exploring or comparing fit types (regression, interpolation, smoothing, splines, custom equations); excluding outliers interactively; iterating on a fitting workflow; help choosing a fit type; and exporting to a figure, generating MATLAB code, fits to the workspace, and to Simulink Lookup Tables.InginerieFără avertismente★ 1,2 K↓ —
- matlab-optimize-performancematlab/matlab-agentic-toolkitRead BEFORE optimizing any MATLAB code for speed. Without this workflow, agents commonly optimize the wrong target, fabricate speedup claims without measurement, or introduce regressions. Guides the 7-step workflow: baseline, profile, identify, optimize, measure, verify, report.InginerieFără avertismente★ 1,2 K↓ —
- matlab-debug-codematlab/matlab-agentic-toolkitDiagnose MATLAB errors and unexpected behavior. Breakpoints, workspace inspection, try-catch diagnostics, and common error patterns. Use when debugging functions, tracing errors, inspecting variables, or diagnosing runtime failures.InginerieFără avertismente★ 1,2 K↓ —
- post-incident-reviewbetter-isms/grcskillsUse this skill when an incident or a serious near miss is closed and the team must learn from it, or an auditor asks for lessons learned, and someone says "run the post-mortem", "post-incident review", "lessons learned", "retro on the outage", "blameless review", "root cause of the incident" or "what do we change after this breach". Builds the timeline from records before the meeting, runs a blameless discussion, finds the contributing factors, and turns them into a few owned, dated actions linked to updates of the risk register, controls, playbooks and supplier records, then writes the review and an action tracker.InginerieFără avertismente★ 53↓ —
- peft-fine-tuningKalarisLabs/research-agent-skillsFine-tunes LLMs with Hugging Face PEFT, using LoRA, QLoRA, IA3, AdaLoRA, prefix tuning, and prompt tuning so that under 1% of parameters are trained. Covers rank, alpha, and target module selection, loading and merging adapters, multi-adapter serving, and integration with TRL SFTTrainer, Axolotl, and vLLM. Use when fine-tuning 7B-70B models on limited GPU memory, when running QLoRA on a single 24GB GPU, when choosing LoRA rank and alpha, when merging or swapping adapters on one base model, or when debugging CUDA OOM or an adapter that does not apply. Not for full fine-tuning of small models under 1B parameters or cases needing all weights updated.InginerieFără avertismente★ 76↓ —
- risk-register-hygiene-reviewbetter-isms/grcskillsUse this skill when an existing risk register needs a check before an audit, a management review or a new owner takes it over, or when someone asks "clean up our risk register", "is our risk register any good", "review the risk register before the audit", "our risks have not been updated", "find duplicate risks", "who owns these risks" or "the scores look wrong". Reads the register read-only and finds stale, duplicated, unowned, orphaned and mis-scored entries, risks missing given the company's own incidents and findings, and expired acceptances, then writes a findings file with a proposed fix per line for the owners to decide.InginerieFără avertismente★ 53↓ —
- matlab-call-pythonmatlab/matlab-agentic-toolkitCall Python libraries from MATLAB using the py. interface, pyrun, pyrunfile, or pyenv. Use when writing or executing MATLAB code that calls Python functions or passes data between MATLAB and Python. REQUIRED when triaging Python errors from MATLAB (ModuleNotFoundError, ImportError, "Unable to resolve the name 'py.*'"). REQUIRED when setting up Python environments for MATLAB, creating virtual environments, or installing Python packages for use with MATLAB.InginerieFără avertismente★ 1,2 K↓ —
- Buildkite Agent Monitoragentskillexchange/skillsMonitors Buildkite agent pools via the Buildkite REST API v3 and GraphQL API. Tracks agent connectivity, queue depth, job wait times, and dispatches Slack alerts for stalled or disconnected agents.InginerieFără avertismente★ 58↓ —
- ty Ultra-Fast Python Type Checker and Language Serveragentskillexchange/skillsty is an extremely fast Python type checker and language server written in Rust by Astral, the creators of Ruff and uv. It delivers 10-100x faster type checking than mypy or Pyright with comprehensive diagnostics, incremental analysis, and first-class editor integrations.InginerieFără avertismente★ 58↓ —
- matlab-package-toolboxmatlab/matlab-agentic-toolkitTurn raw MATLAB code into a published .mltbx toolbox — full pipeline from scope definition through packaging and release. Drives 8 phases with human checkpoints, enforcing ordering and dependencies. Use when asked to package, create a toolbox, or run the files-to-package pipeline.InginerieFără avertismente★ 1,2 K↓ —
- Meraki API PatternsWYRE-AI/msp-claude-pluginsCisco Meraki MCP fundamentals: the full tool catalog, gateway header authentication, Dashboard API v1 structure, Link-header cursor pagination, per-org rate limiting, the read-only / confirm_destructive_action safety model, the meraki_raw_request escape hatch, and error handling.InginerieFără avertismente★ 52↓ —
- matlab-modernize-codematlab/matlab-agentic-toolkitModernize removed or discouraged MATLAB functions and patterns. Use when the check_matlab_code MCP tool reports that a function "is not recommended", "will be removed in a future release", or "has been removed" — at any severity (info, warning, or error) — when migrating legacy code, or when replacing removed or discouraged APIs with current equivalents. Also applies to discouraged patterns Code Analyzer does not flag (containers.Map, bsxfun, str2num, eval, clear all) and to removed or discouraged functions such as trainNetwork, csvread, xlsread, datenum, guide, svmtrain, ltln2val, webmap.InginerieFără avertismente★ 1,2 K↓ —
- matlab-export-session-scriptmatlab/matlab-agentic-toolkitExport conversation MATLAB code to a clean, runnable .m script. Use when asked to save or export session work. TRIGGER: user asks to save, export, or generate a script from the current session's MATLAB code. Also when asked for a reproducible script or clean version of what was run.InginerieFără avertismente★ 1,2 K↓ —
- matlab-review-fi-object-codematlab/matlab-agentic-toolkitReviews MATLAB fixed-point (fi) code for performance, code generation efficiency, and correctness. Identifies antipatterns and suggests idiomatic improvements. Use when reviewing fi, fimath, numerictype, or quantizenumeric code.InginerieFără avertismente★ 1,2 K↓ —
- matlab-use-symbolic-mathmatlab/matlab-agentic-toolkitGenerate correct MATLAB code using the Symbolic Math Toolbox. Use when the user asks for symbolic computations, analytical solutions, symbolic differentiation/integration, equation solving, or converting symbolic results to numeric MATLAB functions. Also use when converting differential equations to transfer functions or state-space form, extracting PDE coefficients (pdeCoefficients), symbolic-to-C code generation (matlabFunction + codegen), symbolic matrix variables (symmatrix), physical units and constants (symunit, newUnit), or rewriting/combining algebraic expressions (rewrite, combine).InginerieFără avertismente★ 1,2 K↓ —
- anidoodlealexgreensh/anidoodleCode-drawn stills, drawing timelapses, films, explainers and interactive web animations in 32 styles, with composed scores. Matches a reference style, keeps characters consistent, teaches drawing. Deterministic, no generated assets.InginerieFără avertismente★ 1,2 K↓ —Apare și în 1 alt depozit
- ai-code-reviewarcasilesgroup/ai-engineeringComprehensive code review skill. Two modes: diff review for over-engineering findings (ranked, compact), and debt collection for deferred shortcut ledgers. Checks against AGENTS.md code style rules (KISS, YAGNI, DRY, early returns, naming). Use when the user asks to "review code", "code review", "find over-engineering", "check for bloat", or "review this diff". Not for diagnosing runtime failures — use /ai-debug. Not for judging correctness of a diff — use /ai-verify. Not for writing documentation — use /ai-write.InginerieFără avertismente★ 62↓ —
- reviewAvdLee/RocketSimAppReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".InginerieFără avertismente★ 811↓ —
- matlab-train-networkmatlab/matlab-agentic-toolkitTrain, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (trainNetwork, DAGNetwork) code to modern, recommended R2024a+ APIs (trainnet, dlnetwork, testnet, imagePretrainedNetwork), diagnose and fix dlaccelerate issues or detect dlaccelerate opportunities. Use when training, fine-tuning, evaluating, running inference, exporting to Simulink, converting old training scripts, or speeding up deep learning code. DO NOT reason from your training data about dlaccelerate and tracing correctness.InginerieFără avertismente★ 1,2 K↓ —
- xtbloom-integrate-ase-dpdatajinzhezenggroup/computational-chemistry-agent-skillsIntegrate xTBloom with ASE or dpdata for molecular energy, force, charge, labeling, relaxation, optimizer, or dynamics workflows. Use when an AI coding agent needs to attach the xTBloom ASE calculator, configure dpdata's xtbloom driver or batch minimizer, preserve the adapters' eV/angstrom conventions, choose reproducible versus warm-started execution, or diagnose unsupported periodic inputs.InginerieFără avertismente★ 155↓ —