claude-skills/commands/code-to-prd.md
Claude a088c8ba77
fix: phantom-path sweep — 888 unresolvable references to zero
A directory reorg added a skills/ path segment; hundreds of references never
followed. This sweep repoints every path-like reference in SKILL.md, agents,
commands, orchestration, and templates to verified on-disk targets:

- 30 root commands + 19 root agents: missing skills/ segment inserted
- 7 c-level persona agents: 17 hallucinated reference filenames substituted
  with the real files (e.g. okr_execution.md -> process_frameworks.md)
- 5 research skills: phantom scripts/office/validate.py step replaced with a
  runnable stdlib zip-integrity check
- email agents: skills frontmatter corrected to productivity/email
- orchestration/ORCHESTRATION.md + templates: stale paths fixed;
  agent-template now requires trigger phrasing in descriptions (root cause)
- 76 more files across engineering, c-level-advisor, compliance-os,
  research-ops, ra-qm, marketing, productivity; dual-publish pairs mirrored
- dead refs dropped/replaced where no target ever existed (REGISTRY.md,
  trend_analyzer.py, cursor-microinteractions.md)

New: scripts/check_paths.py linter (CI gate G1) + narrow allowlist for
teaching examples. Verified: 540 files scanned, 0 unresolvable.

https://claude.ai/code/session_019AJddAL1NADWMXsy1qNPQF
2026-06-10 14:33:00 +00:00

78 lines
2.6 KiB
Markdown

---
name: code-to-prd
description: Reverse-engineer a frontend codebase into a PRD. Usage: /code-to-prd [path]
---
# /code-to-prd
Reverse-engineer a frontend codebase into a complete Product Requirements Document.
## Usage
```bash
/code-to-prd # Analyze current project
/code-to-prd ./src # Analyze specific directory
/code-to-prd /path/to/project # Analyze external project
```
## What It Does
1. **Scan** — Run `codebase_analyzer.py` to detect framework, routes, APIs, enums, and project structure
2. **Scaffold** — Run `prd_scaffolder.py` to create `prd/` directory with README.md, per-page stubs, and appendix files
3. **Analyze** — Walk through each page following the Phase 2 workflow: fields, interactions, API dependencies, page relationships
4. **Generate** — Produce the final PRD with all pages, enum dictionary, API inventory, and page relationship map
## Steps
### Step 1: Analyze
Determine the project path (default: current directory). Run the frontend analyzer:
```bash
python3 {skill_path}/scripts/codebase_analyzer.py {project_path} -o .code-to-prd-analysis.json
```
Display a summary of findings: framework, page count, API count, enum count.
### Step 2: Scaffold
Generate the PRD directory skeleton:
```bash
python3 {skill_path}/scripts/prd_scaffolder.py .code-to-prd-analysis.json -o prd/
```
### Step 3: Fill
For each page in the inventory, follow the SKILL.md Phase 2 workflow:
- Read the page's component files
- Document fields, interactions, API dependencies, page relationships
- Fill in the corresponding `prd/pages/` stub
Work in batches of 3-5 pages for large projects (>15 pages). Ask the user to confirm after each batch.
### Step 4: Finalize
Complete the appendix files:
- `prd/appendix/enum-dictionary.md` — all enums and status codes found
- `prd/appendix/api-inventory.md` — consolidated API reference
- `prd/appendix/page-relationships.md` — navigation and data coupling map
Clean up the temporary analysis file:
```bash
rm .code-to-prd-analysis.json
```
## Output
A `prd/` directory containing:
- `README.md` — system overview, module map, page inventory
- `pages/*.md` — one file per page with fields, interactions, APIs
- `appendix/*.md` — enum dictionary, API inventory, page relationships
## Skill Reference
- `product-team/code-to-prd/skills/code-to-prd/SKILL.md`
- `product-team/code-to-prd/skills/code-to-prd/scripts/codebase_analyzer.py`
- `product-team/code-to-prd/skills/code-to-prd/scripts/prd_scaffolder.py`
- `product-team/code-to-prd/skills/code-to-prd/references/prd-quality-checklist.md`