Anthropic Claude Pro/Max OAuth compatibility workflow for this repo. Use when debugging Anthropic OAuth failures, misleading extra-usage errors, Pi request shaping, prompt fingerprinting, or deciding between hook-based fixes and deeper provider overrides.
Heuristics and process for discovering structural improvements in this package. Load when planning a new improvement round — contains the smell taxonomy, analysis workflow, and prioritization framework distilled from many phases of refactoring.
Reference for the Pi coding agent's turn/tool execution model and extension event lifecycle. Use when designing extension timing (when to flush, notify, or intercept), understanding event sequencing, or reasoning about what the agent sees between turns. Includes the verified lifecycle diagram, event handler…
Use when preparing, validating, publishing, or documenting a pi-commandcode-provider release/deployment, including version bumps, changelog entries, npm publish, GitHub releases, tags, and release follow-up comments.
Review prose written for others -- user-facing docs, prompts for other LLMs, inline comments, docstrings, and other-facing messages -- for local jargon leakage, orphaned references, missing grounding, and audience or genre misfit.
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
Resolve project-local issue tracker routing and publish Linear issues safely. Use before creating Linear issues, PRDs, phase breakdown issues, or when deciding whether Linear/GitHub/local docs is the configured tracker. Enforces capability ≠ routing: Linear requires project-local policy, team association, auth, and…
Create distinctive, crafted TUI components for pi using @mariozechner/pi-tui and @mariozechner/pi-coding-agent. Use when building interactive terminal UIs — custom components, overlays, dialogs, dashboards, widgets, data visualizations, animated elements, game-like interfaces, or any visual TUI work inside pi…
Search and verify Joel's Pi, Claude, Codex, Cursor, Grok, and OpenCode session history. Use when asked to recover prior context, find exact transcript evidence, inspect session receipts, continue old work, or verify capture health. Prefer flowing recall before raw transcript search when the question is about prior…
Create distinctive, crafted TUI components for pi using @earendil-works/pi-tui and @earendil-works/pi-coding-agent. Use when building interactive terminal UIs — custom components, overlays, dialogs, dashboards, widgets, data visualizations, animated elements, game-like interfaces, or any visual TUI work inside pi…
Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.
Orchestrate subagents in herdr from pi fabric using the plain subagent tool (pi-herdr-agents). Covers exact fabricexec call shapes, model tiers, parallel spawn patterns, and hard-won gotchas. Use for any delegation: single one-off tasks or parallel fan-out.
Pi overlay for diagnosing Tinker training, renderer, and deploy issues. Use when training is slow, hung, mismatched vs vLLM/SGLang, or an error is opaque. Canonical triage lives in Tinker Cookbook.
Sample, evaluate, and post-train Inkling and Inkling-Small from Pi. Use when the user mentions Inkling, tml-renderers, TMLv0, thinking effort, Inkling-Small, or Inkling audio/images. Load before writing Inkling training or eval code.
Pi overlay for Tinker post-training. Use when the user wants to plan SFT/RL/DPO/distillation, pick a model, or run experiments from Pi. Canonical methodology lives in Tinker Cookbook — do not reinvent it here.
Explicit command-style skill for implementing approved SDD tasks from tasks.md with tight scope, tests, and verification evidence. Use only when the user explicitly asks to execute or implement a specific approved SDD task or feature. Do not auto-load for discussion, planning, review, or unapproved tasks.
Explicit command-style skill for initializing or adopting SDD in a project by creating or preparing .ai/, .ai/steering/, and .ai/sdd/. Use only when the user explicitly asks to initialize, set up, adopt, or bootstrap SDD. Do not auto-load for general planning, feature specs, status checks, or implementation.
Explicit command-style skill for inspecting .ai/sdd state and recommending the next safe action. Use only when the user explicitly asks for SDD status, progress, blockers, readiness, or next action. Do not auto-load for general SDD work; do not create specs or implement code.