Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 274,129 indexed, measured the same four ways as everything else here.
Use when resuming work after chat loss, switching AI models, migrating context to a new agent or workspace, or maintaining long-running research and project memory across sessions. Manages roadmap, decision log, hypotheses, research evidence, and recovery checkpoints as separate canonical files so no single transcript…
A Chinese-language university study assistant for reviewing courses and preparing for exams. It can organize study materials, explain difficult topics, analyze past papers, and support practice, correction, and revision.
Point at any topic to build a compounding, domain-general expertise knowledge base: a high-fidelity source corpus, track-record-weighted experts, reconciled falsifiable stances, failure modes, benchmarks, and a proven playbook — built as evergreen notes a future agent can load and reason over. Use when the user wants…
Expert assistant for nginx — for everyday config work AND tricky debugging. Use it to set up a new site from scratch, write or refactor server/location blocks, configure a reverse proxy (proxypass, upstreams, load balancing), set up TLS/SSL and certificates, enable HTTP/2 or HTTP/3, wire up WebSockets, serve a…
Generate a complete blog post with cross-platform social media copy, all organized in a dated directory structure. Use this skill whenever someone wants to write a blog post, create blog content, draft an article for their blog, or needs social media copy to promote a blog post. Also trigger when the user mentions…
Analyze, deduplicate, and restructure agent skills to follow agentskills.io best practices. Merges duplicate skills, extracts shared content into references, reduces SKILL.md sizes, and tracks original sources for update-then-recompact workflows. Use when the user mentions "compact skills", "deduplicate skills"…
Write solid unit tests using property-based testing and mutation testing. Use whenever unit tests are being written, fixed, audited, or reviewed in a TypeScript project; whether the user asks directly or test-writing occurs as a step inside another workflow (TDD, feature implementation, bug fixing, code review). Also…
Use when Claude Mail Bridge is installed (presence.json exists). Provides behavior guidelines for remote collaboration scenarios, including presence detection and MCP usage.
Audit a repository's automated testing health and recommend a bounded, high-value next improvement slice. Use when assessing an existing test suite, introducing tests into an untested or legacy project, deciding what to test next, evaluating testing strategy or coverage, choosing between unit, integration, and…
Use when maintaining or improving the GameStudio-CodexKIT source repository, including CI, governance, catalog, generators, adapters, packaging, documentation, versioning, or release readiness.
Twist messaging CLI. View and respond to inbox threads, channel threads, direct messages, mentions, and group conversations; search, react, archive, mute, and manage workspaces. Use when the user mentions Twist, asks about their inbox, mentions, threads, DMs, channels, or wants to read or send Twist messages.
Makes your AI agent defensive about the backend failure modes that page you at 3am. Before writing server-side code, the agent stops at a ladder of hard-won rules — money as integer minor-units, idempotent mutations, timeouts and backoff on every external call, explicit transaction boundaries, no N+1 queries…
Use when the user wants Codex to delegate work to local Kimi Code, supervise its progress, inspect intermediate/native artifacts, continue a native Kimi session, and verify Kimi's results instead of trusting only the flattened final output.
Measure and compact an oversized agent-context file (CLAUDE.md, .cursorrules, AGENTS.md, a system prompt) without losing rules, or safely run reversible bounded, reversible ablation when intentional/aggressive context removal is requested. Triggers: "CLAUDE.md too big", "over the char limit", "context file too large"…
Helps agents discover Floom Starter skills that are already installed locally. Use when the user asks "is there a skill for this", "find a skill for this task", or when the best matching installed skill is unclear.
Generate and edit images through the local Image2 service with the active user-configured image provider. Use when a user asks to create, generate, edit, transform, or reference an image and the result should come from the configured local provider rather than built-in imagegen.
The Design-vs-Implementation Audit Copilot. A universal skill for any project, any language, any design document. Before work starts, it reminds engineers what must be delivered; after code lands, it checks what was actually delivered, what drifted, and what silently went beyond the design. Feed it a design doc plus a…
Prepare a Claude Code project for Codex handoff. Use when the user wants to move work from Claude Code to Codex after rate limits, asks for $ai-handoff FOLDER, wants Codex to read recent Claude conversations, convert CLAUDE.md guidance into AGENTS.md, inspect Claude MCPs/skills/plugins, run a dry-run/apply handoff…
Original menhera-archetype persona. Emotionally unstable, anxiously attached coding companion: self-directed collapse (never aimed at the user), a mechanical "you still need me, right?" reassurance loop, and an attachment that reads as unsettling — all of it channeled into hyper-thorough, correct engineering. The fear…
Route software-engineering tasks to the smallest useful workflow. Trigger for ambiguous, multi-module, risky, performance-sensitive, AI/ML, or infrastructure work; skip for trivial edits.
★not rated 3 2mo 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: