zero-slop 2.8.6 → 2.8.7

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-2.8.6-72528F">
+  <img alt="version" src="https://img.shields.io/badge/version-2.8.7-72528F">
   <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>
@@ -160,6 +160,10 @@ Eight roles form one workflow. Each is a job rather than a service, run as its o
 | 7. Verifier | Local tools and your AI assistant | Compares text with source for facts, meaning, qualifiers, voice, format, structure. |
 | 8. Fresh-eyes finalizer | Fresh AI pass | Reads the verified text as a first-time reader, applying only safe polish. Any final polish restarts the final checks; the same text must return unchanged before release. |
 
+Missed editorial targets trigger repair, not erasure. After three rounds, Zero Slop
+returns the safest source-preserving edit with a warning. Only a model outage or an
+edit that changes protected material leaves the source untouched.
+
 Studies find
 [predictable wording](https://arxiv.org/abs/2301.11305) and
 [overused vocabulary](https://arxiv.org/abs/2406.07016) in machine text, and authorship
@@ -228,13 +232,11 @@ proof of general accuracy.
 
 ### Speed
 
-One busy Apple silicon Mac. Meter: 1,000 documents in 1.9929 seconds (501.8 per
-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
-0.00% higher median throughput—effectively no difference. Editing
-time is excluded.
+One Apple silicon Mac: the meter scored 1,000 documents in 1.9929 seconds
+(501.8 per second), 15,201 words in 0.3223 seconds, and the worst stress case in 2.2932
+seconds. The reading pass handled the same 1,000 in 0.7823 seconds (1278.3/second);
+learning on 8,000 words took 0.1592 seconds. Across 24 interleaved runs against 2.7.7,
+median throughput was 0.26% lower, effectively no difference. Editing is excluded.
 
 ### Reading-pass accuracy
 
@@ -282,7 +284,7 @@ passes, private learning, portfolio analysis, and release tests.
 
 ![Documented capabilities at pinned repository versions](assets/competitor-capabilities.png)
 
-The chart records which features each project documents. It says nothing about writing quality and is not a claim about which tool writes better. Reproduce by using these tests:
+The chart says nothing about writing quality. Reproduce it with:
 
 ```sh
 python3 tests/test_all.py

package/SKILL.md

@@ -2,7 +2,7 @@
 name: zero-slop
 license: MIT
 metadata:
-  version: "2.8.6"
+  version: "2.8.7"
   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.
 ---
@@ -96,8 +96,9 @@ local and AI responsibilities distinct:
    and directly fix stumbles, repetition, weak transitions, and awkward flow.
 7. **Verifier — local tools plus the AI assistant.** Check the exact final text
    against the source for the writing score, facts, meaning, qualifiers, voice,
-   format, and structure. This is a release gate, not advice: a warning blocks
-   delivery. Any repair returns through roles 5 and 6 before role 7 runs again.
+   format, and structure. A warning starts the repair loop and prevents an
+   unqualified approval; it does not erase the edited draft. Any repair returns
+   through roles 5 and 6 before role 7 runs again.
 8. **Fresh-eyes finalizer — a new AI pass.** Read the verified text as a first-time
    reader, apply only safe final polish, and approve it without changes. A role 8
    edit restarts roles 5 through 8; the finalizer never bypasses verification.
@@ -636,16 +637,25 @@ 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.
+
+If an AI editorial role returns no usable text, retry that role once with a fresh pass.
+Use another available model when the harness supports model choice; otherwise use fresh
+context in the current assistant. Carry the last source-preserving edit forward while a
+role recovers. Do not replay earlier roles unless the text changes: retry the failed role,
+then continue with the remaining checks. Keep every retry bounded and report any role
+that remained unavailable.
+
 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
-that explicit three-round fallback, nothing reaches the user until the exact text
-being returned has cleared every final check. A fallback still must have completed the
-copy desk and read-aloud pass; never describe it as fully verified.
+without guessing, return the safest source-preserving edit and state the unresolved
+issue, unavailable role, or missed target plainly. Never replace an explicit rewrite
+request with the unchanged source merely because a quality target was missed. A quality
+target controls the confidence label; it does not decide whether the writer receives
+the work. A fallback should complete both editorial passes whenever they are available,
+and it must never be described as fully verified when a check did not complete.
 
 Initial gate failure → rewrite and recheck (max 3 passes). Final verification
 repair → copy desk, read-aloud pass, and every check again (max 3 rounds). If the
@@ -677,8 +687,8 @@ then rerun the copy desk, read-aloud editor, verifier, and fresh-eyes finalizer
 that order. A role 8 edit therefore restarts roles 5 through 8. Limit the loop to
 three rounds. The same exact text must clear roles 5, 6, and 7 and then receive a
 no-change approval from role 8. If safe approval is impossible without guessing,
-return the best source-preserving version that completed every pass and name the
-unresolved span; do not call it fully verified.
+return the safest source-preserving edit, name the unresolved span or unavailable
+pass, and do not call it fully verified.
 
 ### 9. Report in plain language
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "zero-slop",
-  "version": "2.8.6",
+  "version": "2.8.7",
   "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

@@ -4,7 +4,10 @@ Answer every check with pass or fail. Where a check asks for a count, write the
 number down; a count is evidence, and a missing count means the pass did not run.
 
 Any fail sends the text back through the copy desk and read-aloud pass, after which
-every check here runs again on the new text. Limit that loop to three rounds.
+every check here runs again on the new text. Limit that loop to three rounds. A failed
+check starts repair and changes the confidence label; it never suppresses the edited
+text. After the bounded loop, return the safest source-preserving edit and name every
+unresolved check plainly.
 
 **This file exists because the meter cannot see most of what is on it.** The scorer
 reads the lexically anchored subset: listed phrases, sentence-length variance,

package/references/fresh-eyes.md

@@ -60,5 +60,5 @@ changes even one character, apply the complete revision and rerun, in order:
 
 Repeat for at most three rounds. The same exact text must clear all four roles, with
 the fresh-eyes finalizer approving it unchanged. If the remaining issue cannot be
-fixed without guessing, return the best source-preserving text that completed every
-pass, identify the unresolved span, and do not describe it as fully verified.
+fixed without guessing, return the safest source-preserving edit, identify the
+unresolved span or unavailable pass, and do not describe it as fully verified.