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.
21,305 skills from 781 repositories · updated 10 minutes ago
1,364 skills
- meta-tags-optimizerViryaZheng/recomby-geoOptimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media preview", "my click rate is low", "title optimization", or any meta tag task.TestingNo warnings★ 458↓ —
- matlab-use-machine-learning-appsmatlab/matlab-agentic-toolkitUse when the user wants to train, compare, or export machine learning models using Classification Learner or Regression Learner — including opening the app, loading data, training models, evaluating metrics, comparing results, visualizing plots, testing on held-out data, exploring model interpretability, and exporting trained models. Programmatic access to Classification Learner and Regression Learner apps via AppController.TestingNo warnings★ 1.2K↓ —
- elevenlabs-agentsjezweb/claude-skillsBuild conversational AI voice agents on the ElevenLabs platform. Configure agent + tools + knowledge base, integrate SDK (React / React Native / Swift / JS / server-side), test, deploy. Use whenever the user mentions ElevenLabs, building a voice agent, an AI phone system, an AI receptionist, conversational AI, or troubleshooting deprecated @11labs packages, webhook errors, CSP violations, localhost allowlist, or tool parsing errors.TestingNo warnings★ 1.1K↓ —
- minutes-verifysilverstein/minutesVerify that Minutes is properly set up and working — model downloaded, mic accessible, directories exist, no stale state. Use when the user says "is minutes working", "check my setup", "verify minutes", "test recording setup", "why isn't minutes working", "minutes health check", or after running setup for the first time.TestingNo warnings★ 1.6K↓ —Also in 1 other repo
- implementhashgraph-online/awesome-codex-pluginsChange or repair code, config or services without weakening tests; report what ran and what did not. Use when: implementing a change or fixing a defect.TestingNo warnings★ 1.4K↓ —
- simulink-collect-metricsmatlab/simulink-agentic-toolkitCollect and assess quality metrics for Simulink models using the metric.Engine API. Use when evaluating model design quality (maintainability, complexity, architecture) or testing completeness (unit testing, SIL, PIL, coverage, pass rates) after edits or test runs. Covers metric discovery, collection, report generation, and diagnostics. Triggers on: "collect metrics", "quality metrics", "metric.Engine", "testing metrics", "maintainability metrics", "SIL metrics", "PIL metrics", "what metrics are available", "assess quality", "coverage metrics", "generate metric report", "diagnose metric errors".TestingNo warnings★ 1.3K↓ —
- cross-video-qaJimLiu/baocut用户问「我哪一期讲过 X」「这几部视频里谁说过 Y」「X 在我的视频里是怎么讲的」「有哪些讲 X 的视频」这类要在多部视频里找答案的问题时用：按意思检索、按视频去重、按当前版本重新定位，只凭找回来的原话回答，每条论断注明视频与时间，覆盖不全时说明。不用于总结或改写一部视频（那是总结、博客），也不改视频。TestingNo warnings★ 1.3K↓ —
- divorce-practice-stephane-boghossianlawve-ai/awesome-legal-skillsAI co-counsel for divorce and family-law attorneys — a jurisdiction-portable scaffold spanning the full matter lifecycle. Eight operating modes mirror how a matter actually moves: intake and onboarding, financial disclosure, children and support, property division and QDRO, discovery and document review, drafting, negotiation and mediation prep, and court prep — plus post-judgment modification and enforcement. The methodology is jurisdiction-agnostic: it forces real, verifiable research for every local form, formula, or rule rather than inventing one, handling common-law, community-property, civil-law, and MENA personal-status regimes as variables. Built around one non-negotiable: privilege. It drafts, analyzes, organizes, and pressure-tests. It is not the lawyer.TestingNo warnings★ 891↓ —
- maintainNewhashgraph-online/awesome-codex-pluginsUse this to find out whether an existing dbt project or semantic layer (dbt, Ossie or SLayer) is correct against its warehouse, and if not, why. `maintain verify` checks the project as it stands; against a .dex/ snapshot, `maintain check` finds schema, volume, grain, and semantic drift and `maintain reconcile` proposes the fix. Reach for it whenever an existing project is suspected wrong, whether or not anything is known to have changed: "this model is wrong, work out why", "the numbers look too high", "some rows are missing", "this column is empty", "duplicates in my fact table", "the project is broken", "diagnose why this test fails", "a test fails and nobody changed the model", "the dashboard moved but the code did not", "did anything drift", "the row count dropped", "the metric definition changed". Read-only; fixes come back as reviewable diffs and never overwrite hand-written work. Writing the fix, or repairing a model you just edited, is transform's; a data question with no project is explore's.TestingNo warnings★ 1.4K↓ —
- scenario-roblox-environmentNewscenario-labs/skillsUse when building or lighting a Roblox map: graybox or blockout, level layout, landmarks, doors and walls, parts versus unions (CSG), collision fidelity, terrain (generate, sculpt, paint, water, Part to Terrain), MaterialVariants, custom terrain materials, PBR textures from Scenario, skyboxes, Lighting, Atmosphere, Clouds, bloom, color correction, day or night moods, interior light, scattering rocks, bushes and trees, level of detail (SLIM, RenderFidelity), per-model streaming or a streaming test, collision overlays, invisible walls, or texture sizes. Also when a map looks flat, foggy, too dark or plastic, grass pokes through floors, a doorway blocks players, content pops in or never unloads, a custom material disappears, or the sun lights the wrong side.TestingNo warnings★ 1.1K↓ —
- simulink-explain-missing-coveragematlab/simulink-agentic-toolkitUse this skill when the user asks to summarize, or asks why Simulink Coverage objectives are missing, unsatisfied, or uncovered on a coverage result they already have — why specific decision, condition, MCDC, relational-boundary, or saturation/overflow outcomes weren't exercised, whether uncovered logic is dead code, or how to close the gap (a test, a coverage filter, or a design change). It reads an existing cvdata, .cvt file, sim-with-coverage output, or Simulink Test result; it never runs cvsim to collect coverage.TestingNo warnings★ 1.3K↓ —
- idea-geniehashgraph-online/awesome-codex-pluginsBrainstorm evidence-backed options for what to build, or stress-test an idea. Use when: deciding what to build next, comparing options or testing an idea.TestingNo warnings★ 1.4K↓ —
- simulink-instrument-real-time-applicationmatlab/simulink-agentic-toolkitSet up signal capture for a Simulink Real-Time application using `slrealtime.Instrument`. Use when choosing which signals a real-time application captures and where the data goes — test-pointing or canvas-badging a signal before build (`TestPoint`, `DataLogging`), constructing an Instrument from an `.mldatx`, calling `addSignal`, `addInstrumentedSignals`, `addFileLogSignals`, `validate`, `connectCallback`, `copy`, or `generateScript`, attaching an instrument to `tg.Instruments` via `addForFileLog`, `addForSDI`, or `addForMATLAB`, setting up live-streaming signals, dynamic file-log workflows, or persisting an instrument as M-code. Selects and routes signals only — not for configuring, building, running, or connecting applications onto targets.TestingNo warnings★ 1.3K↓ —
- testhashgraph-online/awesome-codex-pluginsWrite or assess tests that prove behavior and would fail without the fix. Use when: writing tests, TDD, or asked whether a green test is enough.TestingNo warnings★ 1.4K↓ —Also in 2 other repos
- pre-motion-andrew-birdlawve-ai/awesome-legal-skillsAdversarial premortem for England & Wales civil litigation - builds the strongest version of a case, then attacks it from four angles to find where it loses before opposing counsel does. Runs an adversarial premortem on a UK litigation matter. Builds the strongest version of the case, then attacks it from four angles — procedural, substantive, evidentiary, strategic — to find where it actually loses. Returns a ranked stress-test brief: failure scenarios, evidence inconsistencies, blind spots, mitigations, and one brutal one-sentence verdict. Use before issue, before settlement negotiations, before a litigation-funder pitch, or before deciding whether to take a case.TestingNo warnings★ 891↓ —
- founder-pricingJakeschincariol/founder-skillFinds the price buyers will actually pay. Reads the consumer panel's four price answers per buyer into a Van Westendorp price-sensitivity range (too cheap, a bargain, getting expensive, too expensive), sets it against what competitors really charge and against the CFO's margin, and recommends a price, a price ladder (good / better / best) and an opening offer to test. Use when the user says "how much should I charge", "price this", "is $X too expensive", "pricing strategy", "what price", or after the consumer panel.TestingNo warnings★ 1.5K↓ —
- vapiAnil-matcha/awesome-muse-connectorsManage Vapi voice AI: assistants, phone numbers, calls. Outbound calls are high actuation and need exact-match confirmation; test numbers by default. Trigger phrases: vapi, voice assistant, outbound call, AI phone call.TestingNo warnings★ 1.4K↓ —
- qa-reviewarjun988/blender-skillsProduction QA gate for Blender assets using viewport screenshots, validation checklists, naming audits, and ship/no-ship verdicts via MCP.TestingNo warnings★ 388↓ —Also in 1 other repo
- ambiguity-reportlawve-ai/awesome-legal-skillsTurn an interpretive-ambiguity audit of a legal text — contract, statute, regulation, or judicial opinion — into a polished deliverable. Produces a multi-page website (default), a single-page interactive site, a Microsoft Word document, a PowerPoint deck, or a LaTeX/PDF. Use whenever a user has a stress-test result, ambiguity audit, or "where will this be litigated" scenarios and wants to publish, present, or share them. Triggers on "publish the audit," "make a report from this," "turn this into a website / deck / brief / Word doc," "make a Netlify site," "build slides of these ambiguities," "render the scenarios," "package this stress test," "produce a LaTeX version," and similar. Pairs with the ambiguity-stress-test skill (the underlying analysis) but works on any structured or semi-structured ambiguity analysis. Visual design is opinionated but the user can override colors, fonts, and brand label. Most formats need Python and a writable filesystem; single-file HTML works where the host has neither.TestingNo warnings★ 891↓ —
- recsys-book-qaNewjhljx/RecSys-Industrial-BookAnswer recommendation-system questions from the released book PDFs with chapter and page citations. Use for explanations, comparisons, formulas, architecture concepts, and questions asking what the book says.TestingNo warnings★ 468↓ —
- vid-motion-graphicsVarnan-Tech/opendirectoryGenerates motion graphics videos (MP4) from a content brief. Multi-scene HTML/CSS animations rendered frame-by-frame in headless Chromium via Playwright, assembled with FFmpeg. 1080×1080 default, 16:9 (1920×1080) and 9:16 (1080×1920) supported. 5 style presets. Trigger when user says "create a video", "motion graphic", "animated video", "make a reel", "create an explainer", "animated infographic", or "short video".TestingNo warnings★ 685↓ —
- owner-intent-auditsno-ai/sno-station-skillsCheck agent-produced plans, tests, or code against the owner's actual intent. Find missing meaning, unrequested work, stale truth, unreachable decisions, unsupported completion claims, and implementation debt. Use before approval or merge.TestingNo warnings★ 638↓ —
- pleading-injection-guardlawve-ai/awesome-legal-skillsDetects prompt injection hidden in documents from the other side (pleadings, skeletons, bundles, served evidence, opponents' emails and attachments) before an AI reads them, so the model is not turned against your client. Checks word by word that the text an extractor hands the model was visibly drawn on the page: white, near-white, covered, clipped, off-page, tiny, transparent and invisible-mode text in PDF (ink test plus OCR); Word formatting resolved as Word does (styles, shading, theme colours, scaling, off-page frames, fallbacks, unused headers); HTML/CSS, RTF, email with attachments and zips, xlsx/pptx and legacy formats. Flags Unicode smuggling, text addressed to an AI and authorities found only in hidden text. Fails closed. Optional Read-tool hook. Use BEFORE any AI summary or analysis of an opposing or third-party document. Triggers: 'scan for injection', 'is this document safe', 'check the other side's skeleton', 'injection guard'.TestingNo warnings★ 891↓ —
- recsys-book-qaNewjhljx/RecSys-Industrial-BookAnswer recommendation-system questions from the released book PDFs with chapter and page citations. Use for explanations, comparisons, formulas, architecture concepts, and questions asking what the book says.TestingNo warnings★ 468↓ —