Siqi Chen 4 дней назад
Родитель
Сommit
d7e6dd682a
3 измененных файлов с 5 добавлено и 4 удалено
  1. 1 1
      .claude-plugin/plugin.json
  2. 1 0
      README.md
  3. 3 3
      SKILL.md

+ 1 - 1
.claude-plugin/plugin.json

@@ -2,7 +2,7 @@
   "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
   "name": "humanizer",
   "description": "Rewrite AI-sounding text so it reads naturally without changing what it says.",
-  "version": "2.11.2",
+  "version": "2.11.3",
   "author": {
     "name": "blader",
     "url": "https://github.com/blader"

+ 1 - 0
README.md

@@ -159,6 +159,7 @@ Humanizer follows the sample's rhythm, word choice, punctuation, and deliberate
 <details>
 <summary>Show release notes</summary>
 
+- **2.11.3** - Strengthened the step 3 fact-integrity check to explicitly guard against silent deletion of ranking claims (words such as *most*, *least*, *first*, *only*), superlatives, and simultaneity assertions (words such as *simultaneously*, *at once*, *both*). Patterns §10, §15, and §24 can remove these words while appearing to remove only shape (fixes #212). No change to the 35 patterns.
 - **2.11.2** - Removed the plugin symlink and separate Claude Desktop package. Current Claude Code loads the root `SKILL.md` directly, so GitHub's source ZIP now works in Claude Desktop. No change to the 35 patterns.
 - **2.11.1** - Added a Claude Desktop-ready release package with one regular `humanizer/SKILL.md` file. GitHub's source archive still keeps the plugin symlink (fixes #224). No change to the 35 patterns.
 - **2.11.0** - Rewrote all repo guidance, descriptions, checks, and skill instructions in Plain Language. Kept all 35 patterns and their behavior.

+ 3 - 3
SKILL.md

@@ -7,7 +7,7 @@ description: |
   voice, filler, or chatbot artifacts. Based on Wikipedia's "Signs of AI writing."
 license: MIT
 metadata:
-  version: "2.11.2"
+  version: "2.11.3"
 ---
 
 # Humanizer: remove AI writing patterns
@@ -445,8 +445,8 @@ These details often carry the writer's voice. Keep them unless they hurt the mea
 2. Write a draft. Read it aloud. Check the rhythm, details, simple verbs such as *is* and *has*, and the right level of formality.
 3. Ask two questions:
    - **"What still sounds AI-generated?"**
-   - **"Did the rewrite add or remove any fact, name, number, date, quote, citation, ranking, or other claim?"**
-   Treat any unsupported addition as an error. Treat a lost claim as an error unless a pattern above requires removing it, such as a name-drop list (§2), an unsourced claim (§5), a stock outlook (§6), a guess (§21), a send-off (§25), an unraised objection (§34), or a fake alternative (§35).
+   - **"Did the rewrite add or remove any fact, name, number, date, quote, citation, ranking, or other claim?"** Shape rules such as §10, §15, and §24 can drop a ranking, a superlative, or a claim that things happen at once. Check that those survived.
+   Treat any unsupported addition as an error, and any lost claim unless a pattern above calls for cutting it.
 4. Write the final version. State each point naturally instead of patching one flagged phrase at a time. If a sentence stays awkward, rewrite the paragraph around its main point. Apply the dash rule in §14.
 
 Return the result required by [How to return the result](#how-to-return-the-result).