§ reference · skill

annotate-guidance

Documents a project's architecture for AI assistants by writing compact architecture.md files into a .rpiv/guidance/ shadow tree alongside the source.

arguments target-directory

§ 01 · purpose

Purpose

Onboards Claude, Cursor, or any Pi-aware AI agent to a brownfield codebase by emitting a parallel .rpiv/guidance/ tree of small, scannable architecture.md files. The guidance system later injects these on demand when an agent touches the matching directory, so context cost stays proportional to what the agent actually reads.

§ 02 · when to use

When to use it

  • The project should keep CLAUDE.md out of the source tree (shadow-tree layout).
  • You need first-time AI onboarding or want to refresh stale guidance after a refactor.
  • Pick annotate-inline instead if you want CLAUDE.md files next to the code.
  • Pick migrate-to-guidance instead if inline CLAUDE.md files already exist and only need to be moved.

§ 03 · inputs

Inputs

Name Required Source
target-directory no CLI argument or current working directory
existing architecture docs no Any README.md, CLAUDE.md, or architecture.md the user mentions inline
target-directory
Defaults to CWD when omitted.
existing architecture docs
Read fully before agents are dispatched.

§ 04 · outputs

Outputs

Artifact Path Format
Root overview .rpiv/guidance/architecture.md markdown
Per-layer guidance .rpiv/guidance/<sub>/architecture.md markdown
Decomposed sub-layer guidance .rpiv/guidance/<sub>/<child>/architecture.md markdown

§ 05 · key steps

Key steps

  1. Read directly-mentioned files first Why: Locks domain knowledge from existing docs into the main context before any subagent runs, so later passes do not contradict what the team already wrote down.
  2. Pass 1 — map tree and detect architecture in parallel Why: Two locator agents — one tree-mapper, one architecture-sniffer — run side by side so layout discovery costs one round-trip instead of two.
  3. Apply guidance-depth rules; propose targets Why: A two-pass selection (top-level layers, then opt-in decomposition of composite layers) keeps the target list grounded in folder shape rather than guesswork, and is shown to the user for confirmation before any analysis spend.
  4. Pass 2 — analyzer + pattern-finder per target (parallel) Why: One codebase-analyzer answers the "what is this layer for" questions; one codebase-pattern-finder extracts idiomatic code shapes. Running both per target in parallel produces the deepest signal per token.
  5. Developer checkpoint on findings Why: Surfaces deprecated patterns, migrations-in-progress, and cross-layer rules that code reading alone cannot reveal. Asked one question at a time so each answer can steer the next.
  6. Batch-write architecture.md files Why: All files are written in a single emission pass after the checkpoint, so the guidance tree is internally consistent and never left half-populated mid-session.

§ 06 · related skills

downstream researchdesignblueprint