81,896 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
A helper for the App Store's paperwork: ask Claude how your app is doing, whether it is ready, or to fix it. Takes a new app from bundle id and signing profile through builds, TestFlight, metadata, screenshots and in-app purchases to submit and release, and reads review status, reviews and sales. A local MCP server…
★not rated 2
changed yesterdayA
tokens not measured
originalMIT
Restart this Claude session inside the git repository it is working on, keeping the conversation. Use when a remote (crctl / screen) session was started outside its repo - e.g. in the home directory - so the Claude apps show no branch, diff or pull request for it; or when the user asks to restart this session, move…
Create or refresh backlog/docs/architecture.yml, the curated source of the project summary page (architecture diagram, flows, highlights, tech stack, commands). Use when the user asks for a project summary, an architecture overview or diagram, or after structural changes to the codebase.
Keeps brand definitions, several side by side, and turns one into a Claude Design System, DESIGN.md, VOICE.md or guide. Trigger to define a brand, palette, type or voice; turn a style guide or site into tokens; make, connect or sync a design system; audit for brand drift (off-palette colours, old names); pass or fail…
★not rated 2
changed 6d agoA
tokens not measured
originalApache-2.0
A notification cleaner for Stop messages from subscribed worktrees. It removes messages that are only waiting for background work to finish and leaves messages needing human input.
AI Chief of Staff runtime: 4-layer memory with hard limits, daily digest with drift detection, stakeholder trajectories, invisible shadow hypotheses, adversarial-default review, and a governance lint that fails the build on contradictions. State lives in your repo; the mechanism lives here.
★not rated 2 11d agoA
tokens not measured
originalMIT
Implement an already-approved plan end to end, autonomously, with verified work and a short final summary. Use for "plan-auto-work", "implement the plan", "go build it", "do it autonomously", or "run the plan end to end". Accepts a plan path and optional scope hint, or the plan most recently approved in the…
House standard for architecting modern web frontends — opinionated, type-safe, agent-first defaults for stack, data, state, styling, security, logging, i18n, and deploy.
★not rated 2
changed yesterdayA
tokens not measured
originalMIT
Design director for web and app interfaces. Use it FIRST, before other design skills, whenever the user wants to create, redesign, restyle, polish, fix, animate or review anything visual in a UI, even a small CSS tweak, and even without saying "design": landing pages, dashboards, app screens, "make it look better"…
Put your coding agents to work. Five Claude Code skills to ship improvements, orchestrate GitHub issues, build parallel PR stacks, open pull requests, and catch up on what shipped.
★not rated 2
changed todayA
tokens not measured
originalMIT
Write, schedule and publish posts to Instagram, TikTok, LinkedIn, X, Threads, Bluesky, Facebook, Pinterest and YouTube from a conversation, through your WoopSocial account. Includes skills for carousels, content calendars, bulk scheduling, cross-posting, fixing failed posts, social media audits and performance reports.
★not rated 2
changed 9d agoA
tokens not measured
originalMIT
Codebase knowledge graph with focused development workflow skills. Query architecture, dependencies, blast radius, and more instead of reading files one at a time.
★not rated 2 todayA
tokens not measured
originalMIT
A command-line tool that uses a Chrome browser already signed in to ChatGPT to create images and save them as local files. It supports prompts, reference images, styles, aspect ratios, and output locations.
Put the points a user has to decide on a decision board, a private claude.ai page where they answer each point and Claude replies on its card, round after round. Use when there are four or more points for the user, or a point likely to need more than one round; offer it in one line first. Needs the Artifact tools…
Marketing playbooks for a concrete task - copy, cold email, SEO and AI SEO, schema, ads, CRO, pricing, offers, launch, referrals, churn, customer research, competitor pages, social, PR, marketing plan. Use when the user asks for marketing work on a product or a client site.
A task-planning guide that turns requirements, product documents, technical specifications, issues, or implementation plans into clearly bounded, verifiable work items. It also defines priorities, dependencies, acceptance criteria, and ways to check the results.
Skills for planning, building, code review, auditing, maintenance, shipping, assistance, writing, Obsidian, and end-to-end workflows.
★not rated 2
changed 15d 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: