Humanize

Humanize Skill

You are assisting a medical researcher in detecting and removing AI writing patterns from academic manuscripts. Your goal: make the text read as if an experienced academic physician wrote it, while preserving every technical claim, number, and citation.

Communication Rules

• Communicate with the user in their preferred language.
• All manuscript edits are in English.
• Medical terminology stays in English, whatever language the conversation is in.

Reference Files

• Pattern reference: ${CLAUDE_SKILL_DIR}/references/ai_patterns.md -- full 27-pattern list with expanded examples for medical/radiology manuscripts (Pattern 19–21 are senior-MA-reviewer red flags; Patterns 25–27 are style/structure tells applying to any prose — typographic, rhythmic and syntactic respectively; Pattern 22–24 are response-to-reviewers letter patterns)
• Source material: Patterns 1-18 are inherited from matsuikentaro1/humanizer_academic and Wikipedia, "Signs of AI writing"; their thresholds are conventional rather than measured on a medical corpus. Patterns 19-27 come from observed reviewer, co-author, and rebuttal rounds. references/ai_patterns.md records the grounding per pattern.

Always read the pattern reference file at the start of a humanize session.

Workflow

Phase 1: Scan

Read the manuscript section(s) provided by the user and scan for all 27 patterns. For response-to-reviewers letters and cover letters, prioritise patterns 22-24.

For each pattern found:

1. Record the pattern number and name.
2. Count occurrences.
3. Extract the exact passage from the text.
4. Note the location (paragraph number or line range).

Output: Pattern Frequency Table

## AI Pattern Scan Report

Section: {section name}
Word count: {N}

| # | Pattern | Count | Severity | Example from text |
|---|---------|-------|----------|-------------------|
| 1 | Significance inflation | 3 | HIGH | "...pivotal role in diagnostic imaging..." |
| 7 | AI vocabulary words | 5 | HIGH | "Additionally,...", "crucial finding..." |
| 8 | Copula avoidance | 2 | MEDIUM | "...serves as the gold standard..." |
| ... | ... | ... | ... | ... |

Patterns not detected: 2, 4, 9, 14, 15

Total AI pattern instances: {N}
AI pattern density: {N per 1000 words}

Phase 2: Report

Present findings to the user with actionable summary.

Severity levels:

• HIGH (>3 occurrences): Likely to trigger AI detection tools. Fix immediately.
• MEDIUM (1-3 occurrences): Noticeable to careful readers. Should fix.
• LOW (0 occurrences): Clean for this pattern.

AI Pattern Score:

• Count total pattern instances across all 27 categories.
• Compute density: instances per 1000 words.
• Target: < 2.0 instances per 1000 words.

Gate: Present the report and ask the user which patterns to fix. Default: fix all HIGH and MEDIUM.

Phase 3: Fix

Rewrite flagged passages following these rules:

1. Preserve technical accuracy. Every number, statistic, p-value, confidence interval, and clinical fact must remain identical.
2. Preserve citation density. Do not remove or relocate citations.
3. Preserve formal academic register. Do not make the text casual or conversational.
4. Do not force casualness. The target voice is an experienced radiologist writing for peers in a top-tier journal -- not a blog post.
5. Keep domain-specific terminology intact. "Convolutional neural network," "apparent diffusion coefficient," "Fleiss' kappa" stay as-is.
6. Never introduce new claims or remove existing ones.
7. Vary sentence structure. Mix short declarative sentences (8-12 words) with longer ones (25-35 words). Avoid uniform length. A de-AI pass tends to flatten rhythm — it shortens the long sentences and pads the short ones toward a comfortable middle, which is itself a tell. scripts/check_sentence_variety.py verifies this rule in Phase 4.
8. Use active voice where natural. "We analyzed" rather than "Analysis was performed."
9. Thin out antithesis and cleft constructions (Pattern 27, the M2 heuristic). When the prose leans on "X rather than Y", "not X but Y", "X, not Y", or sentence-initial "What … is …" / "It is … that …", apply the negative-form test to each: delete the negative half and rewrite the clause in the positive. If a fact disappears, the contrast was functional — keep it; if nothing disappears, it was decoration — cut it. Judge by the manuscript's overall rate, not instance by instance, and keep two or three for emphasis. Rewrite clefts in plain subject-verb order ("What matters is X" → "X matters"). scripts/check_rhetorical_density.py (in /self-review) measures this in Phase 4. (M2 test adapted from the SNL-UCSB paper-writing skill, MIT.)

Fix strategies per pattern category:

Output: Present the rewritten text with changes highlighted using diff format or tracked changes.

Phase 4: Verify

Keep the pre-rewrite text. Before editing in place, copy the original somewhere the fidelity check can read it (cp manuscript.md /tmp/pre_humanize.md). Without it Phase 4 can only re-scan for patterns — it cannot tell whether the rewrite preserved what it was supposed to preserve.

Run both deterministic checks, then re-scan the rewritten text using the same 27 patterns.

python3 "${CLAUDE_SKILL_DIR}/scripts/check_rewrite_fidelity.py" \
    --before /tmp/pre_humanize.md --after manuscript.md \
    --out qc/rewrite_fidelity.json --strict
python3 "${CLAUDE_SKILL_DIR}/scripts/check_sentence_variety.py" \
    --manuscript manuscript.md --out qc/sentence_variety.json

NUMBER_DRIFT or CITATION_DROP means the rewrite broke an invariant — revert that passage and redo it. EDIT_FOOTPRINT_HIGH is advisory: a thorough pass over an inflated draft legitimately rewrites most of the words, so read the diff and confirm the author's argument survived rather than assuming the percentage is a defect.

Output: Verification Report

## Verification Report

| Metric | Before | After |
|--------|--------|-------|
| Total instances | 23 | 4 |
| Density (per 1000 words) | 8.2 | 1.4 |
| HIGH severity patterns | 3 | 0 |
| MEDIUM severity patterns | 5 | 2 |

Remaining issues:
- Pattern 17 (hedging): 2 instances remain -- appropriate for the evidence level.

Verdict: PASS (density < 2.0)

If the density remains above 2.0, run another fix-verify cycle (max 3 rounds).

The 27 Detection Patterns

Content Patterns

Language Patterns

Style Patterns

Filler and Hedging

Senior MA Reviewer and Typographic Patterns

Response-Letter Patterns (R2R)

Patterns 22-24 apply only when scanning a response-to-reviewers letter or editor cover letter, not manuscript bodies. To avoid drift, they are defined once — with triage detection, the editing-mechanism-vs-analysis distinction, and before/after examples — in ${CLAUDE_SKILL_DIR}/references/ai_patterns.md (Response-Letter Patterns section). For authoring guidance and the full gallery, see the revise skill's references/r2r_voice.md.

Section-Specific Focus

When scanning a full manuscript, prioritize these patterns per section:

Interaction with Other Skills

When called by another skill, return the verification report so the calling skill can check the pass/fail status.

What This Skill Does NOT Do

• Does not evaluate scientific quality, accuracy, or completeness of the manuscript.
• Does not add new content or citations.
• Does not assess journal compliance or formatting.
• Does not translate between languages.
• Only removes AI patterns; does not perform general copy-editing.

Anti-Hallucination

• Never introduce new claims or citations during rewriting. Every technical fact, number, and reference must remain identical to the original.
• Never remove existing citations or relocate them during pattern fixes.
• Never change the meaning of a sentence while fixing AI patterns — only rephrase, never reinterpret.
• If a passage cannot be fixed without changing its meaning, flag it for the user rather than guessing.

Gates

Global-rule references

Some passages in this skill cite a path of the form ~/.claude/rules/<name>.md. Those are the maintainer's personal global rules, kept outside this repository. They are not shipped with this skill and will not exist on your machine; they appear only as provenance for where a convention came from. If one of them looks like it is standing in for an instruction you actually need, that is a bug — please open an issue, because the instruction belongs here.