zero-slop 2.8.5 → 2.8.6

package/README.md

@@ -5,7 +5,7 @@
   <img alt="tests" src="https://img.shields.io/badge/tests-passing-227B5B">
   <img alt="dependencies" src="https://img.shields.io/badge/runtime%20dependencies-0-227B5B">
   <img alt="privacy" src="https://img.shields.io/badge/learning-private-227B5B">
-  <img alt="version" src="https://img.shields.io/badge/version-2.8.5-72528F">
+  <img alt="version" src="https://img.shields.io/badge/version-2.8.6-72528F">
   <a href="https://hol.org/guard/plugins"><img alt="Listed in the HOL plugin registry" src="https://img.shields.io/badge/HOL%20registry-listed-2C6E8F"></a>
   <a href="https://github.com/hashgraph-online/awesome-ai-plugins#tools--integrations"><img alt="Listed in awesome-ai-plugins" src="https://img.shields.io/badge/awesome--ai--plugins-listed-2C6E8F"></a>
   <a href="https://zero-slop.ai/try/"><img alt="This README scores 11.6 out of 100 on the slop score, inside the human range" src="https://img.shields.io/badge/slop%20score-11.6%2F100-0f7d55"></a>
@@ -233,7 +233,7 @@ second), 15,201 words in 0.3223 seconds, worst stress case 2.2932 seconds.
 Reading pass: 0.7823 seconds for the same 1,000 (1278.3 per
 second), 0.1092 for the same large document, linear to 96,000 words. Learning
 pass, 8,000 words: 0.1592 seconds. Across 24 interleaved runs against 2.7.7 we measured
-1.29% lower median throughput; that is machine noise, not a speed claim. Editing
+0.00% higher median throughput—effectively no difference. Editing
 time is excluded.
 
 ### Reading-pass accuracy

package/SKILL.md

@@ -2,7 +2,7 @@
 name: zero-slop
 license: MIT
 metadata:
-  version: "2.8.5"
+  version: "2.8.6"
   author: manavmishra
 description: Turn drafts into sharp, natural prose or inspect them without rewriting. Zero Slop runs inside the user's existing AI assistant; Claude, GPT, or another compatible model reads and edits in context while local tools point to exact phrases and protect the source. Use when the user asks to humanize or de-slop writing, inspect AI-sounding patterns, fix text that reads like ChatGPT, polish outward-facing prose, draft social or LinkedIn content, or apply a final quality check to prose the agent generated. The workflow preserves facts, voice, and format and learns privately from repeated, reason-labelled human edits.
 ---
@@ -32,8 +32,13 @@ citations, and the ladder below orders the signals by measured strength.
    number, name, anecdote, or experience — and experiential/interior claims
    count ("by test day it felt familiar", "I was terrified"): if the author
    didn't say it, it's fabrication, even when it would make the piece land
-   better. Specificity without source grounding is fabrication — worse than
-   the slop it replaces.
+   better. Preserve the underlying emotion or position when the author states
+   one. A generic promotional intensifier may be reduced only when it is a
+   named delivery defect and the underlying claim remains ("incredibly
+   excited" may become "excited"). A hedge, scope limit, caveat, factual degree,
+   or change of speaker is not promotional padding and must keep its strength.
+   Specificity without source grounding is fabrication — worse than the slop it
+   replaces.
 2. **Flag hollow spans, don't fill them.** Prose that makes no claim cannot be
    rescued by rewording. Flag it and ask for the missing substance.
 3. **No over-correction.** Trading AI-slop for edgy-slop (forced hot takes,
@@ -631,6 +636,10 @@ If verification requires any textual repair, send the repaired text through the
 desk and final read-aloud pass again, then repeat every final check. Continue until the
 same text clears the copy desk, final read-aloud pass, semantic and format review,
 scorer, and fidelity gate.
+A required repair may raise the writing score from the previous draft as long as it
+stays below the release limit. Source meaning, stated emotion, and factual accuracy
+outrank a smaller number. Never discard a necessary semantic repair merely because an
+unsafe version scored lower; rerun every check on the repaired text instead.
 Limit this repair loop to three rounds. If a problem still cannot be resolved
 without guessing, return the best source-preserving version that completed both
 editorial passes and state the unresolved issue and failed check plainly. Outside

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "zero-slop",
-  "version": "2.8.5",
+  "version": "2.8.6",
   "description": "An Agent Skill that scores AI-sounding prose locally, guides the host AI through an editorial rewrite, and checks changed source details. The local tools run offline with zero dependencies.",
   "bin": {
     "zero-slop": "bin/zero-slop.mjs"

package/references/eval.md

@@ -212,7 +212,9 @@ the report even when they are zero.
 49. **No invented specifics.** No number, name, anecdote, date, or source appeared
     that the author did not supply.
 50. **No invented interior claims.** No stated feeling, motive, or experience the
-    author never wrote.
+    author never wrote. An emotion or position present in the source still appears in
+    the rewrite. Its wording may lose a generic promotional intensifier when the
+    underlying claim remains; it may not disappear or switch speakers.
 51. **Qualifiers survive.** Hedges, scope limits, and caveats carry the same strength
     as the source.
 52. **Claims not reframed.** Same names and numbers can still carry a changed

package/references/fresh-eyes.md

@@ -18,7 +18,9 @@ rewriter to approve its own work.
 - **Reader effort.** A smart first-time reader can follow the argument once through.
   Unpack only a genuine stumble; do not dilute expert language the audience needs.
 - **Voice continuity.** The same person seems to have written the beginning, middle,
-  and end. Restore source-backed warmth or texture lost to over-editing.
+  and end. Restore source-backed warmth or texture lost to over-editing. Restore a
+  source-stated emotion or position that an earlier pass accidentally removed, using
+  plain language rather than reinstating empty promotional padding.
 - **Residual process language.** Remove internal labels, scoring talk, evaluation
   jargon, or comments meant for the editor rather than the reader.
 - **Genre and format.** The text looks and sounds native to its destination. Preserve