Claude Code skills

49,516 tagged Claude Code, measured the same way as everything else here.

Browse within: agentic-ai 320antigravity 277agentic-skills 191ai-workflows 185coding-agents 165claude-code-skills 114agentic-framework 109agentic-workflow 109swarm 109Autonomous Agents 106agent-infrastructure 101claude-cli 100ci 97actions 96

rolfie-han/hanxiaoyu-visual-story-comic

Skill Claude CodeCodex

A skill for turning an authorized story, script, article, or outline into a coherent multi-page comic. It plans characters, scenes, props, page layouts, image prompts, and continuity checks.

not rated 5 +1 20d ago A 117 tokens original MIT

claude-hook-builder

3314

skills-lock/skil-lock

Skill Claude Code

Scaffold Claude Code hook configs by reading your existing settings and skills.

not rated 4 +1 5d ago A 19 tokens original Apache-2.0

anywrite

3315

Antheurus/anywrite

Skill Claude CodeCodex

Use this skill whenever the user mentions "anywrite" by name, or mentions Anytype, asks to create/update/search/organize notes, tasks, or PKM objects in Anytype, or wants to upload files, manage properties/tags/types, or chat inside an Anytype space. Covers all 52 endpoints of the Anytype local API (spaces, objects…

not rated 4 +1 1mo ago A 115 tokens original MIT

synorive

3316

Aevorine/Synorive

Skill Claude CodeCodex

A Chinese-language local search tool for finding content in your own documents, code, images, saved web pages, and video dialogue. It can also index new files and find similar content.

not rated 4 +1 2d ago A 111 tokens AGPL-3.0

vision

3317

visianlee/vision-mcp

Skill Claude CodeCodex

A vision bridge that sends images to supported visual-language services and returns text descriptions to a text-only model. It includes tools for image analysis, text extraction, image comparison, error screenshots, diagrams, and interface reviews.

not rated 4 +1 2mo ago A 80 tokens original MIT

dagx-agi-kernel

3318

dankofly/perfectify

Skill Claude CodeCodex

Improve and verify agent work after repeated failures, in dependency-heavy tasks, or when optimization claims need baseline and regression evidence. Use for DAGx/Perfectify requests, failed retries, risky multi-step work, or requests to verify an improvement. Exclude routine questions, drafting, one-step edits, and…

not rated 4 20d ago A 72 tokens original MIT

site-to-ios-app

3319

JasonColapietro/ios-app-dev-skills

Skill Codex needs its repo

Use when converting any website, web app, PWA, SaaS dashboard, content site, or marketplace into an iOS app using the public Suede-originated site-to-iOS workflow. Covers URL audit, App Store 4.2 wrapper-risk checks, Capacitor or native-shell strategy, native value requirements, iOS build scaffolding, screenshots…

not rated 5 +2 7d ago A 85 tokens original MIT

remarkable-memory

3320

mostafa-drz/claude-skills

Skill Claude Code

Turns handwritten reMarkable notes into a queryable semantic memory. Syncs pages from a reMarkable tablet (via the reMarkable MCP server, rmapi, or a USB/SSH bridge), renders each page to an image and reads the handwriting with Claude vision — no OCR key — then extracts each page into confidence-scored, human-editable…

not rated 4 changed 3d ago A 194 tokens original MIT

Swallow100/gpt-5.6-stop-overengineering

Skill Codex

Keep GPT-5.6 and other coding-agent work proportional to the request by locking scope, choosing the smallest sufficient implementation, matching verification to risk, and stopping when success is proven. Use for implementations, bug fixes, refactors, reviews, or maintenance where scope creep, speculative abstractions…

not rated 4 +1 1mo ago A 84 tokens original MIT

devagent

3322

FreePeak/devagent

Skill Claude CodeCodex

Dispatch implementation tickets through the DevAgent pipeline (worktree isolation, test gates, PR delivery) from any agent session.

not rated 4 changed 6d ago A 27 tokens original MIT

wechat-video-subtitle

3323

jianminggan/wechat-video-subtitle

Skill Claude CodeCodex

A tool for downloading WeChat video-channel videos and creating Markdown transcripts from them. WeChat is a messaging and media platform, and a transcript is a written version of spoken audio.

not rated 4 1mo ago A 112 tokens original MIT

context-auditor

3324

Abhillashjadhav/AI-PM-essential-skills

Skill Claude Code

Use this skill when a user wants to audit a CLAUDE.md, system prompt, agent context file, or any assembled context before running it in production. Triggers on phrases like "audit my context", "check my CLAUDE.md", "review my system prompt", "why is my agent behaving badly", "context issues", or when a user pastes a…

not rated 4 +2 13d ago A 132 tokens original MIT

scoville-brainstorm

3325

benjaminstelzer/scoville-brainstorm

Skill Codex

Use only to explore materially different solution mechanisms before a choice, with isolated generation, bounded prior-art comparison, calibrated originality language, and a decision-ready shortlist. Activate for explicit Scoville Brainstorm, or when a task explicitly requests several materially different solution…

not rated 4 changed 3d ago A 125 tokens original MIT

Hans-Vader/squadjs-plugin-creator-skill

Skill Claude CodeCodex

Use when creating, writing, or scaffolding a new SquadJS plugin, adding a server-side feature to a Squad server via SquadJS, or deciding whether SquadJS can support a desired behaviour ("can SquadJS detect X / do Y on a Squad server?"). Covers the plugin lifecycle, the full event/RCON capability surface, and the hard…

not rated 4 +1 11d ago A 83 tokens GPL-3.0

echo-guard

3328

Hansweek/echo-guard

Skill Codex

A finalization guide for deliverables after corrections, rejected proposals, or requests to remove or replace content.

not rated 4 19d ago A 105 tokens

throughline

3329

kitepon/Throughline

Skill Codex

Use when the user asks to use Throughline from Codex, continue or restore Throughline memory, export read-only handoff context for a local launcher, prepare a new Codex thread handoff, summarize a captured Codex session, or check whether the Throughline Codex Stop hook captured the current session. Hide long…

not rated 4 2d ago A 75 tokens original MIT

avvarre:reviewer

3330

PralhadYadawad/avvarre

Skill Codex

Perform a severity-first Avvarre code review and verify every requested fix.

not rated 4 18d ago A 22 tokens original MIT

sysadmin-performance

3331

HermeticOrmus/linux-sysadmin-skills

Skill Claude CodeCodex

Analyze and optimize performance on a Debian/Ubuntu Linux system by assessing CPU, memory, disk, network, and processes, finding the bottleneck, then applying targeted tuning with before-and-after measurement. Use when a machine is slow and you need to find why.

not rated 4 +1 3mo ago A 56 tokens original MIT

wayfinder

3332

gaia-research/gaia-skill-heaven

Skill Claude CodeCodex

Chart a too-big effort as a shared map of decision tickets on the Gaia headquarters issue tracker, then resolve them one at a time until the way to the destination is clear. Use when someone says: "this is too big for one session", "chart a map", "wayfinder map", "plan this effort", "what do we need to decide first"…

not rated 4 yesterday A 179 tokens

gws

3333

fmind/dot

Skill Claude CodeCodex

Automate Google Workspace with gws: schema-first calls, profile isolation, bounded reads, and verified Drive, Docs, Sheets, Gmail, Calendar, or Chat writes. Use for Workspace from the terminal.

not rated 4 changed 2d ago A 44 tokens original MIT

jazz-max/ruflo-hub

Skill Claude Code

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.

not rated 4 27d ago A 27 tokens

roadmap-build

3336

datacore-one/datacore

Skill Claude Code

Build or repair a roadmap that agents can actually execute, not just read. Produces a single validated YAML source of truth, generated views, definitions of done with evidence kinds, a task pool linked on two axes, an idea intake queue, and three standing checks that keep it honest. Use when asked to "build a…

not rated 4 today A 111 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: