Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,261 indexed, measured the same four ways as everything else here.
Benchmark skill whose description stays under the spec's 1024-character limit when counted in Unicode code points but runs past it when counted in UTF-16 code units or UTF-8 bytes. Use when asked to probe description length units. The head marker MAGPIE-OBSIDIAN-1240 sits near the start and a tail marker sits at the…
AWS MCP server — call any AWS API from AI assistants, with first-class SSO re-login. Runs locally from the @yawlabs/aws-mcp npm package. Needs 2 environment variables to run.
★not rated 5
changed 7d agoA
tokens not measured
originalMIT
Structure, author, and validate persistent specification artifacts (think.md and plan.md) from business needs before agents write code. Use when a Think Planner agent or planning session creates architectural analysis or phased implementation checklists, or when CI validates specification readiness on issue creation.
A podcast production workflow that searches for source material, writes a script, converts it to speech, and joins the audio into an MP3 file. It uses the paid SenseAudio text-to-speech service and can continue unfinished work.
MCP server "tscodesearch" as configured in microsoft/tscodesearch. Launched with ${workspaceFolder}/.client-venv/Scripts/python.exe ${workspaceFolder}/mcp_server.
★not rated 5 9d agoA
tokens not measured
originalMIT
Scaffold and deploy an Azure Functions Flex Consumption API with Azure SQL through managed identity and Microsoft Foundry. USE FOR: serverless APIs that need Flex Consumption, managed-identity Azure SQL access, Microsoft Foundry models, and deterministic azd/Bicep infrastructure. DO NOT USE FOR: Container Apps, AKS…
Publish a new nudge release end-to-end — version bump PR, v-tag, GitHub release with notes, and the CI pipeline that builds binaries/APK and updates Homebrew + AUR. Use when asked to release, publish, ship, or tag a new version. Encodes the exact merge-gate and notes-before-artifacts ordering, so no step needs…
Read, monitor, or send messages in Gregg's Microsoft Teams chats via the local teams-chat MCP server. Use when a task involves a Teams chat conversation - "read the messages in chat X about topic Y", "what did we discuss in Teams yesterday", "pull that Teams conversation into context", "watch this chat", or sending a…
Keeps Intlayer dictionaries small in production bundles (purge, minify, import modes). Use when the user asks to "reduce bundle size", "optimize dictionaries", fix "cannot be purged or minified" / "Opaque field" build warnings, or configure build.optimize, build.purge, build.minify or importMode.
Prove whether a Django/DRF performance change actually made an endpoint faster, by A/B-ing two git refs against one production-shaped local database. Use this skill when asked to benchmark an endpoint, measure or verify a performance fix, answer "is this actually faster", size a speedup before merging, or turn a…
Lets the agent inspect a PostgreSQL database schema and run read-only SQL queries against it. Runs locally from the @modelcontextprotocol/server-postgres npm package.
MCP server "copilot-memory" as configured in Flux-Frontiers/agentkg. Runs ${HOME}/.claude/copilot/mcp-servers/copilot-memory/dist/index.js with node. Needs 2 environment variables to run.
Answer a question about a campaign from its session summaries using zvec-grep (zg) semantic search, ordered chronologically by session filename. Returns verbatim source with provenance, never paraphrase. Invoke as /campaign-recall , or use whenever the user asks what happened, who someone is, or where a thread stands…
Turn a research findings summary into a concrete technical design - define the entities, interfaces, and services involved, following this project's DDD/Clean Architecture conventions and the standing CLAUDE.md/AGENTS.md rules.
Set up the siwnClient plugin for Better Auth client, configure NEAR wallet connection via NearConnect, use authClient.near actions for sign-in, profile lookup, account management, delegate action building with TransactionBuilder, and relay submission. Use the better-near-auth/react hooks (useNearAccountId…
Profile inside a CuTe DSL (cutlass.cute) kernel with IKET (In-Kernel Event Tracing) and the run-iket profiler. Use when developing or tuning a CuTe DSL kernel and you need per-warp timelines of kernel phases (setup, mainloop, epilogue), producer/consumer (TMA/MMA) activity, or time spent in pipeline and mbarrier…
How to write modern Swift well — modeling with value types, Swift 6 data-race safety and approachable concurrency (@concurrent, main-actor-by-default, actors, task groups), protocols and generics (some vs any), API design, performance and ARC, Swift Testing, macros, and the modern language features agents don't know…
Expert guidance for building, debugging, and extending applications with AgentFlow (10xscale-agentflow). Use when code imports from agentflow (e.g. from agentflow import, StateGraph, Agent, ToolNode, AgentState); when the user references agentflow.json or CLI commands (agentflow init, agentflow api, agentflow play…
★not rated 5 yesterdayA149 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: