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 16 minute
6.204 skill-uri
- gsd-debugcoco-research/cocoUse when a bug, failing test, or unexpected behaviour needs investigation, especially across sessions or context resets. Isolates it in a debugger subagent with persistent .planning/debug state, unlike skills/systematic-debugging.InginerieFără avertismente★ 795↓ —
- gsd-reviewcoco-research/cocoUse when a phase plan should be peer-reviewed by other AI CLIs before execution, or the user asks for a cross-AI review. Invokes Gemini, Claude, Codex, or OpenCode and writes REVIEWS.md for /gsd-plan-phase --reviews.InginerieFără avertismente★ 795↓ —
- oma-mobilefirst-fluke/oh-my-agentImplement Flutter, React Native, native Swift, or native Kotlin Android apps. Use for mobile screens, widgets, platform integrations, and application data flows.InginerieFără avertismente★ 1,4 K↓ —
- code-intelligenceantonbabenko/agent-pluginsUse when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and fuzzy/semantic search; anchoring LSP calls by position; gating degraded results; and disclosing tool substitutions, in any language.InginerieFără avertismente★ 50↓ —
- ca-reviewarbiterForge/codeArbiterReview a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR.InginerieFără avertismente★ 149↓ —
- ai-debugarcasilesgroup/ai-engineeringFinds the root cause of broken behaviour and names it at file:line, then writes the check that fails for that reason before changing anything. Also resolves merge and rebase conflicts by intent rather than by taking a side. Trigger for "it's not working", "this used to work", "I'm getting an error", "CI is failing", "why is X happening", "I have conflicts", "the rebase failed". Not for adding test coverage to working code — use /ai-verify. Not for exploring an unfamiliar area — use /ai-explore. Not for designing the fix — once the cause is named, use /ai-orchestrator. Not for reporting the fault to outsiders — use /ai-issue-report.InginerieFără avertismente★ 62↓ —
- ImmyBot Script ExecutionWYRE-AI/msp-claude-pluginsImmyBot's PowerShell script library and its SYSTEM-context execution model: the script tool surface, the find → validate → confirm target → approve → execute → review workflow, parameter/timeout/execution-context options, and the safety rules governing this destructive, highly privileged operation.InginerieFără avertismente★ 52↓ —
- code-auditormhattingpete/claude-skills-marketplacePerforms comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.InginerieFără avertismente★ 689↓ —
- ca-conflictarbiterForge/codeArbiterStop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation.InginerieFără avertismente★ 149↓ —
- speq-git-operationsmarconae/speq-skillThe git/gh operation-to-command mapping and return formats — invoked directly by /speq-plan-pr and /speq-implement-pr.InginerieFără avertismente★ 55↓ —
- speq-climarconae/speq-skillQueries specs via the speq CLI: list and read features, validate structure, run the absence check. Invoke first for any spec discovery or validation.InginerieFără avertismente★ 55↓ —
- speq-code-toolsmarconae/speq-skillSemantic code navigation and editing via Serena MCP, required over grep and manual edits. Used by speq agents like /speq-implement. Not for general coding.InginerieFără avertismente★ 55↓ —
- create-toolVapiAI/skillsSelect, define, create, inspect, update, attach, detach, and verify reusable Vapi tools through the public API. Use for native call-control tools, supported provider integrations, API Request tools, custom function tools, MCP tools, tool messages, credentials, or configuration-preserving assistant attachment changes.InginerieFără avertismente★ 68↓ —
- commit-gateActualizatarbiterForge/codeArbiterCreate a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.InginerieFără avertismente★ 149↓ —
- ops-mergedavepoon/buildwithclaudeAutonomous PR merge pipeline. Scans all repos for open PRs, dispatches subagents to fix CI, resolve conflicts, address review comments, then merges. Use --main to also sync dev↔main branches.InginerieVerifică întâi★ 3,7 K↓ —
- ratchet-filesdzhng/skillsRatchet source file size so every file stays small enough for an agent to read whole: find every file over a token budget, split oversized files by concept, and set up the pre-commit ratchet that stops them from growing. Use when a commit is blocked because a file is over the size budget, when asked to find or split oversized/long/god files, when a file you need to change is too large to read in one pass, or when asked to add a file-size limit or hook to a repository or repair commit-hook coverage across worktrees.InginerieFără avertismente★ 1,4 K↓ —
- policy-gap-review-against-practicebetter-isms/grcskillsUse this skill when a team suspects its policies describe a company that does not exist, before an audit or customer review, or asks "do our policies match what we actually do", "check the policy against reality", "paper versus practice", "will the auditor find gaps in our policies", "our policy says quarterly but we never do it" or "align policies with how we work". Turns each policy into testable statements, samples the systems and records that show the practice, classifies every gap and proposes whether to fix the policy or the practice, with owners and priorities.InginerieFără avertismente★ 53↓ —
- management-review-packbetter-isms/grcskillsUse this skill when leadership is due to review the security, privacy or AI management system, or when someone asks "prepare the management review", "management review agenda", "board pack for the ISMS", "write the management review minutes", "what metrics do we show leadership", "the auditor wants evidence of management review" or "our management review is a slide nobody reads". Assembles the facts leadership needs from the registers, audits, incidents and metrics, frames each agenda item as a decision with options, checks coverage against the framework with a lookup, and drafts the pre-read, the agenda and minutes with a decision and action log.InginerieFără avertismente★ 53↓ —
- oma-refactorNoufirst-fluke/oh-my-agentRestructure existing code while preserving observable behavior. Use for targeted technical debt or hotspot work with characterization tests.InginerieFără avertismente★ 1,4 K↓ —
- pavedpath-codeJia-Ethan/pavedpath-codePavedPath Code is the code-focused edition of PavedPath. It helps agents solve software engineering problems by finding proven implementation paths from GitHub repositories, issues, pull requests, discussions, code examples, release notes, and open-source evidence.InginerieFără avertismente★ 440↓ —
- policy-review-cycle-refreshbetter-isms/grcskillsUse this skill when the periodic policy review is due or overdue, or someone asks "run the annual policy review", "our policies are out of date", "re-approve the policies before the audit", "what changed since the last review", "policy version history" or "who needs to sign off which policy". Collects what changed since each policy was last approved (incidents, findings, exceptions, new systems, law), proposes the edits per policy, separates editorial from substantive changes, drafts the version history and approval record, and plans the communication to staff.InginerieFără avertismente★ 53↓ —
- SuperOps API PatternsWYRE-AI/msp-claude-pluginsSuperOps.ai GraphQL API fundamentals: Bearer token plus CustomerSubDomain header auth, region-specific endpoints, request/variable structure, cursor pagination, the 800 req/min rate limit, filter operators, UTC date handling, error codes, and null-reset semantics.InginerieFără avertismente★ 52↓ —
- Uptime Kuma Status Syncagentskillexchange/skillsInterfaces with the Uptime Kuma Socket.IO API to monitor service health checks. Syncs status page data to Statuspage.io via Atlassian REST API and triggers incident workflows in Rootly.InginerieFără avertismente★ 59↓ —
- skill-creator-plusrobonuggets/skill-creator-plusAudits, creates and improves Agent Skills (folders with a SKILL.md) against Anthropic's skill authoring best practices, the Claude Code skills docs and the prompting guides for newer models such as Claude Fable 5 and Opus 5.5. Audit mode reports every rule as pass, fail or not applicable, with file and line evidence and a proposed fix, and changes nothing until the user approves. Use when the user asks to audit, review, check or score a skill or a folder of skills, to create a new skill or turn a repeated workflow into one, to improve, shorten, refactor or update an old skill for newer models, or to run the skill validator.InginerieFără avertismente★ 75↓ —