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.
49,492 skills from 2,391 repositories · updated 16 hours ago
49,492 skills
- scenario-ugcscenario-labs/skillsUse when producing UGC-style creator video with Scenario: a talking-head ad or testimonial from a portrait and a script, a founder clip, a product demo or unboxing, a reaction or before-after cut, a faceless voiceover over b-roll, or vertical social video for TikTok, Reels, or Shorts that must feel filmed on a phone rather than produced. Keywords: UGC, creator ad, talking head, testimonial, avatar, lipsync, founder video, social proof, faceless voiceover, organic, vertical video.MediaNo warnings★ 2.2K↓ —
- primer-designK-Dense-AI/scientific-agent-skillsDesigns and audits PCR and RT-qPCR primers with Primer3, explicit thermodynamic conditions, reference-based off-target amplification searches, and traceable sequence coordinates. Use for designing primer pairs, checking existing primers, exon-junction or isoform-specific assays, variant masking, cloning tails, multiplex compatibility, and interpreting Primer-BLAST results. Includes bounded local in-silico PCR and BLAST screening; distinguishes computational candidates from experimentally validated assays.DesignNo warnings★ 56.1K↓ —
- adjudicate-reviewpedrohcgs/claude-code-my-workflowTurn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread damage correct work. Every finding is a CANDIDATE until checked against the actual source. Use whenever you receive review comments, audit findings, or a critique you did not write yourself, especially when the reviewer is a model or when the volume is too large to check by feel.EngineeringNo warnings★ 1.7K↓ —
- scenario-moderationscenario-labs/skillsUse when a Scenario generation is blocked, refused, or returns a moderation or sensitive-content error, when a video is rejected after rendering or its audio track is flagged, when an output is flagged for likeness to a real person or for IP and copyright detection, when the same prompt passes on one model and fails on another, or when a team's own characters, weapons, or props get flagged. Keywords: blocked prompt, content moderation, refused generation, provider filter, false positive.MediaNo warnings★ 2.2K↓ —
- what-if-oracleK-Dense-AI/scientific-agent-skillsSupports structured what-if scenario analysis for research planning, experimental contingencies, and scientific project decisions. Explores favorable, reference, adverse, wild-card, contrarian, and second-order scenarios with explicit assumptions, evidence, and decision triggers. Use to stress-test a research plan under uncertainty; scenario narratives do not estimate causal effects or calibrated forecast probabilities.TestingNo warnings★ 56.1K↓ —
- scenario-audioscenario-labs/skillsUse when generating or handling audio on Scenario via MCP. Triggers include music tracks, full-length songs with vocals written from lyrics, background scores, soundtracks, game sound effects, SFX, foley, ambience, looping audio, voiceover, narration, speech, TTS, text-to-speech, dialogue, voice cloning, re-voicing a recording, scoring or adding sound to a video, transcription, or requests to create, wait on, play, or download audio files (MP3, WAV) with Scenario tools.MediaNo warnings★ 2.2K↓ —
- mex-relaymex-memory/mexPrepare and manage durable MEX team handoffs. Use when the user asks to hand work to a person or team, prepare an end-of-session handoff, save what the next engineer needs, create a MEX Relay, take or close a Relay, or explicitly invokes /mex-relay or $mex-relay. Treat Relay as a memory and context baton, not chat, notifications, task assignment, issue tracking, or a Jira replacement; do not activate for ordinary status messages that are not durable handoffs.ProductivityNo warnings★ 1.8K↓ —Also in 1 other repo
- pkedgeLeoYeAI/agent-master-skillsMonitor Polymarket prediction markets, spot mispricings between crowd probabilities and real-world evidence, track whale positioning from the top-50 leaderboard wallets, and detect fresh wallet insider signals. Supports four modes: SCAN (daily digest of flagged markets), DEEP DIVE (full single-market analysis with web search evidence), WHALE WATCH (consensus detection across top trader positions), and INSIDER WATCH (fresh wallet large-position detection).OtherNo warnings★ 2.2K↓ —
- mex-inboxmex-memory/mexDraft and review contributions to existing MEX project knowledge. Use when the user asks to capture a discussion or decision in project knowledge, propose an addition or correction for team review, or explicitly invokes /mex-inbox or $mex-inbox. Also supports existing Spec proposals. Do not activate for brainstorming alone, routine GROW upkeep, email inboxes, session logs, or handoffs.PlanningNo warnings★ 1.8K↓ —Also in 1 other repo
- venue-templatesK-Dense-AI/scientific-agent-skillsPrepares journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Supports selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.DocumentsNo warnings★ 56.1K↓ —
- scenario-3d-worldsscenario-labs/skillsUse when generating navigable 3D worlds or Gaussian splat scenes on Scenario via MCP: text-to-world, image-to-world, a 360 panorama or skybox turned into a walkable splat, multi-view photos or a video walkthrough reconstructed as a splat, or one object photo to splat. Keywords: World Labs Marble 1.1, 1.1 Plus, 1.0 Draft, Hunyuan World, HY World, image-to-skybox, skybox-to-splat, multiview-to-splat, TripoSplat, gaussian splatting, 3DGS, spz, world generation, explorable scene, VR.MediaNo warnings★ 2.2K↓ —
- code-reviewcbrock84/headcountConducts and responds to code review — reviewing a change for correctness, design, and risk, and evaluating review feedback received on your own work. Use this before merging, when asked to review a diff or pull request, when review feedback has arrived and needs acting on, or when feedback seems wrong and needs a reasoned response rather than compliance.EngineeringNo warnings★ 2.6K↓ —
- open-notebookK-Dense-AI/scientific-agent-skillsOrganizes research with the self-hosted Open Notebook alternative to NotebookLM. Supports source ingestion (PDFs, web pages, audio, video, and Office documents), cited document chat, text and vector search, notes, custom transformations, and multi-speaker podcasts. Use when automating Open Notebook through its REST API or configuring its local or cloud AI providers, including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral.MediaNo warnings★ 56.1K↓ —
- mex-relaymex-memory/mexPrepare and manage durable MEX team handoffs in git-native project memory. Use when the user asks to hand work to a person or team, prepare an end-of-session handoff, save what the next engineer needs, create a MEX Relay, take or close a Relay, or invokes /mex-relay or $mex-relay. Keywords: mex, project memory, relay, handoff, team memory, Claude Code, Codex. Treat Relay as a memory baton, not chat, notifications, task assignment, issue tracking, or a Jira replacement; do not activate for ordinary status messages that are not durable handoffs.EngineeringNo warnings★ 1.8K↓ —
- buzzLeoYeAI/agent-master-skillsReal-time news aggregator with Discord & Telegram push. Manage Jin10, BlockBeats, RSS, X KOLs, Polymarket, OpenNews via REST API.EngineeringNo warnings★ 2.2K↓ —
- disclosure-checkpedrohcgs/claude-code-my-workflowPre-screen analysis outputs (tables, figures, logs) built on restricted or confidential data for statistical-disclosure-limitation problems before any release. Scans for small cell counts, complementary-suppression gaps, dominance (p-percent / (n,k)), re-identifiable exact counts, PII leakage, and unrounded sensitive statistics; classifies each finding CRITICAL / WARNING / OK and gates on any CRITICAL. Use before depositing or sharing restricted-data results, or when the user says "disclosure check", "SDL scan", "is this output safe to release", "check for small cells", "disclosure avoidance", "pre-screen for the RDC", or "can I export this from the enclave".OtherNo warnings★ 1.7K↓ —
- mex-inboxmex-memory/mexDraft and review contributions to existing MEX project knowledge in the repo wiki. Use when the user wants to capture a team decision, convention, or architecture note, propose an addition or correction for team review, or invokes /mex-inbox or $mex-inbox. Also supports existing Spec proposals. Keywords: mex, project memory, CLAUDE.md, team memory, drift, inbox. Do not activate for brainstorming alone, routine GROW upkeep, email inboxes, session logs, or handoffs.PlanningNo warnings★ 1.8K↓ —
- api-gateway-mcp-servergoogle/skillsConfigures Google Cloud API Gateway to act as a remote Model Context Protocol (MCP) server (Public Preview) that exposes REST APIs as agent tools over HTTP (POST /mcp). Use when migrating OpenAPI 2.0 specs to OpenAPI 3.x for MCP, annotating specs with x-google-api-management.mcp and x-google-mcp-tool, securing tools/list with JWTs or API keys, connecting Google ADK (McpToolset) or Apigee API hub and Agent Registry, or troubleshooting MCP JSON-RPC errors (-32601, -32602, -32000). Do not use for Apigee X proxy bundles, outbound LLM model routing, or GKE Gateway API.OfficialEngineeringNo warnings★ 21.9K↓ —
- smbcrm-advanced-toolsLeoYeAI/agent-master-skillsUse when helping SMBcrm customers with Private Integration Tokens, REST API v2, workflows, custom webhooks, MCP, or Agent Studio API. Use for API troubleshooting, automation design, data sync, AI assistant setup, or any task involving https://services.smbcrm.com endpoints.DesignNo warnings★ 2.2K↓ —
- dokumente-intakeKlotzkette/claude-fuer-deutsches-rechtFür Dokumentenintake: ordnet Akte, Belege und Lücken; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Energierecht.OtherNo warnings★ 1.8K↓ —
- widerspruchKlotzkette/claude-fuer-deutsches-rechtFür Fahrgastrechte-Widerspruch — Skill: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 1.8K↓ —
- orchata-ragLeoYeAI/agent-master-skillsKnowledge management and RAG platform with tree-based document indexing. Use this skill to search, browse, and manage Orchata knowledge bases via MCP tools.OtherNo warnings★ 2.2K↓ —
- grok-aiLeoYeAI/agent-master-skillsHarness grok-ai capabilities inside ClawHub to dissect, annotate, and transform your video content with razor-sharp intelligence. This skill lets you query footage conversationally, extract timestamped insights, and apply context-aware edits driven by Grok's reasoning engine. Whether you're cutting highlight reels or analyzing recorded presentations, grok-ai handles the heavy lifting. Supports mp4, mov, avi, webm, and mkv formats.MediaNo warnings★ 2.2K↓ —
- pptx-postersK-Dense-AI/scientific-agent-skillsCreates and audits editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Used when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.DocumentsNo warnings★ 56.1K↓ —
differential-audit
pedrohcgs/claude-code-my-workflow
TestingUpdated Sep 27, 2026
From the author
Compare two implementations of the same thing — a port (R↔Python↔Stata), a reimplementation, a replication package, a refactor, or a new version against the old — so that agreement means something. Freeze inputs first, inventory every expected output, test the comparator itself, compare every channel (not just the headline number), and give each divergence a stable ID and a smallest witness. Use for cross-language parity, replication, upgrade/regression gates, or whenever "the numbers match" is about to license a claim.
Install
npx skills add pedrohcgs/claude-code-my-workflow --skill differential-audit -a claude-code
Installs to .claude/skills/differential-audit/ · 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 onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 89
Security100
Provenance79
Maintenance100
Licence100
Adoption52
Files (1)
- SKILL.md