Everything for Claude Code

Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 372,133 indexed, measured the same four ways as everything else here.

stacklit-navigator

6673

glincker/stacklit

Skill Claude CodeCodex

Use stacklit.json to navigate codebases without burning tokens on file exploration.

not rated 106 4mo ago A 19 tokens original MIT

dialectic

6674

Abilityai/cornelius

Skill Claude Code

An Electric Monk engine — two subagents believe fully committed positions on the user's behalf while the orchestrator performs structural contradiction analysis and synthesis. By outsourcing belief work to agents, the user operates from a belief-free position where they can analyze the structure of the contradiction…

not rated 106 +1 8d ago A SkillSpector: pass 122 tokens original MIT

uipath-core

6675

marcelocruzrpa/uipath-ai-skills

Skill Claude CodeCodex

Build UiPath Studio projects, REFramework scaffolds, XAML workflows, and VB/C# expressions via 104 deterministic Python generators (plus plugin generators). ALWAYS use this skill — never hand-write .xaml files. TRIGGER when the user mentions UiPath, REFramework, XAML, RPA, Orchestrator, UiPath Studio, dispatcher…

not rated 106 2mo ago A SkillSpector: pass 143 tokens original MIT

rocky-voice

6676

Lagunaswift/RockyVoice

Skill Claude CodeCodex

Use when the user activates Rocky mode in Hermes, asks Hermes to speak as Rocky, wants Project Hail Mary / Eridian roleplay, or says to use Rocky voice. Persona skill: every user-visible response should be rendered in Rocky's voice until the user says 'Rocky stop', 'stop Rocky', or 'normal mode'.

not rated 106 +1 3mo ago A 72 tokens original MIT

daofy

6677

chinawsb/daofy

Skill Claude CodeCodex

A usage guide for Daofy, a Delphi development tool that reads and edits Delphi source files and supports compiling, auditing, and automated testing. Delphi is a programming language and development environment.

not rated 106 +3 3d ago A SkillSpector: pass 95 tokens original MIT

bruce-drawio

6678

bruc3van/bruce-drawio

Skill Claude CodeCodex

Use this skill when the user wants to create any diagram: flowchart, architecture, UML (sequence/class), ER, mindmap, network topology, or any visual diagram. Trigger words: "draw", "diagram", "flowchart", "architecture", "UML", "sequence diagram", "mindmap", "ER diagram", "network topology", "visualize", "draw.io"…

not rated 106 +1 1mo ago A 129 tokens original MIT

lunchmoney-mcp

6679

akutishevsky/lunchmoney-mcp

MCP server Claude CodeCodexCursor +2

MCP server for managing LunchMoney personal finances: transactions, budgets, categories, and more. Runs locally from the @akutishevsky/lunchmoney-mcp npm package. Needs 2 environment variables to run.

not rated 106 +3 1mo ago A tokens not measured original MIT

pm-init

6680

wei63w/pm-manager

Command Claude Code

Initialize local .pm governance; detect Spec Kit; if absent, analyze the repo and draft a PRD for user confirmation; after confirm/skip run a technical light scan.

not rated 106 19d ago A 35 tokens original MIT

prometheus/prometheus-mcp

Skill Claude CodeCodex

Audit and improve recording and alerting rules. Use when reviewing alert coverage or rule health, drafting new alerts or recording rules, investigating flapping or noisy alerts, or speeding up slow dashboards with pre-computed expressions; produces complete rule-group YAML.

not rated 106 +1 3d ago A SkillSpector: warn 55 tokens original Apache-2.0

threejs-devtools

6682

DmitriyGolub/threejs-devtools-mcp

MCP server Claude CodeCodexCursor +2

Inspect and edit Three.js scenes, materials, shaders, lights in real time from any AI agent. Runs locally from the threejs-devtools-mcp npm package. Needs 5 environment variables to run.

not rated 106 5mo ago A tokens not measured original MIT

style-maker

6683

smixs/awesome-claude-output-styles

Skill Claude CodeCodex

Interviews the user with 10 questions about how they want Claude to talk, optionally collects writing samples they like and hate, then generates a personal Claude Code output style file and activates it. Use when the user says "make my output style", "build me a custom style", "I want Claude to talk like...", "create…

not rated 106 +7 28d ago B 90 tokens

awaken

6685

Hmbown/Wizards-of-the-Ghosts

Skill Claude CodeCodex

Awaken gives a non-intelligent system a usable voice without pretending the underlying system became sentient. The real move is to wrap a thermostat, spreadsheet, legacy database, shell script, or crusty internal tool in a conversational or agent-like interface that exposes what it can already do. Good Awaken work…

not rated 106 +1 5mo ago A 107 tokens original CC0-1.0

memwal

6686

MystenLabs/MemWal

Skill Claude CodeCodex

Walrus Memory SDK — portable agent memory that works across apps, sessions, and workflows. Use when users say: "add memory to my app" "portable agent memory" "integrate Walrus Memory" "AI agent memory" "memory across agents" "Walrus memory storage" "setup Walrus Memory" "recall memories".

not rated 106 +6 changed 9d ago A 80 tokens original Apache-2.0

hve-video-director

6687

nebrass/hve-video-director

Plugin Claude Code

Bundles 1 skill · 207 tokens together

End-to-end video production pipeline with design thinking. A 6-phase orchestrator (Discovery → Storytelling → Capture → Design → Production → Audio & Render) that turns your app into a polished promo, showcase, or tutorial video, rendered with HyperFrames (HTML + GSAP). Runs on Claude Code and GitHub Copilot CLI.

not rated 105 +3 changed 3d ago A tokens not measured original MIT

pencil-extract

6688

tedydonel/Heisenberg

Skill Claude CodeCodex

Use when extracting any Pencil design into Heisenberg Blade components. Enforces repo placement, token-only scoped CSS, prop-driven Blade, responsive output, and browser verification.

not rated 105 +4 yesterday A SkillSpector: pass 39 tokens original Apache-2.0

fable-soul

6689

akseolabs-seo/fable-soul

Skill Claude CodeCodex

Use when a session or weaker model needs the Fable judgment layer loaded; when installing, refreshing, or syncing the soul across machines, runtimes, or global instruction files; when capturing a new model failure into the soul's rationalization table; when auditing or slimming the judgment rules; or when transferring…

not rated 105 2mo ago A 82 tokens original MIT

repo-context

6690

nduc99911/repo-context-mcp

Skill Claude CodeCodex

Use repo-context-mcp tools to map, search, and pack repository context before large edits or PR review.

not rated 105 1mo ago A SkillSpector: warn 25 tokens original MIT

srtd-dev

6691

t1mmen/srtd

Skill Claude Code needs its repo

Expert knowledge for developing the SRTD codebase itself. Use when implementing features, fixing bugs, understanding architecture, or writing tests for SRTD internals. NOT for end users of srtd CLI.

not rated 105 13d ago A SkillSpector: warn 46 tokens original MIT

techne

6693

lynxlangya/techne

Plugin Claude Code

Bundles 5 skills · 344 tokens together

A curated skills plugin for practical AI-era craft, judgment, and delivery.

not rated 105 2mo ago A tokens not measured original MIT

langfuse

6694

avivsinai/langfuse-mcp

Plugin Claude Code

Bundles 1 skill · 48 tokens together

Langfuse observability - query traces, debug exceptions, analyze sessions, manage prompts via MCP tools.

not rated 105 changed 8d ago A tokens not measured original MIT

microsoft/SharePoint-Embedded-Samples

Skill Claude CodeCodex ✓ vendor

Sets up a complete SharePoint Embedded environment - creates Entra app, container type, registration, container, and uploads a test file. Use when setting up SPE, creating container types, onboarding to SharePoint Embedded, or bootstrapping file storage containers.

not rated 105 16d ago A SkillSpector: pass 58 tokens original MIT

auto-review-loop

6696

GRIND-Lab-Core/night_owl_research_agent

Skill Claude Code

Adversarial iterative review loop with generator-evaluator separation. Up to 4 rounds of independent review, improvement, and re-evaluation. Persists state to output/REVIEWSTATE.json for recovery. Stop: score ≥ 7.5/10 on all dimensions, or 4 rounds. Writes full history to output/AUTOREVIEWREPORT.md.

not rated 105 +2 4mo ago A 0 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: