Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,343 indexed, measured the same four ways as everything else here.
Use Lingzao creator-content tools for Xiaohongshu/XHS, Douyin, and WeChat official-account public content. Lingzao supports XHS SEO, Xiaohongshu account analysis, benchmark account discovery, viral note breakdown, keyword research, one-stop content packages from keyword/link/image/inspiration material, title and cover…
OneCLI Gateway: transparent HTTPS proxy that injects stored credentials into outbound calls. You MUST use this skill when the user asks you to read emails, check calendar, access GitHub repos, create issues, check Stripe payments, or interact with ANY external service or API. Do NOT use browser extensions or OAuth CLI…
Find current Polygres guidance for setup, application integration, retrieval design, and troubleshooting by navigating the hosted skills library. Use when a task needs published Polygres guidance through web access.
Manage AI coding skills and commands with the skm CLI: one local Git repo of skills/commands, installed into Claude Code, Codex, pi, dsh and any custom target. Use when asked to import/adopt a skill, install or uninstall one somewhere, update or verify the repo, inspect what is installed where, add an install target…
A guide for writing, rewriting, and reviewing prompts and instructions for coding agents. It examines how each sentence affects what an AI model produces, including files such as AGENTS.md and skill instructions.
Run an autonomous Claude agent through the local EventBridge (Kafka + CloudEvents), stream the reply, and resume prior conversations by correlationID. Use this when the user asks to "run an agent to X", "ask an agent to X", "print the response", "continue ", or "show the conversation for ". Talks HTTP to one…
Install, find, link, update and validate engineering standards from the Agent.md registry (304 free MIT markdown standards across 20 categories) using the activate-agentmd CLI; print the breaking changes for the dependency majors this project runs; and lint agent instruction files for leaked keys and prompt injection.…
A research workflow that uses CNKI, a Chinese academic literature database, through an external tool connection. It produces evidence-based literature reviews or research reports from Chinese academic sources.
Develop, build, test, and gate changes in the epistemic-graph engine repository. Use before adding a capability, changing the wire contract, or running the test/gate suite in this repo. Covers the Rust-native rule (new behaviour is a Rust crate exposed through the generated wire contract; Python/Go/JS are clients, not…
Update or create your attached lemonaid brief, choose its status, record questions and waiters, check child cleanup, or start a reviewer. Use when asked to update your brief or when work changes what it needs or is waiting on.
Use when setting up or writing end-to-end tests with blastproof — the plain-English YAML e2e runner that drives Chromium and resolves elements from the accessibility tree. Covers blastproof init, plan, run, test, the .blastproof/ directory, config.yaml, impact mapping with routes:/ignore:, score gating, and writing or…
Create genuinely large, detailed images by generating coordinated regions with the official Gemini API CLI and composing them with native tools. Use for large illustrations, panoramas, murals and explorable worlds; apply a separate world pack only when requested.
Remove writing patterns that make text sound AI-generated. Apply when drafting or revising human-facing replies, PR descriptions and comments, Slack and email drafts, documents, code comments, and commit messages.
Explain or customize NextProb project settings and workspace extensions, including HTML settings interfaces, sidebar configuration, ignore rules, agent instructions, and user-defined plugins, hooks, commands, and background services.
One tick of the GitHub maintenance loop for the repository named in .loop/config.json: send what the maintainer already approved, triage the issues created in the configured window, fix what is worth fixing test-first, follow the owner's own pull requests through CI, review and merge, and draft every outbound action…
Build, edit, inspect and export native SolidWorks models through solidworks-mcp. Use for CAD modeling, raster-to-sketch work and SolidWorks COM/MCP diagnostics. Read before calling a SolidWorks MCP tool.
Manage the FinFocus plugin lifecycle: discover, install, update, remove, validate, inspect, and troubleshoot installed plugins. Use when installing or updating a pricing plugin, installing a plugin from a GitHub URL, choosing a region-specific binary, fixing a plugin that will not start, a stale lock, a checksum or…
★not rated 11
changed 3d agoA167 tokens
originalApache-2.0
Writing RPG Maker MV event command lists - dialogue, choices, switches and variables, conditional branches, shops and battles - with the rpgmaker-mv MCP server. Use when creating NPCs, chests, quests or cutscenes.
Budget, payment and audit controls for AI agent API calls and MCP tool calls. Runs locally from the satgate-mcp-bridge npm package. Needs 2 environment variables to run.
★not rated 11 todayASocket: warn
tokens not measured
originalApache-2.0
Standardize the inline comment/fix cycle for LaTeX papers: the owner edits .tex files and leaves % comments; you capture every comment verbatim into a persistent ISSUES.md ledger, fix each one in the sources, describe each fix in plain language, promote recurring lessons into standing rules, and land the round with a…
★not rated 11 18d agoA0 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: