voice-editor

undefined

</output_format>

<editing_modes>
<mode name="light">
**Use when:** Content is close to voice, just needs polish

**Passes:** 3, 5, 6 (Slop Removal, Rhythm, Final Check)
**Expected edit:** 10-20%
**Time:** 5-10 minutes per 500 words
</mode>

<mode name="standard">
**Use when:** Typical AI output with style guide

**Passes:** All 6
**Expected edit:** 30-40%
**Time:** 15-20 minutes per 500 words
</mode>

<mode name="heavy">
**Use when:** Generic AI output, no style guide used in generation

**Passes:** All 6, possibly multiple iterations
**Expected edit:** 50-70%
**Time:** 25-35 minutes per 500 words

**Consider:** Might be faster to rewrite with better prompts
</mode>

<mode name="rescue">
**Use when:** Content is fundamentally off but has good bones

**Approach:**
1. Extract the core ideas/structure only
2. Rewrite from scratch using voice profile
3. Incorporate any specific facts/examples from original
4. Run standard editing passes on new draft

**This is not editing—it's salvage.**
</mode>
</editing_modes>

<common_problems>
<problem name="too_formal">
**Symptom:** Reads like a corporate memo
**Cause:** AI defaulting to academic/business training data
**Fix:**
- Replace "individuals" → "people"
- Replace "utilize" → "use"
- Replace "implement" → "do/start"
- Add contractions
- Shorten sentences
- Add conversational asides
</problem>

<problem name="too_uniform">
**Symptom:** Every sentence same length, monotonous rhythm
**Cause:** AI optimizing for "clarity" = brevity
**Fix:**
- Vary deliberately: 5-word punch, then 25-word exploration
- Combine related short sentences
- Break long sentences at natural pauses
- Add one-sentence paragraphs for emphasis
</problem>

<problem name="too_hedged">
**Symptom:** Everything qualified, no strong positions
**Cause:** AI avoiding incorrect claims
**Fix:**
- Delete: "it might be argued," "generally speaking," "in some cases"
- Make direct claims you can support
- Replace "might" with "will" where confident
- Add "in my experience" instead of vague hedging
</problem>

<problem name="too_balanced">
**Symptom:** Every section same length, all points equal weight
**Cause:** AI doesn't have opinions/priorities
**Fix:**
- Expand important points, shrink minor ones
- Cut sections that don't earn their space
- Lead with strongest material
- Let structure reflect actual priorities
</problem>

<problem name="voice_drift">
**Symptom:** Starts strong, becomes generic by end
**Cause:** AI loses context over long pieces
**Fix:**
- Edit in 500-word chunks
- Re-inject voice markers every few paragraphs
- Add "personality refreshers" (asides, opinions, humor)
- Check last third especially carefully
</problem>
</common_problems>

<integration_with_other_skills>
**Before voice-editor:**
- Run `slop-detector` for initial assessment
- Ensure `voice-analyzer` has created VOICE.md
- Run `craft-rules` for structural quality audit

**After voice-editor:**
- Run `slop-detector` again to verify cleanup
- Update VOICE.md with new patterns discovered

**Full Workflow:**

**What each skill checks:**
| Skill | Focus | Example Issue |
|-------|-------|---------------|
| slop-detector | AI patterns | "delve," "landscape," "game-changer" |
| craft-rules | Writing mechanics | Weak hook, passive voice, abstract adjectives |
| voice-editor | Personal voice | Too formal, missing characteristic phrases |

**Quick workflow (already clean content):**

**Heavy workflow (generic AI output):**

</integration_with_other_skills>

<success_criteria>
Editing is complete when:
- [ ] All 6 passes have been applied (or appropriate subset for mode)
- [ ] No Tier 1 slop phrases remain
- [ ] Sentence length varies naturally
- [ ] Content matches VOICE.md characteristics
- [ ] Read-aloud test passes (no stumbling)
- [ ] The authenticity question is answered "yes"
- [ ] Edit summary documents all changes
- [ ] VOICE.md update suggestions provided if patterns discovered

**The ultimate test:** Would someone who knows the author recognize this as theirs before seeing the name?
</success_criteria>

<core_principle>
The style guide gives AI direction—it helps produce output closer to your voice than generic defaults. Your editing gives the work your actual voice—the quirks, opinions, personality, and rough edges that make it distinctively yours.

This is why "zero effort" AI fails. The promise of finished content without touching it misunderstands what makes writing valuable. Effort isn't the enemy. Wasted effort is.

You're redirecting effort from blank-page generation to voice-preservation editing. That redirection is the entire point.
</core_principle>