architecture-investigation

Plugin architecture-investigation from marketplace architecture-harness in GROOVIZ/aqzsedrf2. Commands read from the repo's manifest — 1 month ago.

Skills (10)

• grill-the-investigation

  Relentlessly interview the user about an architecture investigation until scope, drivers, methodology, and deliverables are 100% concrete. MUST use AskUserQuestion for every question, multiple-choice only, with a recommended answer. Minimum six questions. Ends with explicit user confirmation. Use wh

• head-of-architecture-review

  Final senior-architect review of a completed investigation. Reads the brief, the plan, the synthesis, a sample of per-item outputs, and the trace log; returns a written review that an engineering leader would sign — or send back. Use as the closing skill of an investigation, after `synthesize-invest

• peer-review-brief

  Audit a freshly-written Investigation Brief for gaps, ambiguity, and weak definitions, then close every gap — by re-reading the grilling, re-reading the codebase, or grilling the user again via AskUserQuestion. Iterates until the brief is solid. Invoked by the `/architecture-investigation:investigat

• peer-review-plan

  Audit a freshly-written investigation plan for gaps — vague verifications, missing schema rows, underweight phases, single-option strategies — then close every gap by re-reading the brief, re-reading the codebase, or grilling the user again via AskUserQuestion. Iterates until the plan is solid. Invo

• peer-review-step

  Peer-review a verified plan-step output from an engineering-judgment perspective. Reads the step's output, considers what an experienced architect would push back on, and returns improvement suggestions. Use after `verify-step` passes, before moving to the next step.

• run-investigation-plan

  Execute an APPROVED investigation plan literally — including batched per-item work — using the plan's declared per-item output schema. Refuses to run without `findings/<id>/plan.md` carrying `status: approved`. After every step, runs `verify-step` (correctness) and `peer-review-step` (engineering ju

• synthesize-investigation

  Roll up per-item findings and strategy options across an entire investigation into a coherent recommendation document. Reads the plan's per-item schema to know which files to consult. Use after `run-investigation-plan` finishes Phase C (cross-item synthesis) and before the head-of-architecture revie

• verify-step

  Check that a just-completed plan step is grounded, complete against the plan's per-item schema, and free of hallucination. Reads the step's output and the citations it makes, opens the cited files, and confirms the claims hold against the real codebase. Returns a verdict and a list of fixable issues

• write-investigation-brief

  Produce a one-page Investigation Brief from a CONFIRMED grilling session. Refuses to run without `findings/<id>/grilling.md` carrying `status: confirmed`. The brief is what the user reviews and signs off on before the plan is written.

• write-investigation-plan

  Turn an APPROVED Investigation Brief into a step-by-step plan a junior architect could execute without further guidance. Refuses to run without `findings/<id>/brief.md` carrying `status: approved`. The plan must declare its own per-item output schema derived from the brief and a falsifiable verifica

Slash commands (1)

• /architecture-investigation:investigate

  Run an architecture investigation end-to-end through the eight harness skills. Enforces two hard stops with explicit user approval via AskUserQuestion. Never skips grilling.

Similar plugins