Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 388,304 indexed, measured the same four ways as everything else here.
Generate or edit images through the HeyRoute gateway (model gpt-image-2): call POST /v1/images/generations or /v1/images/edits and read the SSE response (started/heartbeat/completed/error/done). Use whenever the user asks to generate, draw, or edit an image via HeyRoute / heyroute.ai. Requires the HEYROUTEAPIKEY…
Use when working with low-level Cardano utilities via MeshJS core-cst package. Covers CBOR serialization and deserialization, Plutus data conversion, address resolution and parsing, CIP-8 message signing and verification, script parameterization with applyParamsToScript, native script hashing, and direct access to…
Security audit orchestration for Soroban/Stellar Rust smart contracts. Use when user asks to "audit this codebase", "run soroban auditor", or "check for security vulnerabilities". Utilizes AST squeezing, pre-computed guard/state/integration/divergence/invariant/unsafe maps, parallel agent spawning, a verification…
Plan any multi-step project using a guided conversational interview based on the GTD Natural Planning Model. Walk the user through four phases — Purpose & Principles, Outcome Visioning, Brainstorm, Organize — plus an Execution Bridge.
Fetch and convert web pages to clean Markdown with automatic failover (markdown.new → Jina Reader). Supports single-page fetch and multi-page site crawl.
A collection of Claude Code skills shared by haopeng.liu. Claude Code is a coding assistant that can be extended with reusable instructions and workflows.
★not rated 2 6mo agoA
tokens not measured
originalMIT
Open a REVIEW.md (written by /difit-review) in difit's browser UI for interactive review. Starts a difit instance (or pushes to one the user already has running on a given port), populates it with the unresolved threads from REVIEW.md. Optional — REVIEW.md is the source of truth; this skill just provides a nicer way…
A template skill demonstrating the structure of a Claude Code skill. Use this as a starting point when creating your own skill — copy the directory, rename it, and replace the contents of this file.
Use when debugging, tracing, or mutating state in a running or testable Java application — inject code at method entry/exit, read/write fields, trace calls, throw exceptions, or verify behavior without recompiling.
Use when reviewing a pull request, before posting any feedback. Runs fully automated in GitHub Actions. Detects intent, identifies specs via Linear, dispatches expert agents, classifies findings by severity, and posts inline comments on the exact lines that matter.
DashNex framework knowledge base. Fetches architecture docs, coding conventions, module guides, and design guidelines from the DashNex skills repository. Use when working on any DashNex project.
Surface architectural friction and propose deepening candidates after ratifying or bootstrapping a load-bearing project Glossary.md. Insists on a consistent glossary as a precondition for any review.
A workflow for fetching research papers, including identifying a paper from its title and completing related tasks. Papers are published reports of research findings.
Use when a pull request has review feedback waiting and you want to act on all of it — CodeRabbit, GitHub Copilot, Gemini Code Assist, and any other review bot, plus human reviewers. Collects inline review threads, review summary bodies, and pull request comments, extracts the CodeRabbit findings that never reach the…
Rewrite Thai text that sounds AI-generated so it reads like a Thai writer, without changing what it says. Use when editing, reviewing, or polishing Thai prose for translationese, inflated claims, tourism-brochure language, การ/ความ nominalization, ถูก-passive overuse, ซึ่ง-chaining, connector pileup, redundant…
Harden GitHub Actions and Dependabot: create or modify workflow YAML, reusable workflows, or .github/dependabot.yml; configure dependency updates, alerts, graphs, private registries, and pull-request automation; audit security, correctness, reliability, cost, or performance.
★not rated 2
changed 6d agoA58 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: