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.
48.168 de skill-uri din 2.325 de depozite · actualizat acum 8 ore
6.204 skill-uri
- source-command-refactor-safelylegioncodeinc/vibe-coding-toolsConvert bloat evidence into bounded behavior-preserving repairs with baseline and rollback proof.InginerieFără avertismente★ 94↓ —
- source-command-verify-refactorlegioncodeinc/vibe-coding-toolsCompare pinned refactor behavior, performance, and accepted interfaces with explicit evidence limits.InginerieFără avertismente★ 94↓ —
- reviewing-ai-output-groundednessjaktestowac/awesome-copilot-for-testersHuman review protocol for whether AI output is grounded in its sources: claim-by-claim attribution, hallucination classes, citation verification, sampling that is defensible, and a recorded attestation because groundedness cannot be fully automated. Also covers the responsible-AI pass - harmful output, bias, disclosure and privacy. Use when reviewing a RAG or summarisation feature, when factuality matters more than fluency, or when an eval suite needs the human check it cannot replace.InginerieFără avertismente★ 118↓ —Apare și în 1 alt depozit
- source-command-review-software-licenselegioncodeinc/vibe-coding-toolsExplain and inventory software license evidence, distribution boundaries and unresolved review questions without relabeling rights.InginerieFără avertismente★ 94↓ —
- source-command-launch-productlegioncodeinc/vibe-coding-toolsPrepare an evidence-based product launch with customer fit, channel focus, review readiness, and measurable follow-up.InginerieFără avertismente★ 94↓ —
- api-callerNVIDIA/SkillEvaluatorCall any REST API dynamically. Make GET, POST, PUT, DELETE requests to any endpoint with custom headers and JSON body.InginerieFără avertismente★ 617↓ —
- carrel-searchFengZhenfei/carrelQuery the user's local knowledge bases through the Carrel search API, use original text and source images as needed in the answer, list the reference files and offer follow-up directions drawn from the knowledge graph. Use when the user asks to search the knowledge base, find evidence in the stored material, compare records, or answer from several documents together.InginerieFără avertismente★ 673↓ —
- source-command-work-like-a-teamlegioncodeinc/vibe-coding-toolsTurn a solo or small-team development goal into a five-area responsibility map, a working queue, a Definition of Done, and a review rhythm.InginerieFără avertismente★ 94↓ —
- source-command-perform-website-auditlegioncodeinc/vibe-coding-toolsRun a full Website Auditor by Legion Code Inc. engagement end to end: intake through scored, branded reports, dispatching the 20 Drone/Stinger pairs in dependency order.InginerieFără avertismente★ 94↓ —
- triagenota-america/forgecat-agent-profilesTriage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.InginerieFără avertismente★ 93↓ —
- zoom-outnota-america/forgecat-agent-profilesTell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.InginerieFără avertismente★ 93↓ —
- full-output-enforcementnota-america/forgecat-agent-profilesOverrides 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★ 93↓ —
- rwanda-vatopenaccountants/openaccountantsUse this skill whenever asked to prepare, review, or classify transactions for a Rwanda VAT return. Standard rate 18%. Mandatory EBM (Electronic Billing Machine). No EBM = no input recovery. EAC member. ALWAYS read before handling Rwanda VAT work.InginerieFără avertismente★ 468↓ —
- turkey-vatopenaccountants/openaccountantsUse this skill whenever asked to prepare, review, or classify transactions for a Turkey VAT (KDV — Katma Değer Vergisi) return or advise on Turkish VAT registration, filing, and reporting. Trigger on phrases like "prepare KDV return", "Turkish VAT", "KDV beyannamesi", "ÖKC fatura", or any Turkey VAT request. ALWAYS read this skill before touching any Turkey KDV-related work.InginerieFără avertismente★ 468↓ —
- caveman-statsnota-america/forgecat-agent-profilesShow real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.InginerieFără avertismente★ 93↓ —
- zambia-vatopenaccountants/openaccountantsUse this skill whenever asked to prepare, review, or classify transactions for a Zambia VAT return. Standard rate 16%. Unique 100% withholding VAT mechanism. ALWAYS read before handling Zambia VAT work.InginerieFără avertismente★ 468↓ —
- catch-reportsno-ai/sno-station-skillsReport how many problems the two brains found: mutual review (the other model checks the work, from the peer-review records) and self-check (an agent finds its own error in its own conversation, judged by that agent's own model), side by side. Use when the owner asks whether the second agent or the reviews are worth it, or wants the week's review results.InginerieFără avertismente★ 858↓ —
- rem-reflectsno-ai/sno-station-skillsSelf Learning from this machine's Claude Code, Codex, Hermes, OpenClaw and Cursor sessions. Decide skill changes and lessons with accept/reject/tbd; recall lessons at session start.InginerieFără avertismente★ 858↓ —
- using-git-worktreesnota-america/forgecat-agent-profilesUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackInginerieFără avertismente★ 93↓ —
- antislopnota-america/forgecat-agent-profilesAnti Slop: Rules for AI Coding Agents. The core filter. Load always to stop generic AI slop.InginerieFără avertismente★ 93↓ —Apare și în 2 alte depozite
- full-output-enforcementnota-america/forgecat-agent-profilesOverrides 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★ 93↓ —Apare și în 2 alte depozite
- receiving-code-reviewnota-america/forgecat-agent-profilesUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationInginerieFără avertismente★ 93↓ —
- requesting-code-reviewnota-america/forgecat-agent-profilesUse when completing tasks, implementing major features, or before merging to verify work meets requirementsInginerieFără avertismente★ 93↓ —
- bolivia-ivaopenaccountants/openaccountantsUse this skill whenever asked to prepare, review, or classify transactions for a Bolivia IVA (Impuesto al Valor Agregado) return for any client. Trigger on phrases like "Bolivia IVA", "Bolivia VAT", "SIN filing", "factura", or any request involving Bolivia IVA. MUST be loaded alongside vat-workflow-base v0.1 or later. ALWAYS read this skill before touching any Bolivia IVA work.InginerieFără avertismente★ 468↓ —