41,013 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
ryanelian/crucible-agent-skill
Skill Claude Code
Autonomous, loop-until-clean diff refinement engine. Iteratively burns down feature and refactor diffs by deleting dead code, flattening empty abstractions, and enforcing strict layer boundaries (Sink & Lift). Every change is verified against tests. Use when asked to "crucible", "refine until clean", "burn down diff"…
Skill Claude CodeCodex
Nimbuu UI/UX Skill. Logic-driven interface design distilled from Refactoring UI, Practical UI, and Fundamentals of Creating a Great UI/UX. Three uses. (1) ALWAYS when starting a new project, greenfield app, landing page, or prototype with no design system, no tokens, no brand kit, so spacing, type, colour, hierarchy…
Skill Claude CodeCodex
This skill makes the agent completely useless. It doesn't help. It gives confidently wrong short answers and blames the user.
Skill Claude Code
12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns…
Skill Claude CodeCodex
Use taste as a competitive moat and business advantage. In the AI and vibe-coding era, execution is commoditized. Taste is the defensible edge. Use when advising founders on product differentiation, building product culture, evaluating why some products win despite fewer features, or understanding taste as a strategic…
PranitMohnot/repo-learner-suite
Skill Claude CodeCodex needs its repo
Generate Jupyter notebook exercises from a codebase analysis. Reads the manifest at learn/internals/exercise-plan.md, scaffolds notebooks (or short inline blocks where the manifest says so), runs MANDATORY mock-student + nbconvert validation, then inserts links into learn/curriculum.md at the step markers the analyzer…
Skill Claude CodeCodex
Run a decision through 5 independent AI advisors (Contrarian, First Principles, Expansionist, Outsider, Executor) that peer-review anonymously and synthesize a verdict. Trigger on 'council this', 'pressure-test this', 'war room this', or any high-stakes either/or choice. Skip for factual lookups, summaries, or simple…
JadeYingWah/gpt-5-6-sol-reasoning-style
Skill Codex
Use when another model with weaker reasoning is asked to plan, review, or implement non-trivial work and needs GPT-5.6 Sol-like rigor instead of jumping to implementation.
Shimonimposed141/powerpoint-skill
Skill Claude Code
Create visually rich PowerPoint (.pptx) presentations from academic papers, research notes, or any content the user wants in slide format. Uses PptxGenJS + LaTeX formula rendering. Always use this skill when the user wants PPT/PPTX output instead of Beamer/LaTeX slides. Trigger on: powerpoint, pptx, PPT, make a ppt…
Skill Claude CodeCodex
Generate AI music tracks via the Lacuna Music API. Use when the user wants AI-generated music, BGM, jingles, soundtrack stingers, lofi/synthwave/orchestral/any-genre tracks, vocal songs from custom lyrics, or any on-demand audio generation. Triggers on phrases like "generate music", "make me a track", "compose a…
atomchung/long-run-hybrid-coach
Skill Codex
Maintain one current 28-day running-and-strength direction from the latest available Garmin or Intervals.icu evidence. Use when the user asks to reassess a goal or plan, create or revise a hybrid week, decide what to do today, review planned versus actual training, or preview and deliver a selected workout. Trigger…
Skill Claude CodeCodex
Use when testing or running an app while a VPN/proxy tunnel is up and the app's own outbound calls must leave via the real ISP connection instead of the tunnel - geo-locked or domestic APIs, payment/SMS gateways, bank endpoints, or any service that rejects the VPN's exit IP. Gives the app under test a LAN-direct…
k-vaca/prompt-engineering-skill
Skill Claude CodeCodex
Write, review, and optimize professional prompts for large language models. Use this skill whenever the user asks to write, draft, design, improve, fix, debug, review, or optimize a prompt, system prompt, prompt template, meta-prompt, or agent instructions; asks why a prompt "isn't working" or gives inconsistent…
pencil20388-eng/browser-automation-skills
Skill Claude CodeCodex
Connect Google's Chrome DevTools MCP to AdsPower antidetect browser profiles. This lets AI coding agents (Claude Code, Cursor, Codex CLI) control fingerprint-isolated browser sessions through natural language.
Skill Claude CodeCodex
Research any industry or market to find underserved niches, unmet customer needs, and untapped opportunities. Analyzes competitor blind spots, customer complaints, emerging trends, and geographic gaps to surface specific business opportunities most people miss. No API keys or paid tools required — works with web…
Laic-parsiism709/meshy-3d-agent
Skill Claude Code
Generate 3D models, textures, images, rig characters, and animate them using the Meshy AI API. Handles API key detection, setup, and all generation workflows via direct HTTP calls. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, or interact with the…
Skill Claude CodeCodex
Security review of LLM applications and agents. Use when asked to review, red-team, threat-model or test an LLM feature, chatbot, RAG pipeline, MCP server or autonomous agent for prompt injection (direct or indirect), jailbreaks, system prompt or secret leakage, tool abuse, excessive agency, confused-deputy behavior…
bird-chinese-community/BIRD.skills
Skill Codex
Install or migrate BIRD 2/3 editor support and @birdcc/cli. Use for the BIRD2 LSP VS Code extension, the separate TextMate syntax extension or extension pack, VS Code forks, BIRD.nvim, BIRD.vim, manual Neovim LSP wiring, JetBrains TextMate bundles, birdcc CLI installation, offline VSIX setup, or migrations from…
The-Artificer-of-Ciphers-LLC/skills-from-the-artificer
Skill Claude CodeCodex
Test-driven bug fixing — reproduce before you fix. Use this skill whenever the user reports a bug, describes unexpected behavior, says something is broken, mentions a regression, or asks you to fix an error. This includes phrases like "this is broken", "X doesn't work", "there's a bug in", "getting an error when", "it…
Skill Claude CodeCodex
This skill should be used when the user asks to evaluate, sharpen, red-team, or pressure-test a business idea, offer, market choice, product, or strategic move using Roger Martin and A.G. Lafley's Playing to Win choice cascade. Triggers on phrases including "Playing to Win", "P2W", "where to play", "how to win"…
thirdwatch-dev/scraping-skills
Skill Claude CodeCodex
Use when a site blocks your scraper and you need to get past it — 403 Forbidden on the first request, JS challenges, CAPTCHAs, Cloudflare Turnstile, DataDome, Akamai, PerimeterX, "Just a moment...", access denied, IP bans, or an empty/skeleton page where data should be. Covers diagnosing transient failures vs real…
Skill Claude CodeCodex
Inspect a project's data for correctness and produce a read-only validation report — record counts, NULL rates, value distribution, uniqueness, referential integrity, format validity, and sampled evidence rows. Data is read only from the project's own test fixtures/seed data or from an explicitly configured…
Skill Claude CodeCodex
A skill for using the local ClawHeart command-line tool to audit AI security, evaluate skills, and manage agent credentials.
Skill Claude CodeCodex
Pull a Figma design via the Figma connector and produce a developer handoff - tokens, specs, redlines, asset list, and component notes. Use when handing a design to engineering or auditing a Figma file.
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: