Edit, check, edit

Run on every fresh draft, refresh redline and repurposed set. The full checklists are in ../make-content/references/editing.md.

1. Substance pass. Write four answers into the edit note:

   • the thesis in one arguable sentence;
   • the swap test (pass, or what fails);
   • the fakes removed;
   • whether the CTA matches the intent.

   Run the rest of Pass 1 (so-what, proof density, skeptic, order, hedging) as checks. Fix what fails without writing it up.

2. Claims check: the shared claims gate (the claims-gate skill, ../claims-gate/SKILL.md) for brand claims, plus ../make-content/references/fact-rules.md for world facts, competitor facts, stories, sensitive topics and third-party rights. When the piece is sponsored, affiliate, gifted or a creator collaboration, also load ../ad-policy-check/disclosure.md (in the ad-policy-check skill) and apply it (disclosure in the piece itself, before "more"). It cuts and softens lines, which leaves gaps.

3. Readability pass on the post-cut text: smooth the gaps, headline, lede, H2s as claims, scannability, ending. Then voice match against the best voice sample available, in this order:

   1. the named author's voice card (bylined pieces);
   2. the saved company blog guide brand/voices/blog-<brand-slug>.md for company blog/article work (apply its rules and bans; keep any provisional status);
   3. the kit’s voice example lines;
   4. the brand's own post captions (brand_read organic);
   5. "From the site" lines in product notes;
   6. three lines the human pastes on request.

   If none exist, write "voice unmatched: no real samples" in the note and keep the copy plain rather than guessing at personality.

4. AI-tell check (mechanical) on the final text. Anything the brand's real writing uses stays; with no real samples, everything on the list goes.

Edit note (attached to the piece)