Claude Code skills

48,779 tagged Claude Code, measured the same way as everything else here.

Browse within: agentic-ai 314antigravity 277agentic-skills 189ai-workflows 183coding-agents 160claude-code-skills 115agentic-framework 108agentic-workflow 108swarm 108Autonomous Agents 105agent-infrastructure 101claude-cli 100ci 97skills 97

agent-builder

385

FareedKhan-dev/claude-code-from-scratch

Skill Claude CodeCodex

Use when building a new agent harness, designing tool systems, or structuring multi-agent workflows. Provides patterns, templates, and decision trees for harness engineering.

not rated 293 +1 5mo ago A 34 tokens original MIT

browser-use

386

SirAllap/agentglass

Skill Claude CodeCodex

Drive agentglass's built-in browser — the one already signed in to the sites this project uses. Use when a task needs a page behind a login (a dashboard, a ticket, a staging app), when a URL fetched with curl comes back signed out or JavaScript-rendered, or when the user asks you to look at, click through, or…

not rated 292 +3 changed yesterday A 0 tokens original

auto-research

387

kbanc85/claudia

Skill Claude CodeCodex

Iteratively improve a local artifact (draft, document, page) by running a hill-climbing loop. The user names the artifact, the evaluator, and the budget. Claudia edits the artifact, scores it, keeps it if better or reverts if worse, repeats. Use when user says "iterate on this", "loop on this until it's better", "run…

not rated 290 2d ago A 115 tokens

ai-game-art-pipeline

388

ybuild-ai/ai-game-art-pipeline-skill

Skill Claude CodeCodex

Provider-neutral open-source skill for planning and producing game-runtime art assets and animation: static props/icons, canonical character sheets, combat sprites, 3D/video motion references, Veo/Seedance-style video-to-frames, cinematic ultimates, backgrounds, FX, SFX, runtime packaging, and QA. Use when building…

not rated 290 +2 2mo ago A 96 tokens original MIT

Intelligent-Internet/zenith

Skill Claude CodeCodex

Domain playbook for optimization missions — any task whose goal is to move a metric: performance, latency, throughput, memory, cost, score, quality, compression, ranking, solver, model/eval, and similar metric-improvement work. Defines how to think about and run an optimization mission: establishing the ground truth…

not rated 290 +7 1mo ago A 118 tokens original Apache-2.0

claudemap-runtime

390

QuinnAho/claudemap

Skill Claude Code

Internal ClaudeMap runtime for turning a repository into a live architecture map and driving that map during walkthroughs. Prefer the public commands in .claude/commands for normal use.

not rated 289 +2 4mo ago A 40 tokens original MIT

beamer-academic

391

Faust-Donf/beamer-academic

Skill Claude CodeCodex

Generate high-quality academic Beamer slides from a thesis/paper (PDF, Word, or LaTeX source). Compatible with Claude Code and Codex. Supports thesis defense, proposal presentations, and conference talks. Built-in layout library with 13 professional page types, 5 color schemes, and interactive editing loop. Use when…

not rated 289 +5 21d ago B 148 tokens original MIT

Moore-developers/moore-wechat-article-downloader

Skill Claude CodeCodex

A tool for downloading public WeChat Official Account articles and collecting article histories. WeChat Official Accounts are Chinese publisher or business pages, and the tool supports login, account selection, and scheduled syncing when required.

not rated 288 1mo ago A 76 tokens original MIT

agent-army

393

OneWave-AI/claude-skills

Skill Claude Code

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku…

not rated 287 +5 27d ago A 142 tokens original MIT

email-marketing-bible

394

CosmoBlk/email-marketing-bible

Skill Claude CodeCodex

Data-backed email marketing skill for AI agents. Use when building or running email automation, driving an ESP from an agent (MCP/connectors), diagnosing deliverability, writing or de-slopping email copy, designing emails, choosing a platform, or pulling benchmarks. Covers AI email automation, flows, deliverability…

not rated 286 +3 2mo ago A 93 tokens original MIT

algorithmic-art

395

shuyu-labs/WebCode

Skill Claude CodeCodex

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…

not rated 284 2mo ago A 62 tokens

nicepkg/ai-workflow

Skill Claude Code

This skill generates professional LinkedIn announcement text for intelligent textbooks by analyzing book metrics, chapter content, and learning resources to create engaging posts with key statistics, hashtags, and links to the published site. Use this skill when you need to create social media announcements about…

not rated 282 +1 7mo ago A 62 tokens original MIT

preview-design

397

egregore-labs/egregore

Skill Claude Code

Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…

not rated 282 +2 3d ago A 71 tokens original MIT

PlamenTSV/plamen

Skill Claude CodeCodex

L1 trigger - detects non-determinism, state transition completeness violations, and safety/liveness invariant breaks in consensus code. Inject into depth-consensus-invariant or depth-state-trace.

not rated 281 1mo ago A 45 tokens original MIT

virtengine/bosun

Skill Claude CodeCodex

Use this plugin when the task involves native Windows desktop apps or browser surfaces that do not have a stronger structured integration available.

not rated 280 +1 3mo ago A 0 tokens original Apache-2.0

exam-study-guide

400

ZeKaiNie/universal-examprep-skill

Skill Claude CodeCodex needs its repo

A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.

not rated 280 +3 5d ago A 113 tokens original MIT

xiaohu-ip-studio

401

xiaohuailabs/xiaohu-ip-studio

Skill Claude CodeCodex

A Chinese-language illustration workflow that turns an article’s key idea into a metaphorical image featuring a recurring original character.

not rated 280 +3 2mo ago A 159 tokens original MIT

unsloth-buddy

402

TYH-labs/unsloth-buddy

Skill Claude CodeCodex

This skill should be used when users want to fine-tune language models or perform reinforcement learning (SFT, DPO, GRPO, ORPO, KTO, SimPO) using the highly optimized Unsloth library. Covers environment setup, LoRA patching, VRAM optimization, vision/multimodal fine-tuning, TTS, embedding training, and…

not rated 277 2mo ago C 123 tokens original MIT

git-commit-convention

403

7-e1even/learn-agent

Skill Claude CodeCodex

A guide for writing Git commit messages using Conventional Commits, a shared format that labels changes such as features, fixes, tests, documentation, and maintenance.

not rated 277 +2 yesterday A 32 tokens original MIT

github

404

AIOSAI/AIPass

Skill Claude Code

GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries.

not rated 273 yesterday A 23 tokens original MIT

threads

405

majiayu000/spellbook

Skill Codex

A workflow guide for coordinating several coding agents on a broad task. It defines separate work lanes, file ownership, review gates, and checks that the work is complete.

not rated 272 +7 2d ago A 75 tokens original MIT

predict

406

akseolabs-seo/AK-Threads-booster

Skill Claude Code

Estimate likely 24-hour post performance from the user's historical data. Use after the user writes a post and wants a range estimate, upside view, or expectation check.

not rated 271 +1 2mo ago A 35 tokens original MIT

rag-evaluate-quality

407

lyonzin/knowledge-rag

Skill Claude CodeCodex

Periodically measure the retrieval quality of the knowledge base using evaluateretrieval (MRR@5, Recall@5, Precision@5) plus getindexstats for health metrics. Run weekly, after significant reindex activity, or when the user reports declining answer quality. Prevents silent index rot and grounds "should we tune X"…

not rated 271 +4 3d ago A 78 tokens original MIT

define-jumbo-goals

408

jumbocontext/cli

Skill Claude CodeCodex

Add Jumbo goals liberally to decompose objectives into finite units of work with bounded context. Use when defining new Jumbo goals from user requests, or to augment your own work to maintain scope while ensuring complementary work is registered.

not rated 270 +1 11d ago A 50 tokens AGPL-3.0

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: