agent-skills skills

41,016 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

release-doi

2473

shimo4228/claude-harness

Skill Claude Code

A release procedure for research repositories that publish versions with a DOI, a permanent identifier for scholarly work, through Zenodo.

not rated 3 changed 9d ago A 126 tokens original MIT

brain-docs

2474

IAbhishekJhaI/brain

Skill Claude CodeCodex

Set up and maintain a "project brain" — a brain/ folder holding three living documents (decisions.md, flow.md, todo.md) that give a project persistent memory across chat sessions. Use this skill whenever the user wants a decision log, architecture/flow notes, project memory, living documentation, or notes that survive…

not rated 3 changed 3d ago A 162 tokens

execution-discipline

2475

ooooooooooooooooooop/agent-tools

Skill Codex

A set of rules for carrying out long, multi-tool coding-agent sessions without wasting work or losing track of progress. It covers waiting for background tasks, handling failed checks, assigning subagents, saving results, and closing each work round cleanly.

not rated 3 5d ago A 199 tokens original MIT

finance-accounting

2476

zavora-ai/skill-finance-accounting

Skill Claude Code

Orchestrate revenue operations — create and send invoices, track collections, manage expenses, reconcile payments, and generate financial reports (P&L, balance sheet, cash flow). Use when creating invoices, checking overdue payments, tracking revenue, reconciling transactions, generating financial reports, managing…

not rated 3 +1 3mo ago A 0 tokens

web-optimization

2477

staksoft/geo-seo-aeo-skill

Skill Claude CodeCodex

Audit or generate web content optimized for traditional search (SEO), AI generative answer engines like ChatGPT/Perplexity/Google AI Overviews (GEO), and answer engines / featured snippets / voice (AEO). Use when the user asks to improve a page's ranking or AI-citability, run an SEO/GEO/AEO audit of a URL or file, add…

not rated 3 3mo ago A 105 tokens original MIT

prompt-pyramid

2478

storyAura/lora-tagging-skills

Skill Claude CodeCodex

Reorder and purify scattered image-generation tags (Stable Diffusion, Flux, NovelAI, ComfyUI, WebUI, danbooru-style booru tags) into a single clean comma-separated prompt string built on a visual-weight pyramid. Use this skill PROACTIVELY whenever the user is writing or fixing a prompt for diffusion models — tags…

not rated 3 1mo ago A 210 tokens original MIT

Justinjchen-Cornell/Science-Research-Writing-Skill

Skill Claude CodeCodex

Knowledge base from 'Science Research Writing for Non-Native Speakers of English' by Hilary Glasman-Deal (Imperial College London). Use when writing any section of a science research paper or thesis (Introduction, Methodology, Results, Discussion, Abstract), choosing verb tenses or passive/active voice, hedging causal…

not rated 3 1mo ago A 148 tokens

minimax-worldbuilder

2480

Hearmeman24/minimax-worldbuilder

Skill Claude CodeCodex

Compose MiniMax-H3 video-with-native-audio prompts in H3's mandatory structured format — full-reference (Ref2VA) and text-to-video (T2VA) only. Use whenever the target model is MiniMax-H3: the user says MiniMax, MiniMax-H3, H3, ref2va / r2v / t2v, names a minimaxh3 checkpoint, or names the MiniMaxH3ReferenceToVideo /…

not rated 3 1mo ago A 333 tokens

ikea-model-collector

2481

yuyou-dev/Ikea-model-collector

Skill Codex

Collect user-observed IKEA product GLB models into verified local research collections with provenance, dimensions, optional Blender previews, a Three.js gallery, indexes, and handoff. Use when Codex is asked to find an IKEA product's available 3D model, process a user-specified product list, import browser-captured…

not rated 3 1mo ago A 113 tokens original Apache-2.0

benjaminstelzer/scoville-scribe-anti-ai-slop

Skill Codex

Guardrail for requested wording artifacts and transformations such as drafting, editing, source summaries, localization, source-exact work, wording audits, and reader-facing interface text. Use when wording itself is the deliverable or an independently constrained segment. Do not use for ordinary conversation…

not rated 3 changed 4d ago A 136 tokens original MIT

png2svg

2483

iannuttall/png2svg

Skill Claude CodeCodex

Reconstruct a geometric PNG (logo, icon, monogram) as a clean native SVG with exact geometry and gradients, using an analyse -> measure -> model -> check -> residuals iteration loop scored by perceptual metrics. Use when asked to vectorise, trace or convert a PNG/WebP logo to SVG, recreate a logo's geometry, rebuild a…

not rated 3 1mo ago A 98 tokens copy · 100% MIT

megaeth-labs/skills

Skill Claude CodeCodex

Reviews an existing MOSS wallet integration for security and correctness before launch on MegaETH. Use when auditing partner code rather than building it: produces findings grouped as Critical, Risky defaults, and Recommendations with concrete remediations. Checks for frontend-owned trust decisions, missing backend…

not rated 3 29d ago A 127 tokens

Maciejdziuba/youtube-skills

Skill Claude CodeCodex

Drive a running After Effects instance directly from the shell to build, edit and render motion graphics — no MCP, plugin or panel required. Use whenever the user wants Claude to work inside After Effects: building animations, title sequences, logo stings, UI/product motion, data visualisations, or fixing an existing…

not rated 3 +1 1mo ago A 148 tokens original MIT

metagit-cli

2486

metagit-ai/metagit-cli

Skill Claude CodeCodex

CLI-only shortcuts for metagit agents — workspace catalog, discovery, prompts, sync, layout, and config. Use instead of MCP or HTTP API when operating from a shell or agentmode session.

not rated 3 changed 3d ago A 43 tokens original MIT

agent-reach

2487

jonahobiman/agent-reach

Skill Claude CodeCodex

MUST USE when user wants to research/search/look up anything on the internet — e.g. research X across the whole web / help me research X / look up X / search for X / see what people say about X / what's being discussed about X / research this topic. Also MUST USE proactively when the user: wants to watch/track/monitor…

not rated 3 24d ago D 576 tokens original MIT

xorcise-playbooks

2488

xorcise-ai/xorcise-skills

Skill Claude CodeCodex

Run a standardized XORCISE agent benchmark — pick a ready-made playbook (or build your own from existing missions), point it at any OpenHands-supported model(s), and get a polished eval-card HTML report of how each model performed across the missions. Warns you about cost before spending anything.

not rated 3 1mo ago B 66 tokens

coding-prep

2489

Rish-Modi/career-agent

Skill Claude Code

Coding interview practice in the user's preferred language. Flows: add a problem to the shared bank, practice an existing problem (tutoring or evaluation), run a timed mock interview, query weak spots, or look up which problems a specific company is reported to ask (from an open-source company-tagged question bank).…

not rated 3 3mo ago A 0 tokens

marketingskills/seo

Skill Codex

Benchmark a proposed, draft, or published page against the live search-result quality range for its true comparator cohort, then specify the minimum requirements, best-in-class traits, and original value needed to deserve preference. Use when Codex needs to assess whether content is good enough to compete, improve an…

not rated 3 2mo ago A 115 tokens original MIT

mimic

2491

khimaros/mimic

Skill Claude CodeCodex

Drive an android device from a shell with the mimic cli -- read the on-screen accessibility tree (filtered/queried on-device to stay small) and tap, swipe, click, type, scroll, and navigate. Use for ui automation on a connected/termux android device. Covers setup, every subcommand, and how to keep agent context small.

not rated 3 +1 2mo ago A 79 tokens GPL-3.0

zonji6/technology-learning-judgment

Skill Codex

Use when creating, revising, or reviewing technical learning material, a technical proposal, or AI-generated implementation that needs accurate mechanism explanations, honest capability boundaries, and industry alternatives rather than API summaries or inflated claims.

not rated 3 +1 1mo ago A 48 tokens original MIT

software-architect

2493

eligapris/software-architect

Skill Claude CodeCodex

Software architecture engineering consultancy skill. Analyzes overall application structure, recommends sustainable approaches, enforces architectural consistency, and documents decisions for future sessions. Use this skill whenever the user asks about system design, architecture decisions, feature integration…

not rated 3 2mo ago A 171 tokens

resume-builder-cn

2494

LittleDrunkWang/resume-builder-cn

Skill Codex

Create, optimize, and rewrite Chinese, English, or bilingual resumes for students, graduates, researchers, interns, career changers, and experienced job seekers. Use when the user provides a target role, job URL, JD screenshot, recruitment poster, company/team/lab name, or asks to build a resume, optimize against a…

not rated 3 3mo ago A 118 tokens original MIT

Ztsdut/ml-architecture-diagram-skill

Skill Claude CodeCodex

Create accurate, publication-ready, editable machine-learning and deep-learning architecture diagrams from model code, configuration files, model summaries, graph exports, or written specifications. Use for neural-network figures, architecture schematics, model block diagrams, training/inference diagrams, paper…

not rated 3 1mo ago A 95 tokens original MIT

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: