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.
47.891 de skill-uri din 2.309 depozite · actualizat acum 21 de minute
6.157 de skill-uri
- stakeholder-risk-reviewitseffi/agentic-osReview a feature or PRD for stakeholder and political risk before broad circulation.InginerieFără avertismente★ 117↓ —
- c-cpp-to-lean4-translatorArabelaTso/Skills-4-SETranslate C or C++ programs into equivalent Lean4 code, preserving program semantics and ensuring the generated code is well-typed, executable, and can run successfully. Use when the user asks to convert C/C++ code to Lean4, port C/C++ programs to Lean4, translate imperative code to functional Lean4, or create Lean4 versions of C/C++ algorithms.InginerieFără avertismente★ 260↓ —
- call-prepaAAaqwq/AGI-Super-TeamAn installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters.InginerieFără avertismente★ 112↓ —
- slackhyperfx-ai/marketing-skillsSlack messaging, file sharing, Block Kit formatting, and channel management. Use when the user wants to send Slack messages, post rich Block Kit layouts, share files, react, or manage channels and members.InginerieFără avertismente★ 107↓ —
- template-code-generatorArabelaTso/Skills-4-SEGenerate boilerplate code and project templates/skeletons automatically. Use when: (1) Creating new projects from scratch (React app, FastAPI backend, Express API), (2) Generating repetitive code patterns (CRUD endpoints, models, controllers), (3) Scaffolding components, services, or modules, (4) Creating test boilerplate, (5) Setting up monorepo structures. Provides project templates and code generation patterns for common development tasks.InginerieFără avertismente★ 260↓ —
- introspect0xDarkMatter/claude-modsAnalyze Claude Code session logs and surface productivity improvements. Extracts thinking blocks, tool usage stats, error patterns, debug trajectories - then generates friendly, actionable recommendations. Triggers on: introspect, session logs, trajectory, analyze sessions, what went wrong, tool usage, thinking blocks, session history, my reasoning, past sessions, what did I do, how can I improve.InginerieFără avertismente★ 78↓ —
- code-stats0xDarkMatter/claude-modsAnalyze codebase with tokei (fast line counts by language) and difft (semantic AST-aware diffs). Get quick project overview without manual counting. Triggers on: how big is codebase, count lines of code, what languages, show semantic diff, compare files, code statistics.InginerieFără avertismente★ 78↓ —
- file-search0xDarkMatter/claude-modsModern file and content search using fd, ripgrep (rg), and fzf. Triggers on: fd, ripgrep, rg, find files, search code, fzf, fuzzy find, search codebase.InginerieFără avertismente★ 78↓ —
- instar-sessionJKHeadley/instarPersistent Claude Code agents with scheduling, sessions, memory, and Telegram.InginerieFără avertismente★ 84↓ —
- scaffold0xDarkMatter/claude-modsProject scaffolding - generate boilerplate for common project types with best-practice defaults. Use for: scaffold, boilerplate, template, new project, init, create project, starter, setup, project structure, directory structure, monorepo, microservice, API template, web app template, CLI tool template, library template.InginerieFără avertismente★ 78↓ —
- hz-perfetto-debugmeta-quest/agentic-toolsAnalyzes Meta VR and Horizon OS VR performance using Perfetto traces — frame timing, CPU/GPU bottlenecks, render pass analysis. Use when profiling frame drops, jank, or thermal issues on Meta VR devices. Build paths: all Meta VR app stacks; use hz-quest-verify-first if the build path is unclear.InginerieFără avertismente★ 242↓ —
- debug-ops0xDarkMatter/claude-modsSystematic debugging methodology, language-specific debuggers, and common scenario playbooks. Use for: debug, debugging, bug, crash, hang, memory leak, race condition, deadlock, bisect, reproduce, root cause, breakpoint, profiling, performance issue, segfault, stack trace, core dump.InginerieFără avertismente★ 78↓ —
- hz-unity-platform-sdkmeta-quest/agentic-toolsGuides integration of the Horizon Platform SDK for Meta VR and Horizon OS Unity/C# apps — achievements, IAP, users, leaderboards, challenges, presence, notifications, abuse reporting, entitlements, asset files, application lifecycle, consent, device integrity, language packs, user age categories, and rate and review. Covers setup, initialization, API usage, data types, error handling, and best practices for all 18 public platform SDK packages.InginerieFără avertismente★ 242↓ —
- structural-search0xDarkMatter/claude-modsSearch code by AST structure using ast-grep. Find semantic patterns like function calls, imports, class definitions instead of text patterns. Triggers on: find all calls to X, search for pattern, refactor usages, find where function is used, structural search, ast-grep, sg.InginerieFără avertismente★ 78↓ —
- weekly-reviewaAAaqwq/AGI-Super-TeamAn installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters.InginerieFără avertismente★ 112↓ —
- systematic-debuggingTheGoat395/Codex-SkillsFind and repair unresolved root causes.InginerieFără avertismente★ 135↓ —
- principle-fix-root-causesadriannoes/awesome-agentic-aiApply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.InginerieFără avertismente★ 91↓ —
- counterexample-debuggerArabelaTso/Skills-4-SEDebug proof failures using counterexamples from Nitpick (Isabelle) or QuickChick (Coq) to identify specification errors, missing preconditions, and proof strategy issues. Use when: (1) A proof attempt fails and you need to understand why, (2) Counterexamples are generated by Nitpick or QuickChick, (3) Specifications may be incorrect or incomplete, (4) Theorems need validation before proving, (5) Missing preconditions or lemmas need identification, or (6) Proof failures need explanation and correction suggestions. Supports both Isabelle/HOL and Coq equally.InginerieFără avertismente★ 260↓ —
- gh-cli-pr-statscxcscmu/SkillLearnBenchComputing pull request statistics (merge time, top contributors) from gh CLI JSON output using jq.InginerieFără avertismente★ 91↓ —
- setup-api-keysonilo-ai/skillsGuides users through connecting to Sonilo — signing in with `sonilo login` (OAuth, no key), the remote OAuth plugin for Claude Code or Muse Code, or an API key for CI and headless use. Use when the user needs to configure Sonilo, wants to sign in or connect their Sonilo account, when Sonilo tools are missing, or when a call fails because no key or credential is available. First checks what already works, and only runs full setup when needed.InginerieFără avertismente★ 117↓ —
- hz-metavrx-layout-sdkmeta-quest/agentic-toolsBuild multi-window Meta Horizon OS experiences with the MetaVrx Layout SDK in Jetpack Compose or React Native. Covers framework selection, setup, anchoring, semantic offsets, window promotion, fallback, priority, lifecycle, and theming. Use for apps that need multiple app-owned panels without an immersive scene. Build path: Standard Android, including React Native; use hz-quest-verify-first if the path is unclear, and do not use this skill for immersive Spatial SDK scenes.InginerieFără avertismente★ 242↓ —
- full-output-enforcementadriannoes/awesome-agentic-aiOverrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.InginerieFără avertismente★ 91↓ —
- craft-plugin-releasemichtio/craftcms-claude-skillsReleasing Craft CMS plugins — tagging, Packagist propagation, GitHub releases, branch promotion, shared-library ordering, history rewrites. ALWAYS load when cutting, preparing, verifying, or debugging a plugin release: bumping a version, dating a changelog, creating or moving a git tag, or checking what Packagist serves.InginerieFără avertismente★ 86↓ —
- comic-asset-review-loopwanshuiyin/ARIS-Movie-DirectorPhase-1 (S5) UPSTREAM ref-asset gate — the bounded cross-model adversarial loop that LOCKS one reusable identity-locked asset (character sheet / location plate / prop cutout / text-panel / logo-free symbol) BEFORE it can be composited into any panel. This is NOT the panel_gate (composed-output) or the assembly_gate (cross-panel) — it gates the refs that FEED both, so identity drift is caught at the source, not downstream. Two layers: (1) a MANDATORY static single-source collision check (check_asset_collisions.py — 'one visual dialect, never two', enforced by tool) + zero-text/literal build-asserts; (2) a per-round 3-reviewer panel (Claude narrative ‖ Gemini visual ‖ Codex synth) that blind-scores 5 dims and LOCKS only at 准×3 unanimity (prior_lock_count>=3 approvals in the SAME round) — else regenerate (route to comic-asset-ref-generator) or, at MAX_REVIEW_ROUNDS, escalate the asset REQUIREMENT back to outline/storyboard. Hard IP veto. Use when you say 'lock this character ref', 'asset gate', 'ref review', 'isInginerieFără avertismente★ 74↓ —