- Rewrites may no longer invent facts, names, dates, or citations that
aren't in the source text; specificity must come from the source or
the user. Every example that modeled invented specifics is re-cut to
use only source information (fixes#187)
- The audit step now asks whether the rewrite states anything not in
the source, and treats fabrication as a defect
- Replace paragraph-count parity ("five paragraphs in, five out") with
an information-over-shape rule: every claim survives, depth may vary
- A user-provided voice sample now outranks the em dash ban
- Add invocation modes: pasted text (full deliverable), file (rewrite
in place, summary only), embedded (final text only)
- Bump metadata.version, plugin.json, and README history to 2.9.0
Claude-Session: https://claude.ai/code/session_01G5ydgtbqzJtfC5hrvC5SSA
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Pattern #19 showed curly quotes in both the Before and After columns.
The After should use straight quotes, matching the source-of-truth
SKILL.md example, since converting curly to straight quotes is the
whole point of the pattern.
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Add three style/cadence patterns from the remaining PRs: manufactured punchlines, aphorism formulas, and conversational rhetorical openers. Extend the chatbot artifact rule to catch offer-to-continue closers. Keep the additions narrow with false-positive guardrails for legitimate emphatic sentences and ordinary casual words.
Update README and AGENTS.md to reflect 33 total patterns.
- §14: turn em-dash "overuse" into a hard cut (no em or en dashes in the
final rewrite), with a replacement ladder and a final scan. Idea from #96.
- §21: expand to cover speculative gap-filling ("maintains a low profile,"
"keeps personal details private") where a model invents filler instead of
saying a source is missing. Idea from #111.
- New pattern #30, diff-anchored writing: describe the thing as it is, not as
a narration of what changed. Idea from #81.
Hand-ported lean versions rather than merging the source PRs. 30 patterns
total; README and AGENTS.md updated to match.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Consolidate the workflow that was stated three times (Your Task / Process /
Output Format) into one principles block plus a single "Process and Output"
section. Gate PERSONALITY AND SOUL to content where voice is wanted, so the
skill stops pushing opinions/first-person onto encyclopedic and technical
text (which contradicted "preserve meaning"). Drop the "LLM Idiolects"
subsection (forensic model-fingerprinting, off-goal and ages badly) and
trim the worked example's change list. No change to the 29 patterns.
SKILL.md 613 -> 565 lines, zero detection capability removed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Drop the Warp-specific guidance file in favor of AGENTS.md (read by Claude
Code, Codex, Warp, and others). Trim the duplicated install commands and
correct the stale pattern count (was "25", now 29). Keep the maintenance
contract: SKILL.md is source of truth, keep README/version/pattern-count in
sync, stable numbering.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The original rule said to strip hyphens from compound modifiers
uniformly. That produces ungrammatical English in attributive position:
"a high quality report" is wrong; "a high-quality report" is correct.
The actual AI tell is uniform hyphenation INCLUDING in predicate
position ("the report is high-quality"). Humans typically hyphenate
attributive use only and drop the hyphen when the compound follows
the noun.
Reworded the Problem statement to spell out the attributive-vs-
predicate distinction. Reworked the Before/After so the same compound
modifiers appear in both positions, demonstrating that only the
predicate-position hyphens get dropped.
Most of this skill tells the editor what to remove. This adds the
inverse — what to leave alone, and how to decide.
Sourced from Wikipedia: Signs of AI writing (revision fetched
2026-05-01), specifically the "Ineffective indicators", "Signs of
human writing", and "Differences between LLMs" sections.
Three subsections, no new patterns:
- "What NOT to flag (false positives)" — the indicators that look
AI-coded but are actually neutral (perfect grammar, em dashes
alone, curly quotes alone, formal vocabulary, common transition
words). The over-editing risk is real: if the skill is applied
too aggressively, it strips legitimate prose. Closes with the
"clusters matter, isolated signs don't" rule.
- "Signs of human writing (preserve these)" — positive markers
that should be left untouched: specific detail, mixed feelings,
era-bound references, sentence-length variation, parenthetical
self-corrections, and the November 30, 2022 cutoff for ruling
out AI involvement entirely.
- "LLM Idiolects" — quick triage notes per model family
(ChatGPT/Grok verbose with artifacts; Gemini/Claude concise, no
curly quotes by default). Tendencies, not rules.
No pattern-count change. No README changes (the README's pattern
table is unaffected since this section is meta-guidance, not new
patterns). No version bump.
Add step 4 (Never truncate) to the Your Task checklist so the
humanizer preserves the full length of the original text instead
of condensing it. Also add spaced em dash and double-hyphen
examples to Pattern 14 so all common dash variants get caught.
- Add license and compatibility fields to SKILL.md frontmatter so the
skill is explicitly marked as compatible with both claude-code and opencode
- Update README with OpenCode installation instructions covering both the
native ~/.config/opencode/skills/ path and the claude-compatible path
- Clarify that a single clone into ~/.claude/skills/ works for both tools
since OpenCode scans that path for compatibility
WARP.md still referenced "24 patterns" but pattern #25 (hyphenated
word pair overuse) was added in v2.3.0. The README heading already
says "25 Patterns Detected", so this brings WARP.md in sync.
Add optional Voice Calibration section to SKILL.md. When users provide
a sample of their own writing, the skill analyzes their sentence rhythm,
word choices, and quirks before rewriting - producing output that sounds
like them instead of generic clean human.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
A skill that removes AI writing signs should not itself exhibit them.
ChatGPT puts --- before every headline; this removes all 28 instances.
Frontmatter delimiters are preserved. No content changes.
Fixes#35
Add pattern #25 to detect AI-style uniform hyphenation of common
word pairs (cross-functional, data-driven, client-facing, etc.).
Bump version to 2.3.0.
Fixes#42
Rewrote the README and SKILL full example so the 'Before' deliberately
incorporates all 24 signs of AI writing and the 'After' carefully avoids
every one while keeping similar length and essay form.
Co-Authored-By: Warp <agent@warp.dev>
Update README to recommend cloning directly into ~/.claude/skills/humanizer and provide a copy-only SKILL.md option. Add WARP.md with repo-specific guidance for Warp.
Co-Authored-By: Warp <agent@warp.dev>
Avoiding AI patterns is only half the job - sterile, voiceless writing is just as obvious as slop.
This adds guidance on:
- Signs of soulless writing (uniform sentences, no opinions, reads like Wikipedia)
- Having actual opinions and reactions
- Varying rhythm
- Acknowledging mixed feelings
- Using first person when appropriate
- Letting some mess in
- Being specific about feelings
Includes before/after examples showing the difference between clean-but-soulless and writing that actually has a pulse.
- Added concrete before/after examples for all 24 patterns in SKILL.md
- Updated README with GitHub installation instructions (clone, one-liner, manual)
- Added summary table of all patterns with brief before/after examples
- Included annotated full example showing which patterns were fixed
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Updated skill with comprehensive patterns from Wikipedia's "Signs of AI
writing" article (fetched directly via curl with Chrome user agent).
Now includes 24 pattern categories organized into:
- Content patterns (significance inflation, -ing analyses, promotional language)
- Language patterns (AI vocabulary, copula avoidance, rule of three)
- Style patterns (em dashes, boldface, title case)
- Communication patterns (chatbot artifacts, disclaimers)
- Filler and hedging patterns
Each pattern includes words to watch, examples from Wikipedia, and fix guidance.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
A skill that removes signs of AI-generated writing from text based on
Wikipedia's "Signs of AI writing" guide. Detects and fixes patterns like
inflated symbolism, promotional language, em dash overuse, rule of three,
and superficial -ing endings.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Wesley Dickens