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.
Autonomous orchestrator that delegates a task to a /pi, /opencode, /codex, or /cursor subagent and drives it to completion without user babysitting. Invoked as /autopilot . Arms a backgrounded wait for an instant completion ping, checkpoints the subagent every 10 minutes (interrupt, progress report, course-correct)…
MCP server "go-gerrit-mcp" as configured in GaijinEntertainment/go-gerrit-mcp. Runs in Docker (ghcr.io/gaijinentertainment/go-gerrit-mcp:1.1.3). Needs 11 environment variables to run.
★not rated 9 3d agoA
tokens not measured
originalMIT
MCP server "playwright" as configured in smartlabsAT/claude-playwright. Runs /private/var/www/claude-playwright-toolkit/dist/mcp/server.cjs with node. Needs 1 environment variable to run.
★not rated 9 5mo agoA
tokens not measured
originalMIT
Meta-skill that improves other skills based on real usage failures. When an SDT reports a skill produced incorrect or unexpected output, this skill analyzes the root cause, generates a structured improvement proposal, applies the fix following CONTRIBUTING.md guidelines, and offers to create a PR or apply locally.…
Wire mnemostack into OpenClaw as an MCP server, alongside the native OpenClaw memory tools (memorysearch / memoryget). The two coexist — mnemostack handles the hybrid pipeline (Vector + BM25 + Memgraph + Temporal + configurable rerank), while the native tools do fast file-scoped retrieval.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Use this skill for IT Business Analysis deliverables in insurance, reinsurance, or financial services. Triggers: writing BRDs, FRDs, user stories, epics, themes, acceptance criteria; creating process flows or swimlane diagrams; building RACI matrices or stakeholder maps; performing gap analysis or impact assessments…
Adds a dx-cli subcommand from a DX Web API method docs page—fetch docs, stub Commander hierarchy, implement request/options, verify with make and --help. Use when the user provides or wants a https://docs.getdx.com/webapi/methods/ URL, asks to scaffold or implement a CLI command for a Web API method, or says "create…
Use this skill when designing, building, reviewing, submitting, or revising an app for Apple platforms so it is compatible by default with Apple App Store Review Guidelines. This skill covers App Store review readiness, default-safe product architecture, privacy, permissions, metadata, payments, user-generated…
Use this skill when building, debugging, or answering questions about Liveblocks. Liveblocks gives you the building blocks and infrastructure to enable people and AI to work together inside your app, powering realtime collaboration. Liveblocks features include collaboration, rooms, organizations, workspaces, comments…
Use this skill whenever Claude is about to help with any task that has multiple reasonable approaches, unclear requirements, personal preferences, or ambiguous scope. This includes (but is not limited to): writing tasks, project planning, recommendations, design decisions, technical choices, content creation, business…
MCP server "qdrant-neo4j-crawl4ai-mcp" as configured in BjornMelin/qdrant-neo4j-crawl4ai-mcp. Runs locally from the qdrant-neo4j-crawl4ai-mcp Python package.
★not rated 9 1y agoA
tokens not measured
originalMIT
MCP server "jcr-partition" as configured in yosh3289/jcrmcp. Runs /path/to/jcr_mcp_server.py with /path/to/python.
★not rated 9 2mo agoA
tokens not measured
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: