prd-to-goal

prd-to-goal — PRD → /goal Decomposition

Converts a PRD / issue / spec into a single copy-pasteable /goal line. The hard part of /goal is not running it — it is writing an until clause that is convergent (terminates), falsifiable (testable boolean), and observable (the agent can actually check it without subjective judgement). This skill makes that decomposition reproducible.

1. When to use

Use it when:

• You have a written PRD, GitHub issue, or spec and want to run /goal against it.
• Past /goal runs drifted, looped, or burned tokens because the until clause was vague (until tests pass, until done, until design is good).
• You need to justify the abort budget — turns, tokens, no-progress threshold.

Skip it when:

• One-shot bug fix where the failing test is the acceptance criterion. Just run /goal until pnpm test -- auth.spec.ts passes.
• No written PRD exists. Run write-prd first — vibes do not decompose.
• The work is destructive or irreversible (DB migrations, mass file deletes). /goal retries; you do not want retries on DROP TABLE.

2. Inputs the skill accepts

Input	How
Pasted PRD text	Provide as the argument, or paste into the chat after invoking.
GitHub issue	gh issue view <N> --json title,body,labels — the skill reads body.
Spec file	Path to a Markdown / text file; the skill Reads it.
ADR / design doc	Same as spec file.

3. The decomposition algorithm

1. Extract acceptance criteria. Pull every MUST, SHOULD, Definition of Done, Acceptance Criteria, and checkbox-style line. If the doc has none, stop and tell the user to run write-prd first — there is nothing to converge on.
2. Map each criterion to an observable boolean. Each criterion must reduce to a single shell-checkable assertion. Examples of observable state:
   • test -f path/to/file (file exists)
   • pnpm test -- pattern passes (test command exits 0)
   • gh pr view <N> --json state | jq -r .state == "MERGED"
   • wc -l < src/auth.ts returns a number within bound
   • pnpm lint exits 0
   • curl -sf $URL returns 2xx
3. Reject non-observable criteria. Drop or rewrite criteria that depend on subjective judgement (code is clean, design feels right, users are happy). Either find a proxy (lint exits 0, Lighthouse score > 90, NPS survey ID exists) or surface the criterion back to the user as out of scope for /goal.
4. Compose the until clause. AND-join the observable assertions in priority order — the cheapest, most likely-to-fail check first so the loop short-circuits early. Three to five assertions is the sweet spot; more than seven usually means the PRD is two PRDs.
5. Fold the budget INTO the same condition. Claude Code accepts one goal per session, replace-on-set, and the bound is written inside that single condition (…, or stop after 15 turns). It is not a second command. Sensible turn caps:
   • 15 for a single feature, 30 for a refactor, 5 for a bug fix.