Agent
Fresh-context quality reviewer — runs deterministic checks and judgment checklist before handoff to /ship-issue.
224 14d ago A 19 tokens
original MIT
Agent
Fresh-context Tidy First assessor — reads the files an upcoming change will touch and proposes preparatory refactorings that make the change easy, landed as separate commits first.
224 14d ago A 33 tokens
original MIT
anthropic
03Skill Claude CodeCodex
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.
224 14d ago A 49 tokens
original MIT
code-design
04Skill Claude CodeCodex
TypeScript conventions, code design principles (SOLID, self-documenting code, file organization), structural design heuristics (dependency width, LoD, output arguments), pnpm rules, ES2024 target, Pi SDK patterns, and Biome/ESLint conflict workarounds. Load during implementation, refactoring, or code review.
224 14d ago A 72 tokens
original MIT
Skill Claude CodeCodex
Review a module's dependency and structural patterns for code smells. Use when adding a parameter to a shared interface, when a dependency bag grows past 5 fields, or when planning a refactoring that touches wiring between layers.
224 14d ago A 47 tokens
original MIT
fallow
06Skill Claude CodeCodex
Codebase intelligence via fallow CLI — dead code, duplication, complexity, refactoring targets. Load when investigating unused code, planning refactors, or reviewing fallow output.
224 14d ago A 38 tokens
original MIT
frontmatter
07Skill Claude CodeCodex
Pi skill frontmatter reference and template. Use when creating or reviewing project skills so they conform to Pi's Agent Skills frontmatter rules, naming constraints, and description requirements.
224 14d ago A 37 tokens
original MIT
Skill Claude CodeCodex
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.
224 14d ago A 47 tokens
original MIT
Skill Claude CodeCodex
Project-specific markdown rules (one-sentence-per-line, compact tables, sequential numbering) and YAML frontmatter schema for plans/retros. Load when writing or editing markdown — contains rules that differ from standard markdownlint defaults.
224 14d ago A 49 tokens
original MIT
mermaid
10Skill Claude CodeCodex
Authoring and reviewing Mermaid diagrams — pitfall categories (semicolons, angle-bracket tokens, quoted headings), renderer verification, and state-machine disambiguation with note blocks. Load when authoring or reviewing Mermaid diagrams in any doc type.
224 14d ago A 52 tokens
original MIT
pi-cli-repro
11Skill Claude CodeCodex
Fast Pi CLI reproduction workflow for this repo. Use when debugging extension behavior through the real pi executable, especially for Anthropic OAuth failures, prompt shaping, request payload inspection, or validating changes without waiting on manual retries.
224 14d ago A 48 tokens
original MIT
Skill Claude CodeCodex
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…
224 14d ago A 70 tokens
original MIT
Skill Claude CodeCodex
Pre-completion protocol for implementation agents — gather context, dispatch the pre-completion-reviewer subagent, and handle its report before writing stage notes and recommending /ship-issue. Load at the end of /tdd-plan and /build-plan after all implementation steps are complete.
224 14d ago A 62 tokens
original MIT
testing
14Skill Claude CodeCodex
Vitest mock patterns (vi.mock, vi.hoisted, vi.fn reset), TDD planning rules, and general test strategy. Load when writing or debugging tests.
224 14d ago A 36 tokens
original MIT
tidy-first
15Skill Claude CodeCodex
Tidy-First protocol for implementation agents — dispatch the tidy-first-assessor subagent over the files an upcoming change will touch, then triage its preparatory-refactor suggestions before implementing. Load at the start of /tdd-plan and /build-plan, after the green baseline is verified.
224 14d ago A 66 tokens
original MIT
Instructions file CodexOpenCode
Instructions for gotgenes/pi-anthropic-auth, covering agents guide: pi-anthropic-auth, project, primary goal, current status and principles.
224 14d ago A 6,534 tokens
original MIT
Agent
Fresh-context craftsmanship scout — reads the largest test files and sweeps method-level design, naming, and test-code quality into a scored debt inventory for phase planning.
184 2d ago A 31 tokens
Agent
Fresh-context quality reviewer — runs deterministic checks and judgment checklist before handoff to /ship-issue.
184 2d ago A 19 tokens
Agent
Fresh-context Tidy First assessor — reads the files a planned change will touch and proposes preparatory refactorings that make the change easy, sequenced as separate commits ahead of the behavior change.
184 2d ago A 38 tokens
code-design
20Skill Claude CodeCodex
TypeScript conventions, code design principles (SOLID, self-documenting code, file organization), structural design heuristics (dependency width, LoD, output arguments), pnpm rules, ES2024 target, Pi SDK patterns, and Biome/ESLint conflict workarounds. Load during implementation, refactoring, or code review.
184 2d ago A 72 tokens
Skill Claude CodeCodex
Review a module's dependency and structural patterns for code smells. Use when adding a parameter to a shared interface, when a dependency bag grows past 5 fields, or when planning a refactoring that touches wiring between layers.
184 2d ago A 47 tokens
fallow
22Skill Claude CodeCodex
Codebase intelligence via fallow CLI — dead code, duplication, complexity, refactoring targets. Load when investigating unused code, planning refactors, or reviewing fallow output.
184 2d ago A 38 tokens
Skill Claude CodeCodex
Heuristics and process for discovering structural improvements in a package. Load when planning a new improvement round — contains the smell taxonomy, analysis workflow, and prioritization framework distilled from 10 phases of pi-subagents refactoring.
184 2d ago A 51 tokens
Skill Claude CodeCodex
Project-specific markdown rules (one-sentence-per-line, compact tables, sequential numbering) and YAML frontmatter schema for plans/retros. Load when writing or editing markdown — contains rules that differ from standard markdownlint defaults.
184 2d ago A 49 tokens