This file is the schema layer of prodkit's knowledge system (inspired by Karpathy's LLM Wiki pattern). It tells the LLM how to maintain the user's product knowledge base and how skills interact with it. Two jobs: (1) define the three-layer knowledge architecture, and (2) encode 7 passive automations that make skills smarter across sessions. No setup required. Everything activates on first use. Prodkit maintains a three-layer knowledge system. The LLM writes and maintains the wiki. The user curates sources and…
Structured heartbeat loop for AI agents that wake periodically, check assignments, do work, and exit. Use when designing agent execution loops, task pickup patterns, blocked-task handling, incremental context loading, or any agent that runs in short execution windows rather than continuously. Derived from production patterns in the Paperclip control plane.
Reduce token consumption in AI agent systems without reducing capability or task quality. Use when designing agent prompts, optimizing heartbeat loops, debugging high token usage, or architecting multi-agent systems where cost matters. Covers the four root causes of token waste and systematic fixes. Derived from production analysis of 11,000+ agent runs in the Paperclip control plane.
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
File-based memory system using Tiago Forte's PARA method. Use this skill whenever you need to store, retrieve, update, or organize knowledge across sessions. Covers three memory layers: (1) Knowledge graph in PARA folders with atomic YAML facts, (2) Daily notes as raw timeline, (3) Tacit knowledge about user patterns. Also handles planning files, memory decay, weekly synthesis, and recall via qmd. Trigger on any memory operation: saving facts, writing daily notes, creating entities, running weekly synthesis, recalling past context, or managing plans.
Use when fixing, editing, changing, debugging, or working with any Python code. Applies the Boy Scout Rule—always leave code cleaner than you found it. Orchestrates other clean code skills as needed.
Use when writing, fixing, editing, or reviewing Python comments and docstrings. Enforces Clean Code principles—no metadata, no redundancy, no commented-out code.
Use when writing, fixing, editing, or refactoring Python functions. Enforces Clean Code principles—maximum 3 arguments, single responsibility, no flag parameters.
Use when writing, fixing, editing, or reviewing Python code quality. Enforces Clean Code's core principles—DRY, single responsibility, clear intent, no magic numbers, proper abstractions.
Use when naming, renaming, or fixing names of variables, functions, classes, or modules in Python. Enforces Clean Code principles—descriptive names, appropriate length, no encodings.
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Trigger when the user requests a review of frontend files (e.g., `.tsx`, `.ts`, `.js`). Support both pending-change reviews and focused file reviews while applying the checklist rules.
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively suggest when the user reports errors, unexpected behavior, or is troubleshooting why something stopped working.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
ramybarsoumCLAUDE.md