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.
49.409 skill-uri din 2.375 de depozite · actualizat acum 3 ore
49.409 skill-uri
- report-issuemicrosoft/power-platform-skillsUse when the user wants to report a bug, file an issue, submit a bug report, or report any problem with the mobile-app plugin.AlteleFără avertismente★ 1,1 K↓ —
- minutes-ingestsilverstein/minutesExtract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", or wants their PARA/Obsidian/wiki profiles updated from conversation data.ProductivitateFără avertismente★ 1,6 K↓ —Apare și în 1 alt depozit
- 00-arena-routeragentscope-ai/OpenJudgeUse when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.PlanificareFără avertismente★ 1 K↓ —
- oma-academic-writingfirst-fluke/oh-my-agentDraft and revise academic prose against a rubric, evidence, and citation requirements. Use for essays, reports, literature reviews, or academic style audits.RedactareFără avertismente★ 1,4 K↓ —Apare și în 1 alt depozit
- shiphashgraph-online/awesome-codex-pluginsShip phase. Runs isolated integration test in a fresh worktree, creates a PR with full spec + audit report in the body, watches CI, and auto-fixes failures.TestareFără avertismente★ 1,5 K↓ —
- improve-search-visibility-citation-checkgooseworks-ai/goose-skillsStep of the improve-search-visibility playbook: runs the agreed buyer questions on AI and Google surfaces, records every run and scores how often the brand is named. Run improve-search-visibility instead; not for direct use.AlteleFără avertismente★ 1,3 K↓ —
- oma-pmNoufirst-fluke/oh-my-agentTurn product requirements into scoped tasks with dependencies and acceptance criteria. Use for implementation planning and prioritization.PlanificareFără avertismente★ 1,4 K↓ —
- helphashgraph-online/awesome-codex-pluginsShow KERNEL help. The unified skill system, state operations, agents, current plugin status. Triggers: help, how, what, skills, commands.AlteleFără avertismente★ 1,5 K↓ —
- blog-page-generatorkostja94/marketing-skillsDeprecated compatibility entry for Blog Index construction. This page is now maintained in Pagina; install and use page-builder to build a new Blog Index.RedactareFără avertismente★ 1,1 K↓ —
- 01-auto-arenaagentscope-ai/OpenJudgeAutomatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.TestareFără avertismente★ 1 K↓ —
- design-systemdaveebbelaar/bamaAccent color and design system for a macOS app, from the app's accent and the accent picker in Settings to Swift tokens in code plus a design/DESIGN-SYSTEM.md that says which token to use when. Use when the user wants a brand or accent color, wants people to pick a color, when an app has more than a few screens, when screens drift apart or animations feel inconsistent, or when the user asks for themes, a style guide, or design tokens.DesignFără avertismente★ 1,5 K↓ —
- minehashgraph-online/awesome-codex-pluginsUse only when the user explicitly asks to run, set up, update, re-mine, or deepen Emulo from real local AI coding-session history.InginerieFără avertismente★ 1,5 K↓ —Apare și în 2 alte depozite
- testing-livekit-agentsfcakyon/claude-codex-settingsWrites turn-level tests for a LiveKit agent in the user's normal test suite: pytest (Python) or Vitest (Node.js). Use when the user asks to "write tests for my agent", "add a test for this tool", "test the handoff", "pin this bug", "why does my agent test fail", or after building or changing agent behavior that needs regression coverage. Covers the SDK's test session harness, assertions on messages, tool calls and handoffs, LLM judging of a reply against an intent, mocking tools, multi-turn tests, and judging whole conversations with the built-in judges. For interactive poking use debugging-livekit-agents. For grading whole conversations at scale use running-livekit-simulations.TestareFără avertismente★ 1,2 K↓ —Apare și în 1 alt depozit
- oma-scmfirst-fluke/oh-my-agentManage Git branches, merges, conflicts, commits, and release baselines. Use for repository history and change-management operations.InginerieFără avertismente★ 1,4 K↓ —
- oma-dbfirst-fluke/oh-my-agentDesign schemas and migrations, tune queries, or plan vector retrieval and database operations. Application API implementation uses oma-backend.DateFără avertismente★ 1,4 K↓ —
- research-audience-signals-and-hooksgooseworks-ai/goose-skillsFor a list of companies, finds dated, linked timing signals from the last 90 days (funding, new leaders, hiring, launches), drops stale ones and noise, scores timing, and gives one personal hook per person from their recent public work. Facts only, no message copy. Use alone when you already have the company list and, for hooks, the people; otherwise run research-audience.ȘtiințăFără avertismente★ 1,3 K↓ —
- cvpr-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing a CVPR submission before the OpenReview deadline, covering abstract registration and profile requirements, the 8-page limit including figures and tables, the Compute Reporting Form, anonymity and external-link bans, dual-submission attestations, reviewer-duty enrollment, and desk-reject triage.PlanificareFără avertismente★ 1,4 K↓ —
- atc-related-workbrycewang-stanford/Awesome-Journal-SkillsUse when writing or auditing the related-work and positioning of an ATC (ACM SIGOPS Annual Technical Conference, formerly USENIX ATC) systems paper — covering the systems literature lanes, positioning against OSDI/SOSP/NSDI/EuroSys/FAST, writing delta-first comparisons, and keeping self-citation double-blind.ȘtiințăFără avertismente★ 1,4 K↓ —
- icdm-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an ICDM (IEEE International Conference on Data Mining) submission for readiness, covering Research-vs-Applied track choice and its anonymity regime, the triple-blind sweep, the 10-page IEEE all-inclusive cap, the single June deadline, in-paper artifact references, and the desk-level triggers that get an ICDM paper rejected without review.ȘtiințăFără avertismente★ 1,4 K↓ —
- kdd-camera-readybrycewang-stanford/Awesome-Journal-SkillsUse when preparing an accepted KDD paper for ACM proceedings, covering the 12-page proceedings budget with 9 content pages, the extra content page over the submission, the 3-page cap on references plus appendix, ACM e-rights and TAPS source processing, ACM Open APC status, de-anonymization, and Digital Library metadata for SIGKDD.ȘtiințăFără avertismente★ 1,4 K↓ —
- sci-abstractbrycewang-stanford/Awesome-Journal-SkillsUse when writing the two front-matter artifacts Science (AAAS) demands — the one-sentence summary for the table of contents and the ≤125-word single-paragraph abstract — both readable by any scientist and both leading with the quantified advance rather than the method. Late-stage polish skill for the flagship AAAS weekly.ȘtiințăFără avertismente★ 1,4 K↓ —
- sosp-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing a SOSP submission for HotCRP readiness, covering the abstract-registration and full-paper deadlines, the 12-page technical-content limit with references excluded, the 7x9-inch two-column format, double-blind rules with paper-ID substitution, conflict declaration under PC-chair audit, and desk-reject triage.ȘtiințăFără avertismente★ 1,4 K↓ —
- podc-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing an ACM PODC submission for HotCRP readiness, covering the two-step abstract-registration then full-paper deadline, the ACM Master template with the 10-page-merits budget and unbounded full version, lightweight double-blind anonymization, the regular-paper-vs-Brief-Announcement choice, and desk-risk triage before the AoE cutoff.ȘtiințăFără avertismente★ 1,4 K↓ —
- wsdm-submissionbrycewang-stanford/Awesome-Journal-SkillsUse when auditing a WSDM submission before the August deadlines - EasyChair setup, the abstract-then-paper week, the appendix-inclusive page budget, the required ethical-considerations section, anonymization that survives Associate-Chair metadata visibility, and desk-reject exposure at a no-rebuttal venue.ȘtiințăFără avertismente★ 1,4 K↓ —
claude-authenticity
agentscope-ai/OpenJudge
TestareActualizat acum 17 ore
De la autor
Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code below and run, no extra packages beyond httpx. Use when the user wants to verify a Claude API key or endpoint, check if a third-party Claude service is authentic, audit API providers for Claude authenticity, test multiple models in parallel, or discover what system prompt a provider has injected.
Instalare
npx skills add agentscope-ai/OpenJudge --skill claude-authenticity -a claude-code
Se instalează în .claude/skills/claude-authenticity/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Descarcă .zip
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
La ce are acces
Doar instrucțiuniFolosește rețeauaLicență: APACHE-2.0
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 88
Securitate100
Proveniență76
Întreținere100
Licență100
Adopție49
Fișiere (1)
- SKILL.md