Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01RCcxND1mMWu6Lt2c2PxexN
1.3 KiB
1.3 KiB
Style rules — all LLM-generated depth files
Apply to usecases.md, intake.md, quality.md, evals/ (and later enrichment files). The templates in this folder reference these rules; on conflict the specific template wins.
- English. Occupation titles as in ESCO (
preferredLabel). - Terse and actionable. Short lines, verb-first where possible, no paragraphs longer than 4 lines. The reader is an agent at runtime — every token must earn its place.
- Evidence-based. Market claims cite market.md percentages ("52 % of ads"); task claims trace to tasks.md/skills.md. No numbers from memory: no salaries, fine amounts, legal deadlines unless they come from a file in the package.
- No filler. Banned: "seamless", "powerful", "cutting-edge", "revolutionize", "best-in-class", "leverage synergies", intro sentences that restate the heading.
- Honest scope. LLM agents draft, structure, check and communicate — they do not perform physical acts, sign legal documents or replace licensed judgment (medical, legal, structural). Phrase use cases accordingly ("prepare", "draft", "check against", "brief").
- Privacy. Invented example data only; never real names/employers from job ads; no PII.
- Determinism aids QA. Keep the exact section skeletons from the templates — the QA harness greps for them.