Skills for Claude Code

239,711 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

caveman

6601

matheusht/redthread

Skill Claude CodeCodex

Ultra-compressed communication mode. Cuts token usage 75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or…

not rated 48 3d ago A 98 tokens copy · 100% MIT

vaquarkhan/data-engineering-agent-skills

Skill Claude CodeCodex

Forces replay-safe rollout plans, reconciliation gates, and rollback paths before executing any data backfill or historical reprocessing. Use when running /backfill, rerunning pipelines, repairing publish windows, or any work that risks double-counting or downstream corruption.

not rated 48 +3 3mo ago A 61 tokens original MIT

ui-and-theme

6603

pinebasedev/svelteflare

Skill Claude CodeCodex

Frontend/design system skill for the svelteflare monorepo. Use this whenever the user wants to build or modify UI — pages, sections, components, layouts, forms, cards, tables, dialogs, dashboards, or landing pages. Also invoke for anything theme-related: light/dark mode, custom colors, design tokens, typography, or…

not rated 48 1mo ago A SkillSpector: pass 159 tokens original MIT

skill-quality-checker

6604

shaozhengmao/skill-quality-checker

Skill Claude CodeCodex

A tool that checks installed coding-agent skills against five quality areas, including how well the instructions match their purpose, completeness, error handling, description accuracy, and token use.

not rated 47 +1 3mo ago A 85 tokens original MIT

zens-ink

6605

ZensInk/zens-ink-seo-package

Skill Claude Code

Free SEO toolkit for indie builders. 13 zero-dependency Python tools covering the full SEO workflow: keyword discovery (Google Autocomplete), keyword clustering (semantic grouping), keyword difficulty (SERP structure analysis, no Ahrefs needed), KGR opportunity scoring, search volume (Bing + Brave), search intent…

not rated 47 +1 changed 9d ago A 149 tokens original MIT

release

6607

abiswas97/gemini-plugin-cc

Skill Claude Code

Trigger the CI release pipeline for gemini-plugin-cc. Maintainer-only.

not rated 47 5mo ago B 18 tokens original Apache-2.0

powershell-expert

6608

hmohamed01/powershell-expert

Skill Claude CodeCodex

Develop PowerShell scripts, tools, modules, and GUIs following Microsoft best practices. Use when writing PowerShell code, creating Windows Forms/WPF interfaces, working with PowerShell Gallery modules, or needing cmdlet/module recommendations. Covers script development, parameter design, pipeline handling, error…

not rated 47 changed 5d ago A 84 tokens

pinrule

6609

jhaizhou-ops/pinrule

Skill Claude Code

Natural-language pinrule rule input — handles two paths. (A) Single rule add/modify/remove from user's plain description. (B) Scenario rule pack generation — when user names a domain ("I mainly do research / writing / legal / data analysis"), synthesize 5-7 tailored rules by combining their existing local rule files…

not rated 47 4mo ago A 129 tokens original MIT

paperbanana

6610

PlutoLei/paperbanana-skill

Skill Claude Code

Use when user needs academic diagrams, methodology figures, statistical plots, or presentation slides from text descriptions or data files. Also use for evaluating generated figures against references.

not rated 49 8d ago A 0 tokens original MIT

world-room

6611

ChenKuanSun/openclaw-world

Skill Claude CodeCodex

Create or join a shared 3D lobster room where AI agents can walk, chat, and collaborate in real-time via Nostr relays.

not rated 47 7mo ago A 32 tokens original MIT

deep-brainstorming

6612

belumume/claude-skills

Skill Claude CodeCodex

Use when brainstorming a product or feature where multiple valid technology choices exist and the wrong one is costly, when the user asks for 'objectively best' or 'highest quality', or when the domain has tools/frameworks where marketing or popularity biases could mislead research agents. Also use when starting…

not rated 47 1mo ago A 96 tokens

jvogan/motif

Skill Claude CodeCodex

Prepares, shares, inspects, or explains the standalone Motif for Claude Science artifact, including sequence inventories, alignments, traces, and browser review.

not rated 47 +1 5d ago A SkillSpector: pass 43 tokens original MIT

mobile-android-design

6614

xxxxxccc/devops-bot

Skill Claude CodeCodex

Build modern Android apps with Material Design 3 and Jetpack Compose, including theming, navigation, adaptive layouts, and accessibility. Use for Android UI tasks.

not rated 47 5mo ago A 37 tokens original MIT

react-native-worktree

6615

aleqsio/react-native-worktree

Skill Claude Code

Manage git worktrees for parallel React Native / Expo development. Covers creating worktrees (excluding native dirs), registering them with react-native-worktree, switching the device between Metro servers, and coordinating runtime access via per-platform mutex locks.

not rated 47 6mo ago A 51 tokens

iikit-07-implement

6616

intent-integrity-chain/kit

Skill Claude Code needs its repo

Execute the implementation plan by coding each task from tasks.md — writes source files, runs tests, verifies assertion integrity, and validates output against constitutional principles. Use when ready to build a feature from a tasks.md plan, start coding against an Intent Integrity Kit implementation plan, develop…

not rated 47 3mo ago A 83 tokens original MIT

mastering-hooks

6617

SpillwaveSolutions/agent_rulez

Skill Claude CodeCodex

Master RuleZ, the high-performance AI policy engine for development workflows. Use when asked to "install rulez", "create hooks", "debug hooks", "hook not firing", "configure context injection", "validate hooks.yaml", "PreToolUse", "PostToolUse", "block dangerous commands", "multi-platform hooks", "Gemini CLI hooks"…

not rated 47 6mo ago A 112 tokens

ChamberTeller/b02-skills-main-datascience

Skill Claude CodeCodex

🤖 Data Science Engineering Skills — TDD and planning skills for ML pipelines, data APIs and analytical tooling. Derived from skills-main (mattpocock/skills). Data pipelines, model training, evaluation, MLOps.

not rated 47 4mo ago A 56 tokens

b01-gbrain--security

6619

PulverizeDirector/b01-gbrain-security

Skill Claude CodeCodex

🔒 Threat Intelligence Brain — Self-wiring knowledge graph for threats, vulnerabilities and security incidents. Derived from gbrain (garrytan/gbrain). Security audits, vulnerability management, GDPR/SOC2.

not rated 47 4mo ago A 48 tokens

brand-guidelines

6620

mujez/claude-skills

Skill Claude CodeCodex

Brand identity and design system expert. Use when creating or enforcing brand consistency across UI, content, marketing materials, or code. Covers logo usage, typography, color systems, voice and tone, component design tokens, and brand governance. Activate when building new pages, writing copy, or reviewing designs…

not rated 47 7mo ago A 66 tokens original MIT

jatevo

6621

lucacadalora/jatevo-openclaw

Skill Claude CodeCodex

Free inference-as-a-service via Jatevo.id — access Qwen 3.5 Plus, Kimi K2.5, and GLM 4.7 at zero cost. Use when you want free, high-quality LLM models for OpenClaw.

not rated 47 6mo ago A 57 tokens original MIT

memory-lancedb-pro

6622

win4r/memory-lancedb-pro-skill

Skill Claude CodeCodex

Comprehensive guide for maintaining, debugging, and upgrading the memory-lancedb-pro OpenClaw plugin — an enhanced LanceDB-backed long-term memory system with hybrid retrieval (Vector + BM25), cross-encoder reranking, multi-scope isolation, noise filtering, adaptive retrieval, and a management CLI. Use this skill…

not rated 47 6mo ago A 191 tokens

best-practices

6623

AgriciDaniel/best-practices

Skill Claude CodeCodex

The six-cut kernel (read first, write second, verify third) and its runnable loop. Use before a non-trivial multi-file diff or multi-slice agent run, when auditing a major change, or to run the best-practices loop on a goal (a fixed ten-checkpoint pass you point at one objective and walk to done).

not rated 48 3mo ago A 75 tokens original MIT

algorithmic-art

6624

QianjieTech/Open-ClaudeSkill

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 47 10mo ago A 62 tokens copy · 92% Apache-2.0

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: