Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,329 indexed, measured the same four ways as everything else here.
Build, change, debug, and prepare production mobile apps across domain meaning, local and server state, lifecycle, platform, and release boundaries. Use for non-trivial Flutter, React Native, iOS, or Android work involving persistence, sync, auth, offline behavior, notifications, permissions, native integrations…
Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…
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…
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.
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 quality-assurance guide based on James Bach's approach to software testing. It treats testing as learning about risks and unexpected behavior, not just checking a fixed list of expected results.
Agentic AI-native multi-tier DNS routing, live packet tracing, and failover bypass engine for Pi-hole, CoreDNS, dnsdist, Unbound, Stubby, DNSCrypt-Proxy, and VPN DNS.
Build production-ready MCP servers using FastMCP framework with proven patterns for tools, resources, prompts, OAuth authentication, and comprehensive testing. Use this when creating FastMCP-based MCP servers with features like Google OAuth, multiple resource types, testing with FastMCP Client, or complex tool…
From a shell, your first action in any session that uses NodeSpace is to run nodespace --version. Run no other nodespace command, and do not save or search anything, until you have done it and the version is {{MINCLIVERSION}} or newer. Through the nodespace tool, which refuses --version, skip this check: the preflight…
Use LISA's ZCLI18NSERVICE ABAP HTTP API to read, write and compare SAP object translations — data elements, domains, CDS views, message classes, text pools, text tables, and more. Covers the six actions, the JSON wire contract, target types and selectors, and the pitfalls. Auth is handled OUTSIDE this skill — by a BTP…
Use when an agent should work with Lifeblood's MCP semantic-code tools: analyzing C# or Unity workspaces, querying symbols/dependencies/blast radius/file impact/test impact, checking architectural invariants, validating edits with compilecheck/diagnose, or choosing the right Lifeblood tool instead of grep-style…
Use when building, reviewing, installing, packaging, or diagnosing an agent-connector integration. Two audiences: MCP developers use agent-connector as a framework dependency inside their own branded MCP package/bin, while agent-host users use connector-free agent-connector usage for whole-conversation token totals.…
Unofficial MCP server for Make.com automation - build, validate & deploy scenarios via AI. Runs locally from the make-mcp-server npm package. Needs 4 environment variables to run.
★not rated 8 9mo agoA
tokens not measured
originalMIT
One-time Replen setup — profiles your active repos so matches are relevant, not generic. Runs autonomously in the background. Invoke with /replen-onboard.
Ein persönliches Design-System mit einer Dateiablage pro Kunde, einer lokalen Weboberfläche und einer lokalen Verbindung, die passende gespeicherte Designinformationen für neue Arbeiten bereitstellt.
Translate natural-language user requests into bounded Claude Code worker tasks while Codex or ChatGPT remains the supervisor. Use when the user gives an ordinary prompt and wants Codex to clarify scope, choose a safe work boundary, generate a worker prompt, approve or defer worker execution, read run summaries and…
MCP server "zotero" as configured in piiinpiiins/Zotero-MCP-lite. Launched with uv --directory /PATH/TO/Zotero-MCP-lite run python -m src.zotero_mcp.server.
★not rated 8 3mo agoA
tokens not measured
originalMIT
Set up APIClaw and land one live API execute. When a user says "set up https://apiclaw.cloud/SKILL.md", or you need a research API call without collecting provider keys, follow this file. Auth is Clerk via npx @nordsym/apiclaw auth login. Confirm with npx @nordsym/apiclaw auth whoami before any execute. Execution is…
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: