Keep long Claude Code sessions coherent by rolling old conversation into a single, constantly-updated summary so the context window stops overflowing and the assistant stops giving degraded or off-topic answers. Use this skill whenever a coding or development session has been running long, whenever the conversation…
Analyze the fonts in fonts/ and set up this repo for proofing. Runs the containerized fontTools introspection, writes a human-readable font summary into CLAUDE.md (and machine-precise data into fontinfo.json), then interviews the user about the proof they want — page size, orientation, colors, header/footer, margins…
After a batch of 2+ user-facing UI changes, produce a before/after verification report to sign off each change while reviewing locally. Invoke on request ('before/after report', 'verification table', 'screenshot diff') or proactively when a finished change set touches ≥2 distinct UI surfaces/behaviors. Captures…
Reveal consequential blind spots after answering. Use proactively for exploration, research, product thinking, architecture, planning, creative work, and decisions, or when the user asks what they missed, what to ask next, or to challenge an idea. Skip routine execution unless a hidden issue could materially change…
Shopware 6 development across plugins, apps and themes: DAL entities, migrations, custom fields and entity extensions, Storefront (Twig, SCSS, JS plugin system), Admin (Vue 3, Meteor Admin SDK), Admin API and Store API, cart processors, collectors and validators, payment and shipping handlers, rule builder conditions…
Render a proposed UI change or set of design concepts as real HTML in the project's own design system, serve it locally, and loop on the operator's clicked decisions and inline annotations until they approve. The visual alternative to describing UI in a wall of terminal text or a markdown plan. Use when the operator…
AGENTS.md scaffolder for context engineering. One-shot generator of a durable, agent-agnostic context tree for any repo: an AGENTS.md router plus a context/ directory split into 5 narrative modules (architecture, design-patterns, glossary, operations, debugging) with append-only L3 data files (.jsonl + .yaml).…
Find a Verified Ticket Triage Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for customer-support agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
Structured thinking skill implementing Bloom's AI Collaboration Framework v3. Auto-scales depth from stakes (reversibility + reliance): quick 3-question framing for reversible exploration, standard 6-question protocol for real decisions, deep mode with epistemics + teach-back + independent audit for binding one-way…
Find a Verified Analytics Reporting Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for data agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
Find a Verified Resume Screening Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for hr agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).
Calculate Indian income tax, capital gains tax (STCG/LTCG), advance tax, and TDS for FY 2025-26 under old and new regimes; includes live ITR e-filing portal verification via Playwright-over-CDP.
Visual helper for react-joyride in any React + Vite repo. /joyride-studio init scaffolds an in-browser capture inspector, the tour runtime, and a vite plugin. /joyride-studio start enables authoring so developers click real elements in the running app to define tour targets. /joyride-studio turns captures into a wired…
A Chinese-language guide for authorized penetration testing and security research. Penetration testing is controlled testing used to find security weaknesses in software or systems.
Turn a song or album idea into release-ready Suno material: a precise Style prompt, fully structured lyrics with metatags, a title, and the iteration plan to refine it. Use this skill whenever the user wants to make music with Suno (or Suno AI / Suno V5 / V5.5), write song lyrics intended for AI music generation…
End-to-end guide for ANY Indian real estate decision by a general audience with little prior knowledge — buying a first home, renting, buying for rental income, plots/land, NRI purchases, upgrading, selling, or inherited property. Drives the conversation, asks the right questions, verifies before valuing (RERA…
Generates a Toyota-style A3 problem-solving report from a problem statement. Use this skill when the user mentions A3 reports, root cause analysis, 5-Whys, fishbone diagrams, Ishikawa, lean problem solving, DMAIC, manufacturing issues, quality escapes, production downtime, scrap reduction, yield problems, or asks to…
Audits AI coding-agent context. Measures always-on context-window cost of CLAUDE.md, AGENTS.md and Agent Skills, and reports skills that will not load, stale path references, redundant instructions and duplicate skill names. Use when the user asks to audit, measure or reduce context cost, check whether a skill is…
A UX strategy and diagnosis guide for planning how a product should work and how users move through it. UX means the user’s experience of using a product; the guide produces strategy documents rather than visual mock-ups or HTML.
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Query the personal LightRAG knowledge graph for persistent memory across sessions.
★not rated 2 6mo agoA16 tokens
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: