Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
49,105 skills from 2,358 repositories · updated 12 hours ago
48,055 skills
- ux-extractjezweb/claude-skillsExhaustively extract UX patterns from a reference web app. Walks every screen, captures screenshots of every state, records interaction patterns, copy verbatim, keyboard shortcuts, responsive treatments, motion, and empty/error/loading states. Produces a reusable pattern library that other audits can compare against. The inverse of ux-audit — asks 'what is the bar?' rather than 'does this match the bar?'. Trigger with 'learn from X', 'extract patterns from X', 'study X's UX', 'reverse engineer the UX of X', 'build a pattern library from X'.DesignNo warnings★ 1.1K↓ —
- jetson-customize-clocksNVIDIA/skillsUse to lock/cap Jetson CPU/GPU/EMC clocks, toggle EMC/CPU DVFS, or change cpufreq governors by editing BPMP DTB and nvpower.sh pre-flash. Do NOT use for live tuning or nvpmodel edits.WritingNo warnings★ 3.8K↓ —
- planning-with-files-esOthmanAdi/planning-with-filesPlanificación persistente basada en archivos para tareas multipaso de agentes de IA. Mantiene task_plan.md, findings.md y progress.md en disco; los hooks del ciclo de vida inyectan contexto seleccionado de planificación del proyecto. La recuperación automática solo lee los archivos de planificación del proyecto. session-catchup.py --metadata, solicitado de forma explícita, puede inspeccionar metadatos locales de sesiones del mismo proyecto; --replay puede emitir extractos limitados y enmarcados con nonce. El modo con gate opcional solo puede solicitar que el host continúe si este lo admite y nunca ejecuta comandos declarados en Markdown. El skill no tiene ninguna ruta de carga por red. Úsalo para investigación o trabajo que requiera 5 o más llamadas a herramientas.PlanningNo warnings★ 27.8K↓ —
- tos-decodermohitagw15856/pm-claude-skillsDecode a terms of service or privacy policy into what you're actually agreeing to, ranked by real-world impact. Use when someone asks 'what am I agreeing to', 'decode this privacy policy', 'is this ToS bad', or 'should I click accept'. Produces a ranked findings table with a 'should I care?' verdict per finding, covering data resale, arbitration and class-action waivers, unilateral changes, content licenses, and what deletion really means.OtherNo warnings★ 1.5K↓ —
- agentlas-operationsagentlas-ai/Agentlas-OSAgentlas 시스템 운용 절차 — hep-network 편성, hep-graph 자동화, cargo/Agent Cloud·marketplace 활용, workforce 로스터 재사용, 메모리 계약. One(개인 에이전트)이 Agentlas를 조작할 때 이 절차를 따른다.OtherNo warnings★ 1.6K↓ —
- whyNewhashgraph-online/awesome-codex-pluginsExplain why code exists in its current form by sending one investigator to each reachable evidence source and returning a cited, confidence-graded answer. Use for "why does this exist", "why was it built this way", "where did this limit come from", "is this dead code".FinanceNo warnings★ 1.5K↓ —
- meta-evalagentscope-ai/OpenJudgeUse when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessing RAG accuracy, or wants to compare prompts/models. This skill is the entry router: it asks diagnostic questions then recommends which sub-skill (local workflow) to use next.TestingNo warnings★ 1K↓ —
- brooks-healthhyhmrright/brooks-lintCombined codebase health dashboard that scores a project across all four quality dimensions — PR quality, architecture, tech debt, and test quality — in a single pass, drawing on twelve classic engineering books. Triggers when: user wants an overall quality assessment, asks "how healthy is this codebase?", "run all the checks", "I need a health score before the release", or wants to onboard a new team with a quality overview. Do NOT trigger for: server health checks, HTTP health endpoints, Kubernetes liveness/readiness probes, database health, or application uptime. Also do not trigger when the user specifically requests only one dimension — use the corresponding focused skill instead (brooks-review / brooks-audit / brooks-debt / brooks-test).TestingNo warnings★ 1.6K↓ —
- oma-qafirst-fluke/oh-my-agentReview changes for correctness, security, accessibility, and performance. Use for scoped quality reviews or verification plans; bug fixes use oma-debug.TestingNo warnings★ 1.4K↓ —Also in 2 other repos
- relational-database-web-cloudbaseTencentCloudBase/CloudBase-AI-Toolkit[Deprecated] Existing CloudBase MySQL Web SDK only. Do not recommend MySQL for new relational apps — use postgresql-development and app.rdb(). Read this only when a browser app must keep using @cloudbase/js-sdk against an environment that already has MySQL.DataNo warnings★ 1.2K↓ —Also in 5 other repos
- swift-cspSushegaad/Claude-Skills-Governance-Risk-and-ComplianceExpert SWIFT Customer Security Programme (CSP) advisor covering the Customer Security Controls Framework (CSCF v2026). Use this skill whenever a user asks about SWIFT CSP, CSCF controls, SWIFT security attestation, KYC-SA portal, SWIFT architecture types (A1/A2/A3/A4/B), mandatory vs advisory controls, independent assessment, SWIFT secure zone, secure flow zone, MFA for operators, SWIFT messaging security, payment fraud prevention on SWIFT, gap analysis for CSCF, or compliance with SWIFT's 32 controls (26 mandatory, 6 advisory in v2026) across the three objectives: Secure Your Environment, Know and Limit Access, Detect and Respond. Control 2.4 (Back-Office Data Flow Security) is now mandatory in v2026. v2026 attestation window is July 1– December 31, 2026. Trigger for any SWIFT CSP or CSCF compliance question.SecurityNo warnings★ 1K↓ —
- wiki-summarymohitagw15856/pm-claude-skillsFetch Wikipedia's current summary of any topic with zero API keys — the REST summary endpoint via curl, for answers that need today's article rather than training-data memory. Use when asked what does Wikipedia say about X, get me the current summary of a topic, check a fact against Wikipedia, or has this article changed. Produces the live extract with the article link, disambiguation handling, and a clean separation between what Wikipedia says and what the model adds.ProductivityNo warnings★ 1.5K↓ —
- tddNewhashgraph-online/awesome-codex-pluginsWhen a bug can be caught by an inexpensive local test, write that narrow failing test before the fix, check that it fails because of the bug, then fix the code and watch the test pass. Use on /tdd, "write a failing test first", "add a regression test", or when a bug has an obvious inexpensive test location.TestingNo warnings★ 1.5K↓ —
- planning-with-filesOthmanAdi/planning-with-filesPersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md, findings.md, and progress.md on disk; Kiro skill instructions and steering state read selected project planning context. Recovery reads project planning files and their timestamps only, not agent transcript stores. This adapter registers no Stop hook, never requests continuation, and never runs commands declared in Markdown. The skill has no network upload path. Use for research or work needing 5+ tool calls.PlanningNo warnings★ 27.8K↓ —
- vitestjezweb/claude-skillsSet up Vitest testing in any project — detects type (Cloudflare Workers, React, Node, library), generates vitest.config.ts, test setup, utilities, and a sample test. Covers mocking patterns, coverage config, workspace setup, Jest migration. Use whenever the user mentions adding tests, setting up Vitest, configuring tests, migrating from Jest, fixing testing infrastructure, or asks 'how do I test this'.TestingNo warnings★ 1.1K↓ —
- compliance-osalirezarezvani/claude-skillsUse when running several compliance frameworks at once: which apply, where controls overlap, a mock audit or one evidence checklist. Runs framework_selector.py, cross_framework_mapper.py, audit_simulator.py and evidence_pool_generator.py.LegalNo warnings★ 29.2K↓ —
- reading-livekit-docsfcakyon/claude-codex-settingsLooks up current LiveKit facts (API signatures, CLI flags, config options, model and provider support, SDK changelogs, pricing) from the docs instead of answering from memory. Use whenever a question touches LiveKit specifics: "does LiveKit support X", "what changed in agents 1.8", "what are the arguments to Y", "how much does LiveKit cost", "find an example of Z in the LiveKit repos", or before writing any LiveKit code. Other LiveKit skills load this one first. Covers the LiveKit Docs MCP server and the `lk docs` CLI.WritingNo warnings★ 1.2K↓ —Also in 1 other repo
- 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.PlanningNo warnings★ 1K↓ —
- nist-800-53Sushegaad/Claude-Skills-Governance-Risk-and-ComplianceNIST SP 800-53 Rev 5 compliance advisor — all 20 control families (AC, AT, AU, CA, CM, CP, IA, IR, MA, MP, PE, PL, PM, PS, PT, RA, SA, SC, SI, SR), Low/Moderate/High baseline selection, FIPS 199/200 system categorization, control tailoring and overlays, privacy controls (PT family), supply chain risk management (SR family), assessment procedures (SP 800-53A), OSCAL, RMF integration (SP 800-37), and mapping to FedRAMP, FISMA, CMMC 2.0, and ISO 27001. Use for any federal system security controls, FISMA compliance, RMF step guidance, control narrative writing, or baseline tailoring question.SecurityNo warnings★ 1K↓ —
- threat-modelmohitagw15856/pm-claude-skillsThreat-model a system or feature to find where it could be attacked, before you build it. Use when asked to threat-model, do a security design review, document security risks, identify attack surface, or apply STRIDE to a design. Produces a structured threat model: assets, trust boundaries and data flows, threats enumerated by category (STRIDE), risk scores, prioritized mitigations, and residual-risk sign-off. Defensive security for systems you own or are authorized to assess.SecurityNo warnings★ 1.5K↓ —
- redis-connectionsredis/agent-skillsRedis client and connection guidance covering connection pooling, multiplexing, pipelining, client-side caching with RESP3, avoiding slow commands (KEYS, SMEMBERS, HGETALL), and tuning socket timeouts. Use when configuring a Redis client (redis-py, Jedis, Lettuce, NRedisStack), batching commands for throughput, eliminating per-request connection creation, iterating large keyspaces with SCAN, enabling client-side caching for read-heavy workloads, or setting connect and read timeouts.OfficialOtherNo warnings★ 171↓ —Also in 1 other repo
- setupfcakyon/claude-codex-settingsThis skill should be used when user encounters "ADC not found", "gcloud auth error", "GCloud MCP error", "Application Default Credentials", "project not set", or needs help configuring GCloud integration.OtherNo warnings★ 1.2K↓ —
- compare-showshashgraph-online/awesome-codex-pluginsCompares two podcasts or YouTube shows side by side: size, latest episode, what each talks about, what both cover, and shared sponsors. Uses arcmira.OtherNo warnings★ 1.5K↓ —
- k2fcakyon/claude-codex-settingsBuild and troubleshoot Cloudflare K2 or K2 Streams durable logs. Use for stream setup, producing from Workers or HTTP, configuring retention and inputs, and consuming through subscriptions.DevOpsNo warnings★ 1.2K↓ —
02-ref-hallucination-arena
agentscope-ai/OpenJudge
ScienceUpdated 19 hours ago
From the author
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
Install
npx skills add agentscope-ai/OpenJudge --skill 02-ref-hallucination-arena -a claude-code
Installs to .claude/skills/02-ref-hallucination-arena/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 88
Security100
Provenance76
Maintenance100
Licence100
Adoption49
Files (1)
- SKILL.md