Everything for Claude Code

Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 386,116 indexed, measured the same four ways as everything else here.

polish-manuscripts

8377

timholy/claude_config

Skill Claude Code

Structural and editorial review of a whole manuscript, followed by a tracked series of editing sessions: survey the text, publish a checklist page where the author decides on each item, agree on cross-cutting rules, then carry out the accepted items one fresh-context session at a time.

not rated 76 +1 changed 2d ago A 61 tokens

mindmap-markmap-viewer

8378

Jaderson-bit/mindmap-markmap-viewer

Plugin Claude Code

Bundles 1 skill · 120 tokens together

Turn Markdown outlines, notes, docs, or plans into an interactive mind map — a single self-contained HTML file that opens offline anywhere (markmap.js, white-on-dark, zoom/expand/export toolbar, context-preserving search).

not rated 75 5mo ago A tokens not measured original MIT

dependency-auditor

8379

UseAI-pro/openclaw-skills-security

Skill Claude CodeCodex

Audit npm, pip, and Go dependencies that OpenClaw skills try to install. Checks for known vulnerabilities, typosquatting, and malicious packages.

not rated 74 +1 8mo ago A Socket: passSnyk: pass 36 tokens original MIT

design-taste

8380

somnus0x/agt-skill-pack

Skill Claude CodeCodex

Pattern-recognition design review: judge whether an interface works before any analysis. Use for UI and design reviews, visual hierarchy checks, and 'does this look right' calls.

not rated 74 1mo ago A 39 tokens original Apache-2.0

release

8381

corezoid/corezoid-ai-plugin

Skill Claude Code

A release workflow for the corezoid-ai-plugin project that prepares a new tagged software version through six defined phases.

not rated 74 changed 18d ago A SkillSpector: warn 184 tokens original MIT

anything-to-md

8382

1596941391qq/ai-openclaw-skeletons

Skill Claude CodeCodex

Universal document to Markdown converter. Convert any file (PDF, Word, Excel, PPT, images, audio, video, YouTube URLs) to clean LLM-ready Markdown. Use when: User wants to convert documents to Markdown User needs to process entire directories of files User has YouTube videos or audio files to transcribe User wants to…

not rated 74 5mo ago A 265 tokens original MIT

memcord

8383

ukkit/memcord

Skill Claude CodeCodex

Privacy-first, self-hosted chat memory for OpenClaw — save and recall conversation history across sessions without any cloud dependency.

not rated 74 3mo ago A 28 tokens original MIT

drupal-htmx

8384

edutrul/drupal-ai

Skill Claude Code

HTMX in Drupal 11.3+ core — the Htmx PHP fluent builder, dynamic forms with swapOob, partial routes with htmxroute, response headers, and Drupal.behaviors integration. Use when building interactive UI without full-page reloads using Drupal's native HTMX support.

not rated 74 5mo ago A 67 tokens original MIT

create-skill

8385

ArchieIndian/openclaw-superpowers

Skill Claude CodeCodex

Scaffolds and validates new superpowers skills. Use when creating a new skill for this repository.

not rated 74 +1 6mo ago A 24 tokens

forkprobe

8387

Jayden-X-L/forkprobe

Skill Claude CodeCodex

Recommend a small set of candidate skills or artifact-generation pipelines for an open-ended task, then compare their outputs so the user can decide what actually helps. Use when the user is unsure if a particular skill would improve their output, when comparing 2+ skills for the same task, when they naturally ask to…

not rated 74 2mo ago A 226 tokens original MIT

deep-interview

8388

tranhieutt/software_development_department

Skill Claude Code

Conducts a structured technical deep-dive to gather detailed requirements, constraints, and decisions from the user. Use when starting a complex feature or when the user wants to be asked structured clarifying questions before implementation.

not rated 74 5mo ago A 46 tokens original MIT

red-pen

8389

richtabor/agent-skills

Skill Claude CodeCodex

A strict editorial reviewer that checks writing principles inspired by George Orwell's "Politics and the English Language" rules and Matthew Butterick's Practical Typography. Use this skill whenever the user says "red pen", "check my prose", "edit this for clarity", "typography check", "tighten this up", "review this…

not rated 74 7mo ago A 147 tokens

nuke-on-rails

8390

nuke-on-rails/nuke-on-rails

Skill Claude Code

Full health and security audit for Rails apps, the review a principal engineer would do. Runs rubycritic, Brakeman, bundler-audit and rubyaudit, triages every finding with the LLM as judge, brings an OWASP Top 10 arsenal of checks for what scanners miss, and returns one impact-ranked action plan. Use for a Rails…

not rated 74 4mo ago A 105 tokens original MIT

Self-Review

8391

dot-agents/dot-agents

Skill Claude CodeCodex

Review your own changes before committing or creating a pull request.

not rated 74 10mo ago A 15 tokens original MIT

speak

8392

blacktop/mcp-tts

Skill Claude CodeCodex

Speaks a short digest through the mcp-tts MCP server whenever the user would otherwise have to be watching the screen to know something happened. Select it while composing the reply in two cases: you are writing a summary at a stopping point (a substantial task finished, a plan is ready, a long…

not rated 74 changed 7d ago A SkillSpector: warn 144 tokens original MIT

opendesign

8393

qiuyiwu1989-star/opendesign

Skill Claude CodeCodex

Be a design director, grounded in OpenDesign (opendesign.cc) — a curated library of 1,400+ real, machine-readable design systems, each with an 11-layer token spec extracted from the live site and verified against actual computed styles. Use whenever someone wants to design or build a website, landing page, dashboard…

not rated 74 2mo ago A 184 tokens

wandb-primary

8394

wandb/skills

Skill Claude CodeCodex

Primary W&B skill for broad or mixed Weights & Biases work: project overviews, W&B runs and artifacts, Weave traces and evaluations, Reports, Workspaces, Automations, Sweeps, Launch, and Agent Lens. Use when the task spans multiple W&B surfaces or the user asks generally what is happening in a W&B project.

not rated 74 changed 29d ago A Socket: warnSnyk: passSkillSpector: pass 75 tokens original Apache-2.0

my-novel

8395

xiaofeng-928/chinese-longnovel-skill

Skill Claude CodeCodex

A workflow for managing long Chinese web novels across planning, writing, continuation, review, and correction tasks. It first locates the correct novel project, then loads only the reference documents and templates needed for the requested task.

not rated 75 changed 1mo ago A 39 tokens original MIT

ctxo-understand

8396

alperhankendi/Ctxo

Skill Claude CodeCodex

Use at the START of any code task (fix, extend, refactor, understand), and whenever you need the right ctxo tool for a structural question, to orient with ctxo instead of going in the wrong direction.

not rated 74 changed 18d ago A SkillSpector: pass 50 tokens original MIT

hardware-io

8398

beriberikix/zephyr-agent-skills

Skill Claude CodeCodex

Hardware interfacing and peripheral management for Zephyr RTOS. Covers the sensor subsystem (channels, triggers, fetch/get), pin control (Pinctrl) and multiplexing, GPIO management using Devicetree specs, and SoC-level hardware configurations. Trigger when adding new hardware components, configuring pinmux, or…

not rated 74 5mo ago A 72 tokens original Apache-2.0

matrix-signup

8399

oguzbilgic/kern-ai

Skill Claude CodeCodex

Register yourself on a Matrix homeserver and wire the credentials into .kern/.env.

not rated 74 +1 yesterday A 20 tokens

cordys-crm

8400

1Panel-dev/CordysCRM-skills

Agent Claude Code

Cordys CRM L2C full-pipeline AI assistant with role awareness, supporting lead-to-cash tracking, funnel analysis, approval management, and intelligent workflow guidance across 5 roles.

not rated 74 +3 19d ago A 41 tokens

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: