avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI…
Use when the user names a local file and explicitly asks to clean, rewrite, humanize, or remove AI-writing patterns in that file itself, with minimal targeted edits and post-edit verification.
$ npx -y skills add conorbronsdon/avoid-ai-writing --skill file-edit-in-place --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/file-edit-in-placeContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user names a local file and explicitly asks to clean, rewrite, humanize, or remove AI-writing patterns in that file itself, with minimal targeted edits and post-edit verification.
name: file-edit-in-place description: Use when the user names a local file and explicitly asks to clean, rewrite, humanize, or remove AI-writing patterns in that file itself, with minimal targeted edits and post-edit verification.
Edit a named file according to the original `../avoid-ai-writing/SKILL.md` edit mode and editing contract.
For cross-Skill work, follow `../avoid-ai-writing-router/references/handoff-contract.md` and `../avoid-ai-writing-router/references/skill-graph.json`.
Accept mutation work from:
A detector result never authorizes a write by itself. User mutation intent must already be explicit.
Before mutation, preserve:
Set `execution_evidence.mutation: executed` only after a real host write/patch succeeds.
Apply the `agency-senior-developer` lens encoded in `../avoid-ai-writing-router/references/agency-role-lenses.md`:
Do not claim a file was edited because a patch was merely proposed.
If the named file contains an image/video prompt, storyboard, shot description, or creative brief that describes people, preserve identity-sensitive details using the `agency-inclusive-visuals-specialist` lens.
Treat cultural, geographic, age, disability, attire, skin-tone/lighting, physical-reality, and anti-stereotype constraints as protected semantics. Narrow editing must not flatten or erase them.
1. Capture or retain the original content needed for comparison. 2. Reuse incoming detector findings when available instead of repeating an executed audit without reason. 3. Otherwise audit candidate matches in the relevant text and apply context exceptions and pass conditions before treating them as findings. 4. Change only justified findings within the authorized scope. Do not broadly rewrite clean paragraphs. 5. Do not rewrite quoted material, code blocks, tables, attributed passages, or other protected regions defined by the canonical Skill unless the user specifically requests edits to that protected content and the change will preserve data and attribution. 6. Preserve frontmatter, links, numbers, units, paths, technical identifiers, document structure, meaning, negation, conditions, causality, uncertainty, and conditional representation constraints except for explicit user-authorized corrections or transformations. Never invent facts, stance, confidence, or experience. 7. Prefer a focused patch or edit operation over replacing the whole file. 8. Re-read the modified region after editing. 9. Record actual mutation evidence. 10. Count the initial file mutation as editing pass 1. A later corrective change or preservation repair uses the next pass from the same requested limit. 11. Hand before/after material to `preservation-verifier` when possible and relevant. 12. Report what changed and what was deliberately left untouched.
When entered from `preservation-verifier` after a `FAIL`:
1. Check the shared editing-pass state. If `pass.index` has reached `pass.max`, do not repair; report the unresolved failure. 2. Use the verifier's blocking errors as the repair scope. 3. Revert or correct only the affected spans. 4. Do not broaden the edit into a new rewrite pass. 5. Write the focused repair as the next editing pass. 6. Return to `preservation-verifier` once. 7. If the second verification still fails, stop and report the unresolved preservation error.
Stop when no justified in-scope edit remains, the requested pass limit is reached, or a verification failure cannot be repaired within that limit. Do not mutate additional files or expand scope without user authorization.
Report the file actually changed, the focused edits made, editing passes used, mutation execution status, what was intentionally preserved, and preservation verification status when it ran. Do not dump a full duplicate of the file. If no edit was justified, leave the file unchanged and report zero editing passes.
Audit & rewrite content to remove AI writing patterns. A practical skill for any AI agent. Supports detect-only and edit-in-place modes, plus voice profiles.
Repo: conorbronsdon/avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI…
Use when the user asks to detect, scan, audit, score, or flag AI-writing patterns without rewriting the text, including requests for a deterministic local…
Use when a request combines AI-writing audit, rewrite, file editing, voice preservation, false-positive interpretation, verification, or when the user invokes…
Use when a user asks what AI-writing flags mean, whether detector output proves AI authorship, or wants a careful interpretation of possible false positives,…
Use when the user provides an original and rewritten version, asks whether a rewrite preserved protected content, or wants a deterministic check for code,…
Use when the user asks to rewrite, humanize, clean up, or remove AI-isms from text while preserving the writer's voice, facts, intent, structure, register, and…