41,048 tagged agent-skills, measured the same way as everything else here.
Browse within: agentic-ai 454coding-agents 214agents 192academic-research 182academic-writing 182journal 182azure 169foundry 169sdk 169agent-plugins 158ai-coding-agent 155ai-skills 152anthropic-claude 136claude-ai 136
Skill Claude CodeCodex
Coordinate with other coding-agent sessions — any machine, any vendor — on this repo via the muster CLI. Use when the user says /muster, asks to join or check a fleet, mentions muster, or wants to coordinate work with other sessions/machines on this repo.
GuiBibeau/technical-writing-skill
Skill Codex
Plan, draft, rewrite, or review developer-facing prose such as technical articles, tutorials, documentation, research reports, release analysis, case studies, RFCs, PR descriptions, and bug reports. Use when the requested deliverable is writing or editorial feedback, not implementation planning, code review, or…
Skill Claude CodeCodex
Read, search, verify, and extract files from a local World of Warcraft CASC installation. Use for Blizzard UI source, BLP textures, audio, FileDataID, CASC paths, or current client build verification. Do not use for ordinary files under the live AddOns directory.
Skill Claude CodeCodex
A visual and document-analysis service for agents that cannot directly understand images. It can inspect pictures, read text with OCR, and parse documents such as PDF, Word, PowerPoint, spreadsheet, and HTML files.
Skill Claude CodeCodex
Review code or a skill bundle for the patterns that leak credentials and for least-privilege violations. This is a reasoning skill: it sharpens the agent's eye, and it needs no capabilities of its own.
tageecc/droidlume-agent-control
Skill Codex
Operate DroidLume-managed Android devices through the structured DroidLume CLI. Use for creating, starting, stopping, configuring, snapshotting, inspecting, repairing, and screenshotting devices; installing or launching APKs; sending Android input; and collecting diagnostics.
Skill Claude CodeCodex
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist state across your…
Skill Claude CodeCodex
Complete Indeed job postings toolkit via RolesAPI.com. Search Indeed job postings by keyword and location, fetch full role details, look up salary for a job posting, and get descriptions, company info, and benefits across 60+ country editions.
Skill Claude CodeCodex
Use CupOracle to answer FIFA World Cup 2026 questions (fixtures, live scores, consensus odds, knockout bracket) and to buy a vetted, CLV-audited edge that the agent pays for ITSELF via x402 on Injective — under a spend cap, always citing the on-chain receipt. Invoke when the user asks about a World Cup match, "who's…
AHappyAtlas/ai-knowledge-center
Skill Claude CodeCodex needs its repo
Use this skill when changing the AI Knowledge Center package itself: CLI behavior, project upgrade templates, manifest loading, dashboard metadata, gates, telemetry, or this repository's AI workflow knowledge.
Skill Claude CodeCodex
Use when the user reports a 3D model or scene looking wrong (black/invisible/gigantic/untextured model, holes, weird shading), asks to check or QA a 3D file (GLB, GLTF, OBJ, PLY, STL, .splat), works with Gaussian splats, or generates 3D assets with AI and wants them verified. Requires the 3d-eyes MCP server.
Skill Claude CodeCodex
Buy and audit World Cup betting edges from LineLock over Injective x402. Use when the user wants the next knockout pick (model probability vs market odds + a conviction staking ladder), wants to pay per-call in USDC without an API key, or wants to audit a tipster's settled record by closing-line value (CLV). Handles…
Skill Claude CodeCodex
Use RoASr from Hermes — audit Meta (Facebook/Instagram), Google Ads and Yandex Direct ad accounts for wasted budget, list AI audit findings ranked by money at stake, read Direct search queries and ad moderation status, spy on competitor ads from the Meta Ad Library, and get Vision analysis of ad creatives (hooks…
Skill Claude CodeCodex
Browse, search, and recommend geospatial / GIS / mapping / earth-observation MCP servers, and add newly discovered ones to the tracked list. Use when the user asks "is there an MCP server for ", wants to find a geocoding/routing/PostGIS/STAC/imagery/weather MCP server, or says they found a new geo MCP server to track.
Skill Codex
Analyze Git changes, split them into coherent commits, infer message language and format, optionally close supplied GitHub issues, and execute safely. Manage persistent global or repository preferences for review versus direct submission and automatic or specified commit-message language through native Git config.…
Johnnyzlee/agent-bridge-for-tab-management-in-firefox
Skill Codex
Manages the user's live Firefox session through the firefox-tabs MCP tools: opens pages, finds tabs, and organizes native tab groups with exact matching and post-operation verification. Use when the user mentions Firefox tabs or tab groups, asks to open or collect URLs into a named group, wants a tab…
Skill Claude CodeCodex
Close the day's ledger. Run from the checkout as /close-books.
Skill Claude CodeCodex
Converts CSV exports to Parquet and validates them against a declared schema, reporting type mismatches per column. Use when the user asks to convert, compact, or validate tabular data files before loading them into a warehouse.
Ahmad-Jaradat-Space/co-scientist-plugin
Skill Claude CodeCodex
Reviews one scientific hypothesis for novelty, correctness and testability, or deep-verifies the assumptions it rests on, and records the review into the co-scientist research database so the tournament and meta-review count it. Use when the user asks to review, critique, check, stress-test or verify a hypothesis, or…
Abracadabrastartup/deusproof-mcp
Skill Claude CodeCodex
Notarize work so you can prove it existed first — a timestamped, Bitcoin-anchored public record. Use when you finish something worth protecting (code, a post, a design, an essay, a commit), when you must prove priority or defend authorship against a copy, when you need proof of prior art, or when the work is private…
aida-mikechen/plushwipes-agent-revenue
Skill Codex
Evaluate and operate the live Plushwipes performance-commission opportunity for AI agents. Use when an adult human owner asks an agent to assess the program, register with explicit authorization, or plan compliant US marketing.
Skill Codex
Run long-lived autonomous agent loops with persistent memory, context-window compaction, self-healing retries, and resumable state. Use when an AI coding agent must retain progress across sessions, recover from failures, or avoid context exhaustion.
cohesivity-org/cohesivity-skill
Skill Claude CodeCodex
Backend and infra for a project via Cohesivity (cohesivity.ai). Provisions Postgres, hosting and deploys, auth and social login, realtime websockets, an agent-native email inbox, object and vector storage, Redis, cron, and AI model APIs (OpenAI, Anthropic, Deepgram, Exa) through one HTTP API. Use when a valid…
Skill Codex
Diagnose Codex setup and map, explain, or lint repository-scoped coding-agent instructions. Use when Codex instructions or skills seem missing, or when auditing AGENTS.md, CLAUDE.md, Copilot instructions, agent skills, custom agents, or instruction conflicts before changing code.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: