Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 391,074 indexed, measured the same four ways as everything else here.
Author RPG Maker MZ games from Claude Code: 113 MCP tools for maps, tile painting, events, database editing, and validation, plus the authoring-judgment skills that make the output actually playable.
Memex spec-checkout — binds your coding thread to a Spec and records in-flow edits against it (claim-gated, privacy-first). Non-blocking, opt-in, uninstallable any time. Sends only changed file paths + the claimed spec; never source code or prompts. Hooks-only: the Memex MCP is planted by npx memex-ai install (spec-4.
A reporting assistant that turns scattered work notes, meeting records, and chat messages into structured daily, weekly, or monthly reports. It groups work by results, progress, routine tasks, risks, and learning.
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for…
Work a Markdown knowledge base — an Obsidian vault, a wiki, a docs tree — by BLOCK ADDRESS instead of by whole page. Use when the job is to find which page and which section says something, read that one section, add a line to an index or a log, or rewrite one section of a note: geml find answers with file#address…
Reviews pull requests with upfront, severity-ranked findings and guides a human reviewer through context, code, and manual test cases. Use for PR reviews, merge assessments, or reviewer test preparation.
Independently review and fix a bounded task through convergence rounds, with evidence-backed closure and explicit stop/remediation decisions. Use for an explicitly invoked adversarial review-and-fix loop over an existing implementation, feature, problem, or diff, including repeated review/fix requests or a second…
A source-based research process for companies, industries, markets, or technical topics. It searches for original material, reads the underlying pages, and records supported claims with quotations and source references.
A human approval checkpoint for a technical plan before coding begins. It requires separate approval of the plan's overall direction and its detailed contents, then records both decisions in TECH.md.
Drive the zitadel CLI to set up and manage Zitadel authentication in a project. Use it whenever the work involves Zitadel or its CLI at all, even for a small request or one that follows earlier Zitadel work: adding login, sign-up or sessions; creating, listing or inspecting a Zitadel project or its credentials…
A PDF report format for explaining completed primary-school homework from supplied questions, student answers, assessments, and reference solutions. PDF is a document format designed for consistent viewing and printing.
Answer questions about CSV files with read-only SQL, without loading the file into context. csvql can't write or reach the network, and --root keeps it inside chosen folders.
★not rated 31
changed 14d agoA
tokens not measured
originalMIT
Animate a tap-through onboarding or web funnel (quiz, survey, web2app flow) so the motion tells the flow's story — each page-to-page hand-off gets its own choreography tied to what the two pages say, the chosen answer physically becomes the progress it earns or the next page's hero, and everything stays fluid…
Agent skills for building Langium 4.x languages and for using the Langium AI (lai) CLI to generate descriptors, system prompts, evals, and MCP servers for your DSL.
★not rated 31 7d 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: