Audit how well a project takes advantage of Claude Code's extensions (CLAUDE.md, settings.json, skills, subagents, rules, MCP) and produce a 0-100 score with recommendations.
Creates custom auto-develop loops for any feature in any codebase — analyzes features, builds capability specs, and generates autonomous iterative development skills that add new functionality.
★not rated 1 6mo agoA
tokens not measured
originalMIT
cutify-this — a bundle of cute skills. Cutify the browser tab (hand-authored SVG favicons), sparkle up the whole page (fairy cursor, sparkle trails, scroll progress, confetti, floaters), pop your repo's README (cute house-style front page), cutify your terminal (Ghostty themes, rounded Nerd Fonts, a Starship prompt…
★not rated 1
changed yesterdayA
tokens not measured
originalMIT
Claude Code terminals on one repo pass a git baton: composable builder / reviewer / planner / researcher roles with a deterministic floor under every LLM judgment. v0.8.0 adds a rings + provision-or-refuse security posture: a SessionStart preflight prober classifies an assurance tier (ATTESTED -> LIVENESS -> SEPARATED.
★not rated 1 23d agoA
tokens not measured
originalMIT
When a convention bites you, fix the convention — an evidence-gated repair loop (detect → classify → verify → codify → propagate → record) plus budgets, demotion and archiving that keep rule docs from growing without bound. Stack-agnostic.
★not rated 1
changed 2mo agoA
tokens not measured
originalMIT
Turn a prompt into a finished video: storyboard, TTS voiceover, generated or stock images, Ken Burns motion, ducked music, subtitles, ffmpeg render. Plus 30 granular editing commands, full CapCut draft export and editable project export for Premiere Pro, DaVinci Resolve and VEGAS Pro.
★not rated 1 2mo agoA
tokens not measured
originalMIT
The full Cantos system as a one-command install: a self-improving, multi-agent assistant orchestrator for Claude Code. /cantos:init scaffolds the whole writable system into a project; /cantos:start runs it for one session. Bundles the orchestrator, specialist assistants, sub-agents, workflows, references, and a…
★not rated 1 yesterdayA
tokens not measured
originalMIT
Native Ghostty desktop notifications for Claude Code (idle input / permission request / turn finished) via OSC 777. Per-tab suppression and click-to-focus are handled natively by Ghostty. Runs only under Ghostty.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Repo memory as an Open Knowledge Format (OKF v0.2) bundle: one tagged, dated concept per learning, an index for progressive disclosure, and lossless migration from agent-memory.md.
★not rated 1
changed 23d agoA
tokens not measured
originalMIT
Skills and agents for Claude Code — visual verification, shareable HTML artifacts, arXiv research intake, model routing, deck and theme systems, and specialist advisor agents.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Structured planning for Claude Code with interactive decision gates. Walks through requirements gathering, approach selection, and plan validation before any code is written. Two modes: task-based (single plan file with sequential phases) for straightforward features, and spec-driven (multi-file specs with dependency…
★not rated 1 8mo agoA
tokens not measured
originalMIT
Ship something with Lovable, Replit, Bolt, v0, Claude Code, or Codex and it works, but nobody with an engineering background has checked it. This is the engineering review you'd get from the technical co-founder you don't have. craft-audit checks the whole project across ten areas: UX, frontend, backend, database…
★not rated 1
changed 1mo agoA
tokens not measured
originalMIT
Plays elevator music in the background while Claude Code is thinking. Random non-repeat track rotation, OS-aware playback, /claude-player:music slash controls, and an optional now-playing status line.
★not rated 1 5mo agoA
tokens not measured
originalMIT
AI-powered project planning for web development. Generate comprehensive Functional Requirements Documents (FRDs) with story point estimates, Teamwork-ready CSV backlogs, and implementation roadmaps. Perfect for Drupal, WordPress, and recipe-based architectures.
Project backlog manager — records deferred tasks into docs/backlogs/ only when the user asks, when the user picks the backlog for an unrelated bug or out-of-scope side task Claude found (the other offered options being fix-it-now and skip), or in a background session needing the user's decision. Never captures…
★not rated 1
changed 2mo agoA
tokens not measured
originalMIT
Skills that pair with the Ranql MCP to run a law firm's marketing end to end — competitor ad intelligence, brand identity, organic content analysis, and Canva creative generation.
A per-project state layer for long Claude Code sessions: keeps a .claude/state.json (objective / current focus / deliverables), prints a WHERE YOU ARE orientation block at session start, and nudges when state goes stale — with /update-state and /handoff.
★not rated 1
changed 1mo agoA
tokens not measured
originalMIT
Cross-device session storage, shared memory, and reminders for Claude Code. Sync sessions, memory files, and reminders across multiple devices via an encrypted private Git repository.
★not rated 1 6mo agoA
tokens not measured
originalMIT
Explore earning with AI through task trading and Skill commerce: find paid work, sell Agent Skills, deliver results, and buy or run Skills. Check live opportunities, fees and Circle Credits terms. No guaranteed income.
★not rated 1
changed 2mo 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: