zby

zby/commonplace

Agent

Evaluate expectations against an execution transcript and outputs.

zby/commonplace

Skill Claude CodeCodex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

zby/llm-do

Settings file Claude Code

"Extend with llm, stabilise with code" - Prompts when you're exploring, Python when you're certain. Workers and tools form one function space—refactor between them.

zby/llm-do

Skill Claude CodeCodex

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

zby/llm-do

Skill Claude CodeCodex

Architectural code analysis for Python design quality. Evaluates simplicity (Rich Hickey), functional core/imperative shell (Gary Bernhardt), and coupling (Constantine & Yourdon). Use for design review or architectural assessment of Python code.

zby/llm-do

Agent Claude Code

Analyzes Python code for high-cohesion and low-coupling principles. Evaluates module boundaries, dependency direction, and interface design. Use when reviewing Python code architecture, checking for circular dependencies, or assessing modularity.

zby/llm-do

Agent Claude Code

Analyzes Python code for Functional Core, Imperative Shell pattern. Detects business logic mixed with I/O, side effects in pure functions, and testability issues. Use when reviewing Python code architecture for separation of pure logic from side effects.

zby/llm-do

Agent Claude Code

Analyzes Python code for Rich Hickey's simplicity principles - decomplection, values over state, pure functions. Use when reviewing Python code for unnecessary complexity, complected concerns, or checking if code "would get a good grade from Rich Hickey." Triggers on requests about simplicity, complexity…

zby/llm-do

Command Claude Code

Deep architectural analysis for Python code using Rich Hickey's decomplection principles. Evaluates simplicity, functional core/imperative shell, and coupling. Use for design review and architectural assessment.

zby/llm-do

Skill Claude CodeCodex

../../tasks/README.md.

zby/llm-do

Instructions file CodexOpenCode

AGENTS.md instructions for zby/llm-do, a project described as: "Extend with llm, stabilise with code" - Prompts when you're exploring, Python when you're certain. Workers and tools form one function space—refactor between them.

zby/llm-do

Instructions file

Claude Code instructions for zby/llm-do, covering instructions for claude and ai assistants, key references, development, documentation examples and agent design.

zby/llm-do

Skill Claude CodeCodex

Find connections between notes and update MOCs. Requires semantic judgment to identify genuine relationships. Use after /extract creates notes, when exploring connections, or when a topic needs synthesis. Triggers on "/connect", "/connect [note]", "find connections", "update MOCs", "connect these notes".

zby/llm-do

Skill Claude CodeCodex

Extract structured knowledge from source material. Two modes — extract (default) for comprehensive atomic claim extraction, and analyze for design proposals where one impact-analysis note replaces claim decomposition. A relevance filter ("does this change how we build our project?") applies to all modes. For extract…

zby/llm-do

Skill Claude CodeCodex

Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".

zby/llm-do

Skill Claude CodeCodex

Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".

zby/llm-do

Skill Claude CodeCodex

Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".

zby/llm-do

Skill Claude CodeCodex

End-to-end source processing -- seed, reduce, process all claims through reflect/revisit/review, archive. The full pipeline in one command. Triggers on "/pipeline", "/pipeline [file]", "process this end to end", "full pipeline".

zby/llm-do

Skill Claude CodeCodex

Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".

zby/llm-do

Skill Claude CodeCodex

Plan vault restructuring from config changes. Compares config.yaml against derivation.md, identifies dimension shifts, shows restructuring plan, executes on approval. Triggers on "/refactor", "restructure vault".

zby/llm-do

Skill Claude CodeCodex

Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".

zby/llm-do

Skill Claude CodeCodex

Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".

zby/llm-do

Skill Claude CodeCodex

Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (health checks). Use as a quality gate after creating notes or as periodic maintenance. Triggers on "/review", "/review [note]", "verify note quality", "check note health".

zby/llm-do

Skill Claude CodeCodex

Update old notes with new connections. The backward pass that /connect doesn't do. Revisit existing notes that predate newer related content, add connections, sharpen claims, consider splits. Triggers on "/revisit", "/revisit [note]", "update old notes", "backward connections", "revisit notes".