From ralph
Generates prd.json task tracking file from PRD.md requirements document. Use when initializing Ralph loop or when the user asks to convert PRD to JSON format for autonomous execution.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ralph:generating-prd-json-from-prd-mdThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Hybrid approach: Python script parses, AI validates and corrects.
Hybrid approach: Python script parses, AI validates and corrects.
python ralph/scripts/generate_prd_json.py --dry-run
Check output for: declared vs parsed story count mismatch, missing stories, empty acceptance/files. If issues found, fix PRD markdown or note for manual correction in step 3.
python ralph/scripts/generate_prd_json.py
Script handles: PRD.md parsing, (depends: ...) extraction, content hashing, state preservation.
Validate (Read tool)
ralph/docs/prd.json (script output)docs/PRD.md (cross-reference)Correct errors (Write tool, if needed)
content_hash if title/description/acceptance changedralph/docs/prd.jsonReport
make ralph_runFor each story, verify:
id follows STORY-XXX formattitle is 3-7 words, matches PRD.md featuredescription is non-emptyacceptance array is non-emptyfiles array contains valid paths (if specified in PRD.md)content_hash is 64-char hex stringdepends_on references valid STORY-XXX IDs (no circular deps, no self-refs)Cross-reference with PRD.md:
#### Feature N: headings have corresponding stories(depends: STORY-XXX) syntax correctly parsed| Issue | Correction |
|---|---|
| Empty acceptance | Extract from description or PRD.md feature |
| Invalid depends_on reference | Remove non-existent story IDs |
| Circular dependency | Remove one direction |
| Missing content_hash | Recompute from title+description+acceptance |
| Duplicate story IDs | Renumber sequentially |
See ralph/docs/templates/prd.json.template for structure and fields.
make ralph_prd_json
make ralph_init # Validate environment
make ralph_run # Start Ralph loop
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub qte77/claude-code-plugins --plugin ralph