Five commands for GitHub skills in Cowork: load from any repo, save iterated versions, share installed skills, sync updates, and auto-detect pasted URLs.
★not rated 5 4mo agoA
tokens not measured
originalMIT
Transcribe a video and add translated subtitles in any language, burned into the picture or as a selectable track. Takes an X/Twitter, YouTube, or any yt-dlp URL, or a local file.
★not rated 5 1mo agoA
tokens not measured
originalMIT
A live, auto-refreshing per-session summary brief docked beside your Claude Code terminal — to quickly get up to speed when switching between parallel sessions.
★not rated 5 yesterdayA
tokens not measured
originalBSD-3-Clause
Security guardrails for AI-built apps: OWASP/API/LLM/MCP rules applied while building, an /audit skill for full reviews, and a hook that blocks secret commits.
★not rated 5 2mo agoA
tokens not measured
originalMIT
Composes Conventional Commits messages with gitmoji from the staged diff, deciding type, scope, emoji, subject, and body, and gating on protected branches, staged secrets, and pre-commit hooks.
★not rated 5 todayA
tokens not measured
originalMIT
Analytics skill pack for disciplined AI-assisted data analysis. Teaches AI to clarify questions, define metrics, separate observation from inference, and deliver decision-ready outputs.
★not rated 5 5mo agoA
tokens not measured
originalApache-2.0
Focused SEO skills: keyword research, on-page and technical audits, AI-search optimization, traffic diagnosis, site-health triage, competitor and content audits, and programmatic SEO, with content companions.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Language-agnostic autonomous codebase improvement loop using isolated git worktrees. Every experiment runs on its own branch — main is never touched until a winning change is merged. Works with any language or framework.
★not rated 5 6mo agoA
tokens not measured
originalMIT
Automatically compress large natural text or log files before processing using LLMLingua to save tokens. Trigger when the user pastes massive text blobs, asks to analyze a large file (logs, docs, transcripts), or provides a prompt too large for the context window.
★not rated 5 4mo agoC
tokens not measured
originalMIT
Adaptive, hands-on learning for unfamiliar technology. Define one outcome, diagnose the next prerequisite, guide and validate attempts without completing the learning target, verify load-bearing claims, and optionally preserve progress.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Agentic organic growth for any website: analytics-driven signals, keyword intelligence, AI-citation tracking, gated on-page execution on WordPress, and a learning loop that compounds in a per-site git repo. An optional configuration form appears when you enable the plugin; setup reads it so nothing is asked twice.
★not rated 5
changed 2d agoA
tokens not measured
originalMIT
A writing and readability tool for Korean and other languages. It includes separate skills and scanners for checking whether a document sounds naturally written.
★not rated 5 17d agoA
tokens not measured
originalMIT
Autonomous judge agents fix your app's debt, build what's missing, and verify every change through a browser or gate suite before it lands, then find the next thing and keep going until you say stop. Each fixer owns a file-disjoint slice of the tree, so no two can ever collide, and nothing unverified reaches git. A…
★not rated 5 1mo agoA
tokens not measured
originalApache-2.0
Stay active while coding. Injects fitness breaks into your Claude Code sessions — micro-challenges between prompts and scaled workouts during long-running tasks. All workout data stays on your machine, exportable to CSV or JSON.
★not rated 5
changed 5d agoA
tokens not measured
originalMIT
Asks the questions an architect would ask: problem clarification, decision guidance, and failure analysis, recorded as plain markdown in your repo. Derived from Microsoft's Clarity Agent.
★not rated 5 3mo agoA
tokens not measured
originalMIT
A comprehensive accessibility-first development environment for Claude Code with WCAG 2.1 AA compliance, Playwright testing, and proactive accessibility guidance.