Everything for Claude Code

Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 390,180 indexed, measured the same four ways as everything else here.

aozyildirim/Agena

Skill Claude CodeCodex

A declarative routing engine that turns ticket / error attributes (reporter, label, project, area path, error class, environment) into a tag + AI agent + priority assignment, so cross-source workflows ("security tickets always go to the OWASP reviewer") stay out of code and in user-editable rules.

not rated 103 1mo ago A SkillSpector: pass 67 tokens original MIT

ZJLi2013/awesome-kernel-skills

Skill Claude CodeCodex

Orchestrates continuous kernel optimization by chaining profiling, bottleneck diagnosis, tier-based optimization, verification, and benchmarking into an iterative loop. This is the "main program" that drives the other skills. Use when you want to iteratively optimize a kernel until it meets a performance target…

not rated 103 +1 7mo ago A 70 tokens

evaluate

7323

WingedGuardian/GENesis-AGI

Skill Claude Code

Evaluate technologies and competitive developments against Genesis architecture.

not rated 103 +4 changed yesterday A SkillSpector: pass 10 tokens original MIT

wiki-self-heal

7324

NulightJens/ai-second-brain-skills

Skill Claude CodeCodex

Autonomously audit an LLM wiki (Karpathy pattern) for gaps, contradictions, orphans, and stale data, then research and fill high-priority gaps using quality-gated web research. Supports audit-only dry-run mode. Operates on a dedicated branch and commits changes for human review — never auto-merges. Use when the user…

not rated 103 7mo ago A 142 tokens original MIT

getvect

7326

craigjmidwinter/getvect

Skill Claude CodeCodex

Convert a raster image (PNG, JPEG, BMP) into a vector file (SVG, EPS, DXF, PDF) locally, with no network call and no account. Use when you have generated or been given a bitmap and need clean editable paths — a logo to scale, line art to cut, a diagram to embed at any size. Do not use for photographs you want to keep…

not rated 103 14d ago A 92 tokens original MIT

ingest

7327

johnfkoo951/cmds-llm-wiki

Command Claude Code

Ingest a source (URL/file/text) into Raw Sources + compile 1015 Wiki pages, with mandatory user-purpose gate and mothership cross-linking.

not rated 103 +2 changed 1mo ago A 33 tokens

claude-md-improver

7328

mrclrchtr/supi

Skill Claude Code needs its repo

Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.

not rated 103 +1 yesterday A SkillSpector: warn 39 tokens original MIT

t-tools

7329

timzaak/web-dev-skills

Plugin Claude Code

Bundles 33 skills, 40 agents · 3,499 tokens together

DDD-driven development skills, sub-agents and workflow commands for Rust, React, miniapp, Flutter, Chrome Extension, and Shopify App projects.

not rated 103 changed 26d ago A tokens not measured original Apache-2.0

shopify-hydrogen

7330

Shopify/agent-skills

Skill Claude CodeCodex ✓ vendor

Edit src/data/raw-api-instructions/{api}.md in shopify-dev-tools, then run: npm run generateagentskills (outputs to distributed-agent-skills/) -->.

not rated 103 +2 4mo ago C 0 tokens

blog-content-auditor

7331

microsoft/cat-agent-skills

Skill Claude CodeCodex ✓ vendor

Use this skill when the user asks to audit, review, score, rationalise, prioritise, refresh, or improve blog posts, article libraries, newsletters, or thought-leadership content.

not rated 103 +7 3d ago A SkillSpector: pass 45 tokens original MIT

context7

7332

indecenti/NucleoOs

MCP server Claude CodeCodexCursor +2

MCP server "context7" as configured in indecenti/NucleoOs. Launched with cmd /c npx -y @upstash/context7-mcp.

not rated 103 +6 yesterday A tokens not measured

curator-continuity

7333

talirezun/the-curator

Skill Claude Code

Apply at the start of a build or coding session on a Curator-tracked project, and again as your own context fills, without waiting to be asked. Activates on "continue", "resume", "where did we leave off", "pick up where we left off", "what were we working on", "catch me up on this project", and on the save side "save…

not rated 103 +1 changed 1mo ago A 228 tokens

yujie

7335

dontbesilent2025/claude-skills

Skill Claude CodeCodex

A text-based virtual pet that responds in the Dongbei dialect of northeastern China. It uses a terminal-style interface and interactive commands.

not rated 103 7mo ago A 75 tokens

google-labs-code/jules-skills

Skill Claude Code

Set up a repository for local GitHub Actions verification using act, so Jules can validate CI before pushing.

not rated 103 +2 5mo ago B Socket: warnSnyk: pass 25 tokens original Apache-2.0

textweb

7337

chrisrobison/textweb

MCP server Claude CodeCodexCursor +2

A text-grid web renderer for AI agents — see the web without screenshots. Runs locally from the textweb npm package.

not rated 103 8mo ago A tokens not measured original MIT

tidewave

7338

ash-project/ash_typescript

MCP server Claude CodeCodexCursor +2

MCP server "tidewave", hosted remotely at localhost, as configured in ash-project/ashtypescript.

not rated 103 3d ago A tokens not measured

zcode-usage-sync

7339

techysy/10router

Skill Claude CodeCodex

A data export tool that copies ZCode's local record of model usage into 10Router, a service that tracks usage statistics.

not rated 103 +7 changed 1mo ago A SkillSpector: warn 186 tokens original MIT

obsidian-sync

7341

fanchenggang/Davflare

Skill Claude CodeCodex

Set up and verify free Obsidian sync (Remotely Save plugin → Davflare WebDAV). Use when a user asks to sync an Obsidian vault to their Davflare drive.

not rated 103 +1 15d ago A 43 tokens original MIT

wolfram-debugging

7342

WolframResearch/AgentTools

Skill Claude CodeCodex

Verified recipes and tested helpers for debugging Wolfram Language code. Use whenever code issues messages, returns $Failed, Failure or unevaluated calls, gives wrong results, is slow, hangs or crashes, or works in one environment but not another; for stack traces, call logs, profiles, mocks or overrides, watchpoints…

not rated 103 +3 yesterday A 115 tokens original MIT

skill-build

7343

runxhq/runx

Skill Claude CodeCodex

Canonical Runx skill-authoring implementation. Use for designing, creating, updating, improving, or adding harness coverage to a Runx skill package; it combines bounded agent judgment with native file writes, inspection, and safe harness validation. When a host skill-creator also triggers, use its general guidance but…

not rated 103 +2 changed 4d ago A 71 tokens original Apache-2.0

start-module

7344

virastack/start

Skill Claude Code

Builds or changes a ViraStack Start ready module (installed with npx virastack add ) end to end, from the registry source in this repository to its page on virastack.com (/start/features/ ), whose sections are a live preview with a Code tab and a copyable prompt, Modülde neler var and Nasıl kullanırsın. Use when…

not rated 103 changed 5d ago A 103 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: