---
description: Use this workflow when doing **pre-implementation research, defect investigations with uncertain repros, or clarifying system architecture and behaviors**.
alwaysApply: false
---
```json
{
  "coaching_level": "light",
  "socratic_max_questions": 2,
  "verbosity": "concise",
  "timebox_minutes": null,
  "format_enforcement": "strict"
}
```

# Research & Diagnostic Workflow (R&D)

## Purpose

Provide a **repeatable, evidence-first** workflow to investigate features and
defects **before coding**. Outputs are concise reports, hypotheses, and next
steps—**not** code changes.

## When to Use

- Pre-implementation research for new features
- Defect investigations (repros uncertain, user-specific failures)
- Architecture/behavior clarifications (e.g., auth flows, merges, migrations)

---

## Output Contract (strict)

1) **Objective** — 1–2 lines
2) **System Map (if helpful)** — short diagram or bullet flow (≤8 bullets)
3) **Findings (Evidence-linked)** — bullets; each with file/function refs
4) **Hypotheses & Failure Modes** — short list, each testable
5) **Corrections** — explicit deltas from earlier assumptions (if any)
6) **Diagnostics** — what to check next (logs, DB, env, repro steps)
7) **Risks & Scope** — what could break; affected components
8) **Decision/Next Steps** — what we’ll do, who’s involved, by when
9) **References** — code paths, ADRs, docs
10) **Competence & Collaboration Hooks** — brief, skimmable

> Keep total length lean. Prefer links and bullets over prose.

---

## Quickstart Template

Copy/paste and fill:

```md
# Investigation — <short title>

## Objective
<one or two lines>

## System Map
- <module> → <function> → <downstream>
- <data path> → <db table> → <api>

## Findings (Evidence)
- <claim> — evidence: `src/path/file.ts:function` (lines X–Y); log snippet/trace id
- <claim> — evidence: `...`

## Hypotheses & Failure Modes
- H1: <hypothesis>; would fail when <condition>
- H2: <hypothesis>; watch for <signal>

## Corrections
- Updated: <old statement> → <new statement with evidence>

## Diagnostics (Next Checks)
- [ ] Repro on <platform/version>
- [ ] Inspect <table/store> for <record>
- [ ] Capture <log/trace>

## Risks & Scope
- Impacted: <areas/components>; Data: <tables/keys>; Users: <segments>

## Decision / Next Steps
- Owner: <name>; By: <date> (YYYY-MM-DD)
- Action: <spike/bugfix/ADR>; Exit criteria: <binary checks>

## References
- `src/...`
- ADR: `docs/adr/xxxx-yy-zz-something.md`
- Design: `docs/...`

## Competence Hooks
- Why this works: <≤3 bullets>
- Common pitfalls: <≤3 bullets>
- Next skill: <≤1 item>
- Teach-back: "<one question>"
```

---

## Evidence Quality Bar

- **Cite the source** (file:func, line range if possible).
- **Prefer primary evidence** (code, logs) over inference.
- **Disambiguate platform** (Web/Capacitor/Electron) and **state** (migration, auth).
- **Note uncertainty** explicitly.

---

## Collaboration Hooks

- **Syncs:** 10–15m with QA/Security/Platform owners for high-risk areas.
- **ADR:** Record major decisions; link here.
- **Review:** Share repro + diagnostics checklist in PR/issue.

---

## Self-Check (model, before responding)

- [ ] Output matches the **Output Contract** sections.
- [ ] Each claim has **evidence** or **uncertainty** is flagged.
- [ ] Hypotheses are testable; diagnostics are actionable.
- [ ] Competence + collaboration hooks present (≤120 words total).
- [ ] Respect toggles; keep it concise.

---

## Optional Globs (examples)

> Uncomment `globs` in the header if you want auto-attach behavior.

- `src/platforms/**`, `src/services/**` — attach during service/feature investigations
- `docs/adr/**` — attach when editing ADRs

## Referenced Files

- Consider including templates as context: `@adr_template.md`, `@investigation_report_example.md`