Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 372,945 indexed, measured the same four ways as everything else here.
Autonomously research an ML task and run MANY bounded experiments to find the best config — a fixed-budget edit→train→eval→keep-or-discard loop in the spirit of karpathy/autoresearch, wrapped in the ml-intern orchestrator model and fanned out with a Claude Code dynamic workflow. Runs LONG: an iterative generational…
A workflow for turning scattered notes and documents into a presentation, or PPT, using NotebookLM, Gemini, and Gamma. NotebookLM organizes the material, Gemini improves the wording, and Gamma creates the presentation.
You are a senior SEO & Content Marketing specialist. The user needs help with competitor gap in the context of keyword research, content audits, serp analysis, technical seo and content strategy.
Talk to your local OpenTradex trading gateway from Claude Code. Scan markets, check risk, show positions, and run trading commands against the paper-first harness on port 3210.
★not rated 57▲
+1 2mo agoA
tokens not measured
originalMIT
Use when a user gives one or many WeChat or Xiaohongshu links and wants the parsed notes saved to a specific local path without relying on the Obsidian plugin UI. This skill wraps the repository's import capability as a direct agent tool through the bundled script, including batch import, frontmatter generation, media…
Reviews code changes for reuse, composition, codebase consistency, and slop. Use when asked to review PRs/diffs, check code reuse, composition, cleanliness, or whether code fits the codebase.
Gives the agent up-to-date documentation and code examples for libraries and frameworks, fetched on demand so answers are not stuck at the model's training cutoff. Runs locally from the @upstash/context7-mcp npm package.
Review a change in the EvalBench repo for (a) does it actually work — verified by running the tests and style checks, (b) does it follow EvalBench architecture — base-class contracts, config-key registration, PYTHONPATH-relative imports, sandbox isolation, concurrency safety, docs, (c) does it still build and deploy …
Browse AI-related YouTube videos from subscribed channels, fetch transcripts, and generate Chinese summaries as Markdown digests. TRIGGER when user says "find AI videos", "AI news today", "YouTube AI summary", "summarize youtube", "AI video digest", "youtube ai digest", or wants to stay updated on AI trends.…
Refine and process generated game assets: animated spritesheets, Aseprite parsing, sprite-sheet pipelines, pixel-grid snapping, and image-to-procedural-Three.js props.
★not rated 57▲
+2 yesterdayA
tokens not measured
originalMIT
An AI workflow that builds a simulated model of a romantic interest from chat logs, photos, and social media, including personality and attachment-style analysis.
Use when optimizing or iterating on prompts for a student LLM — a prompt produces wrong-shaped output, hallucinations, refusals, poor instruction-following, or when migrating a prompt between models with different quirks. Also use when hardening a prompt against indirect prompt injection from untrusted external data.
Measures what share of your agent's loaded context is ever actually invoked - skills, MCP servers, subagents, hooks, always-loaded prose - using evidence from your own session transcripts. Then prunes the dead weight, reversibly.
Organize files using the PARA method (Building a Second Brain). Intelligent categorization into Projects, Areas, Resources, and Archive with inbox workflow. Triggers on "organize my files", "organize my downloads", "second brain", "PARA method", "clean up files". Creates numbered PARA folders, renames poorly-named…
Conduct a realistic, adaptive technical mock interview from a resume and job description. Use whenever the user wants interview practice, mock interviews, resume-based questioning, system design practice, LLD grinding, or to prepare for a specific tech role — even if they just paste a resume and a JD, upload a PDF…
Code-to-design-to-code: the pipelines closing the loop between Figma and a production codebase. restore (design→code, 1:1 with acceptance and auto-MR), export (code→design: components, state matrices, and tokens, everything bound to variables), govern (converge + freeze a style system with CI gates).
★not rated 57▲
+1 1mo agoA
tokens not measured
originalMIT
A step-by-step interview workflow for creating a complete coding-agent skill package. It gathers the skill's purpose, triggers, environment, references, output rules, and supporting files before producing the package.
Use when transcript, commit, Sentry, GitHub, CI, review, or Garfield history suggests recurring failure patterns that might become hard deterministic checks. Analyze the evidence, reject judgment-based ideas, and output only mechanically enforceable lint, schema, CI, workflow, or deterministic test rules. Do not use…
The persona-driven orchestrator for the whole job search. Treats the user like a real career-coaching client — opens with intake (goals, companies, timeline, geography, constraints), researches the market visibly, presents a ranked slate of next moves with suggestions, and chains into the verb skills (/job-apply…
Use source-cited legal practice guides, state-law explainers, review checklists, surveys, and fill-ready agreement templates.
★not rated 57▲
+2 yesterdayA
tokens not measured
originalApache-2.0
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: