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.
45,100 skills from 2,196 repositories · updated 9 hours ago
3,187 skills
- finalizeskillberry-ai/cap-evolveScore the best candidate on the held-out TEST split exactly once and seal the run. Use as the last evaluation step, after optimization stops. The run dir enforces the seal — a second finalize raises an error — so the headline number is produced once on data the optimizer never saw, the way an honest benchmark result must be.TestingNo warnings★ 66↓ —
- evaluateskillberry-ai/cap-evolveScore a candidate on a split with honest, variance-aware evaluation. Use whenever you need a number for a candidate (the algorithm calls it internally; you can also call it directly to inspect). Runs the target via the adapter for each task, scores each rollout, aggregates mean + standard error, and reports pass^k when trials > 1. Never touches the test split (that is finalize's sealed job).TestingNo warnings★ 66↓ —
- hello-worlddcc-mcp/dcc-mcp-coreExample skill - minimal greeting tool. Use only for testing standalone internal service connectivity and Skill discovery. Not for production use.TestingNo warnings★ 70↓ —
- testdriver:dashcamtestdriverai/testdriveraiRecord test execution with video and logsTestingNo warnings★ 464↓ —
- lov-xbti-gallerylovstudio/skills从已核实的社区地址或仓库列出可访问的 XBTI 人格测试案例。支持明确输入与结果回读。Use to browse a gallery of XBTI personality tests.TestingNo warnings★ 73↓ —
- lov-html2pptxlovstudio/skillsConvert HTML into a high-fidelity PPTX deck using a real browser engine (Playwright/Chromium). Each `.slide` element in the HTML becomes one pptx page (rendered as a 16:9 1920×1080 retina image), so any CSS layout — flex/grid, webfonts, gradients, SVG — survives intact. Also ships a local live editor (`edit_html.py`) so the user can tweak HTML in the browser and one-click export PPTX. Trigger when the user asks to "用 HTML 做 PPT", "html 转 pptx", "html2pptx", "html slides", "html 幻灯片", "把这个 html 导出成 ppt", "edit html and export ppt", "build a deck from html", or hands you an HTML file with `.slide` sections.TestingNo warnings★ 73↓ —
- testdriver:secretstestdriverai/testdriveraiSecurely manage passwords and sensitive data in your testsTestingNo warnings★ 464↓ —
- creative-briefcgallic/kai-cmo-harnessGenerate creative direction for ad campaigns — visual concepts, copy variants, video scripts, image specifications, and A/B test matrices. Platform-aware with format specs.TestingNo warnings★ 58↓ —
- performance-memocognyai/claude-code-marketing-skillsThe Monday memo a sharp analyst would write — joins spend on every ad platform to qualified calls, deals, revenue, refunds and churn per campaign ID, catches cheap customers who churn, and ends every line in a decision — keep, kill, change or testTestingNo warnings★ 111↓ —
- structured-datacognyai/claude-code-marketing-skillsSchema.org Structured Data Reference — JSON-LD examples for every major schema type, rich results eligibility, testing tools, and implementation patternsTestingNo warnings★ 111↓ —
- social-enginecognyai/claude-code-marketing-skillsUse organic LinkedIn and X as a free creative test kitchen — listen to what people complain about and ask for, draft a week of hooks from customer language and founder opinions, schedule only what you approve, then promote the posts the algorithm picked up into paid testsTestingNo warnings★ 111↓ —
- foreman-web-testingVisionForge-OU/foremanHeadless end-to-end / web-app testing for the Foreman e2e stage. Derive end-to-end tests from the PRD's User Flows, drive the real application the way a user would (browser flows, screenshots, accessibility checks for web apps), make them pass via the configured e2e command, and emit the FOREMAN-SUMMARY block Foreman parses.TestingNo warnings★ 443↓ —
- foreman-tddVisionForge-OU/foremanStack-agnostic test-driven development loop for a single Foreman issue. Implements one vertical slice with strict red-green-refactor (one test at a time, never horizontal slicing) using the foreman-test wrapper, saves completion evidence, then emits a machine-readable FOREMAN-SUMMARY block Foreman parses.TestingNo warnings★ 443↓ —
- verifying-a-cable-routegraph-robots/open-robot-skillsJudge a finished cable route from a camera rather than from an evaluator — re-read the cable's centreline from the clear-view camera (tracking the carried prior when the support hand still hides one end), test that rod material lies on the owed side of every station within the seat's reach, and that the hand has left the rod. Use when a routing policy must decide for itself whether every crossing is seated and it is safe to stop, and report margins so a disagreement with a scorer is diagnosable.TestingNo warnings★ 58↓ —
- hubspot-sequencesLeadMagic/gtm-skillsDesigns and optimizes HubSpot sequences: enrollment triggers, multi-channel steps, task creation, analytics, and A/B tests. Use when the user is building or fixing sequences in HubSpot Sales Hub. Triggers on: "HubSpot sequences", "HubSpot automation", "HubSpot cadence", "sales hub sequences".TestingNo warnings★ 68↓ —
- testdriver:variablestestdriverai/testdriveraiUse dynamic data and secure secrets in your testsTestingNo warnings★ 464↓ —
- testdriver:variablestestdriverai/testdriveraiUse dynamic data and secure secrets in your testsTestingNo warnings★ 464↓ —
- arize-experimentArize-ai/arize-skillsCreates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluate AI, experiment results, benchmark, A/B test models, or measure accuracy.TestingNo warnings★ 67↓ —
- rhetorical-analystinfranodus/skillsAnalyze arguments, debate tactics, and rhetorical moves across three dimensions: persuasion, rhetoric, and logic. Use when the user wants to analyze a debate, comment thread, speech, article, or any argumentative text — identifying moves, scoring effectiveness, exposing hidden assumptions, tracking logical gaps, and checking for asymmetric standards. When InfraNodus MCP tools are available, ALWAYS begin with generate_topical_clusters, generate_content_gaps, and optimize_text_structure before linear reading. Also use to stress-test arguments or understand why something feels persuasive but wrong. Trigger on: "analyze this argument", "what's wrong with this reasoning", "is this a good point", "what rhetorical moves are being used", "why is this persuasive", "break down this debate", or when a user shares text asking what's going on rhetorically.TestingNo warnings★ 122↓ —
- testdriver:quickstarttestdriverai/testdriveraiRun your first computer-use test in minutes.TestingNo warnings★ 464↓ —
- testdriver:screenshottestdriverai/testdriveraiCapture and save screenshots during test executionTestingNo warnings★ 464↓ —
- sequencing-toolkitLeadMagic/gtm-skillsComplete outreach sequencing toolkit — Smartlead, Instantly, Salesloft, Outreach, Lemlist setup and optimization. Covers mailbox rotation, warmup, A/B testing, deliverability monitoring, and multi-channel orchestration across all major sequencing platforms. Use when setting up or optimizing an outreach sequencing platform. Triggers on: "sequencing toolkit", "Smartlead setup", "Instantly optimization", "outreach platform comparison".TestingNo warnings★ 68↓ —
- strict-enforcementpovvo/claudikins-kernelUse when running claudikins-kernel:verify, checking implementation quality, deciding pass/fail verdicts, or enforcing cross-command gates — requires actual evidence of code working, not just passing testsTestingNo warnings★ 128↓ —
- testdriver:quickstarttestdriverai/testdriveraiRun your first computer-use test in minutes.TestingNo warnings★ 464↓ —