agent-memory-kit
18841Skill Claude CodeCodex
Type: Practice / Framework Dependencies: None (markdown only).
Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 273,139 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
Type: Practice / Framework Dependencies: None (markdown only).
Skill Claude CodeCodex
Acquire and analyze five-year American Community Survey (ACS) data using the urbnindicators package in R. Provides correct treatment of margins of error (MOEs), allows for interpolation, and returns human-readable variable names and an associated codebook. Use when the user wants ACS or Census data; mentions…
Skill Codex needs its repo
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…
Skill Claude CodeCodex
Control BedJet sleep climate devices via MCP tools — temperature, modes, fan speed, biorhythm programs, presets, and device settings. Requires the bedjet-hub daemon running on the local network.
Skill Claude CodeCodex
Create, customize, debug, or validate Shine app, shell, and sys presets, including adaptations of built-in categories. Use for preset source authoring and review; activation and live installation are outside this workflow.
Skill Claude CodeCodex
For writing and executing SQL queries - from simple single-table queries to complex multi-table JOINs.
Skill Claude CodeCodex
A Chinese-language workflow for handling Kubernetes nodes marked NotReady. Kubernetes is a system for running and managing containerized applications across machines.
Skill Claude CodeCodex
Conduct structured requirements-gathering interviews before creating implementation plans. Use this skill when planning non-trivial tasks involving multi-file changes, new features, refactors, or architectural decisions. Auto-skip for clearly scoped, unambiguous single-file changes.
MCP server Claude CodeCodexCursor +2
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Skill Claude CodeCodex
Install gtm-engine and build the user's home. Clones the repo to /.gtm-engine, creates /gtm (brand, keys, assets, insights and engines.json), scaffolds the engine folders wherever the user wants them, copies selected skills into /.agents/skills/ then symlinks them into Claude/Codex/Cursor, interviews the user to fill…
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
Supabase's hosted MCP server: lets the agent manage projects, tables, SQL and migrations. Remote server at mcp.supabase.com.
Skill Claude CodeCodex
Maintain, enhance, and extend the system-agnostic linux-system-manager toolset. Use this skill when adding new features, modifying distro menus, replicating functionality across all distros, managing systemd services, or running tests.
Skill Claude CodeCodex
Generate the Manim scene file (scenes/{module}.py) from an approved-or-reviewed script — layer 4 of the pipeline. Use when a chapter's script is ready and its scenes need building or regenerating.
Skill Claude CodeCodex
Provision and manage Voltage Park H100 GPU instances. Use when the user needs to spin up H100s, SSH into VP instances, transfer files, or terminate cloud GPU instances.
Skill Codex
Use when implementing or modifying frontend work in Noah so changes follow the existing module registration, route metadata, API wrapper, mapper, schema, table, and widget patterns.
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
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.
Skill Claude CodeCodex
Use when coding, designing, reviewing, or writing documentation in TypeScript or Python projects.
dungnotnull/black-soldier-fly-waste-processing-agent-skill
Skill Claude CodeCodex
Skill "black-soldier-fly-waste-processing-agent-skill" from dungnotnull/black-soldier-fly-waste-processing-agent-skill, covering skill.md - skill registry documentation, 1. registry overview, 2. registered skills, 3. how skills are registered and 4. how skills are resolved.
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Have Claude Fable 5 plan the current task, then run an automatic warm diff-review after you execute. You (the below-Fable driver — Sonnet or Opus) gather the evidence and execute; Fable is the context-blind PLANNER — one plan engagement at the start (it writes the plan, unanchored by any draft of yours), one warm…
dungnotnull/rc-boat-hydrodynamics-design-agent-skill
Skill Claude CodeCodex
RC Boat Hydrodynamics & Naval Design analysis and decision-support harness with flexible agent architecture, dynamic skill registry, and production-grade error handling. Use for any RC boat design, analysis, hydrodynamics calculation, stability assessment, propulsion sizing, or naval architecture question. Trigger on…
Skill Claude CodeCodex
Quick read-only health check — session context, workspace mounts, tool availability, and task snapshot. Use when the user asks for system status or runs /status.
Skill Claude CodeCodex
A workflow that turns Chinese scripts, course materials, or spoken narration into 16:9 web presentation videos and MP4 files. It covers narration writing, web-page creation, voice generation, and frame-by-frame screen recording alignment.
Skill Claude CodeCodex
Reconcile an installed Fieldbook copy against a NEWER kit zip. Reads .agent-docs/.kit-manifest.json, 3-way diffs ONLY kit-owned files (skills/hooks/rules/templates/schema — never the colleague's content dirs), and uses sha256-vs-manifest so a file the colleague edited is treated as "theirs" (shows a diff, never…
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: