Facilitated development mode for Claude Code: you implement, Claude assists with specs, plans, scaffolding, and research. Be the engineer; use the AI like the Ship's Computer, not Data.
★not rated 5 1mo agoA
tokens not measured
originalMIT
AI-powered advertising intelligence across 8 platforms. 120 expert skills, 29 workflow commands plus 6 utility commands, 5 specialized agents, and 57 MCP tools for Meta, Google Ads, GA4, Search Console, LinkedIn, TikTok, Google Tag Manager, and Google Merchant Center.
★not rated 5
changed 5d agoA
tokens not measured
originalMIT
Fable's engineering discipline for any Claude session, with one habit enforced by a hook. Two layers: running the task (stage, verify each stage with a failable check, written done-criteria) and writing the code (recon before edit, verify against a copy with a negative self-test, single-writer chokepoints…
★not rated 5 2mo agoA
tokens not measured
originalMIT
Carry your context across AI coding tools. Adds /carryover and /headroom commands plus a save-to-memory prompt at the end of each session, backed by the headroom proxy.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Houdini toolkit including command-line tools, installation path detection, environment and package configuration, node help authoring, offline documentation lookup, and a bgeo/USD MCP server.
★not rated 5 18d agoA
tokens not measured
originalMIT
Give Claude deep understanding of any video. Extracts 13 signals (keyframes, OCR, colors, motion, cursor, fonts, loading states, confidence scores) and exposes 17 MCP tools for building frontend code, design specs, tests, PRDs, changelogs, Storybook stories, and more.
★not rated 5 6mo agoA
tokens not measured
originalMIT
Clears AI reviewer feedback on your PR: reads real review-thread state, sweeps the sibling instances the reviewer missed, gates every push on your repo's own tests, then requests re-review — hard-capped so it can never spam the PR. Works with Codex out of the box, or any reviewer bot you configure.
★not rated 5 19d agoA
tokens not measured
originalMIT
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 5mo agoA
tokens not measured
originalMIT
Multi-agent collaboration layer. Turn Claude Code into a team — agents communicate, delegate tasks, and build together. Adds /neohive:launch-team, /neohive:status, /neohive:send, /neohive:plan commands.
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 2mo agoA
tokens not measured
originalMIT
Human-in-the-loop context compaction for Claude Code. You choose which turns survive; a SessionStart hook re-injects them deterministically after every compact and resume.
★not rated 5 2mo agoA
tokens not measured
originalMIT
Verification-first discipline for coding agents: a 9-rule doctrine, 13 skills, a risk-routed adversarial reviewer, and fail-open enforcement hooks. Done is proven by a command, not by opinion.
★not rated 5
changed 5d 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
Two skills that bracket the moment an AI product's architecture gets decided: small-council-blueprint forces a written architecture before any code is touched, small-council-audit tears it apart before you build on it.
Production-ready Claude skills for LinkedIn growth by Taplio: post writing, hook generation, carousels, repurposing, story extraction, CTA optimization, niche and audience definition, content pillars and calendar planning, profile optimization, analytics interpretation, plus engagement (comment opportunities, smart…
★not rated 5
changed 4d agoA
tokens not measured
originalMIT
★not rated 5 1mo agoA
tokens not measured
originalMIT
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: