Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 379,535 indexed, measured the same four ways as everything else here.
Senior engineer CLI expertise for AI agents — workflows, safety guardrails, gotchas, and anti-patterns across cloud, IaC, containers, databases, dev tools, and platforms.
Build SKILL.md files for Claude Code, Codex, Amp, OpenCode. Production examples and patterns for skill structure, scripts, distribution, and making CLI tools AI-native.
Make AI coding agents prove their work — frozen specs, budgeted verification loops, hard gates, an independent blind verifier. No unverified work passes.
★not rated 8 3mo agoA
tokens not measured
originalMIT
Design recurring knowledge-base update loops for Obsidian-style vaults, project wikis, second-brain folders, and research notebooks. Use when setting up automated source ingestion, daily reflection, meeting-note processing, health checks, state cursors, runbooks, scheduler prompts, or validation gates for a maintained…
Power BI Desktop control for AI agents — reload Desktop so it re-reads TMDL/PBIR changed on disk, and capture the window to PNG so the agent can see what actually rendered. Closes the feedback loop that breaks when an LLM develops Power BI reports. Windows only.
★not rated 8 2mo agoA
tokens not measured
originalMIT
Professional AI/ML research-engineer workflow: research papers first, pick the best method for each problem (computer vision, medical imaging, NLP/LLM, tabular, time-series, audio and speech, recommendation, generative, reinforcement learning, graph, multimodal, video, 3D, and anomaly detection), train and fine-tune…
★not rated 8 3mo agoA
tokens not measured
originalMIT
Research any open-source repository end to end and answer the core question — SHOULD YOU contribute to it? — with a GO / NO-GO / GO-IF verdict backed by evidence: snapshot, momentum, contribution landscape (PR acceptance rates, outside-contributor merge rates, first-timer outcomes), issue health, governance, community…
Visual Design Mode overlay for annotating, inspecting, and modifying UI elements directly in the browser. Click elements to annotate, hover to inspect box models, and let Claude apply your design feedback to source code.
Generate and install an agent skill from a public webpage with WebSkills. Use when a user wants to turn a public docs, help, reference, wiki, or spec page into a reusable local skill, preview extracted skill artifacts, or install the generated skill with npx skills add.
Police large volumes of AI-generated frontend work for design-system conformance, and audit the design system itself so it can be policed. Report-only: verdicts, reviews, plans, and issues — it never edits your code.
★not rated 8 15d agoA
tokens not measured
originalMIT
Zero-key Claude Code cost tracking, per project and per branch. Budget caps with SIGTERM enforcement, reads your local /.claude session logs, and syncs to a hosted team dashboard (Goei).
★not rated 8 4d agoA
tokens not measured
originalMIT
Full-lifecycle SDLC guardrailing framework for Claude Code — from product ideation and planning through implementation, code review, and test validation. Enterprise-grade skills and agents for AI-human peer collaboration.
★not rated 8 todayA
tokens not measured
originalMIT
Find the right skills for a task before acting. Use at the start of any multi-step or unfamiliar request to retrieve relevant skills by meaning, not name. Triggers when the user asks to build, set up, design, deploy, fix, or automate something and the right skill isn't obvious.
Work with the noflate Rust crate: use DEFLATE, gzip, and zlib encoding/decoding APIs; wire sans-io streaming encoders and decoders; use EncodeOptions; handle WebSocket permessage-deflate (RFC 7692); and debug nostd or checksum-related behavior. Use when the task mentions noflate, DEFLATE/gzip/zlib internals…
A full-stack development guide based on DHH’s pragmatic approach, favoring simple applications, framework conventions, and one-person control of the product.
★not rated 8 4mo agoA39 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: