Skip to content
Back to search

anti-slop-kit

MarketplaceWorks with Claude CodeGitHub

A grep gate, a pattern check and a critic loop that make AI-assisted writing read like its author.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/mavrin-xv--anti-slop-kit/badge.svg)](/listings/mavrin-xv--anti-slop-kit)

HTML

<a href="/listings/mavrin-xv--anti-slop-kit"><img src="/api/listings/mavrin-xv--anti-slop-kit/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Everything runs offline on Fernhill Bikes, an invented repair shop.

python3 skills/no-ai-slop/scripts/slop_grep.py examples/fernhill-bikes/draft-sloppy.md
== examples/fernhill-bikes/draft-sloppy.md  [long copy]
  FAIL  banned:3  game-changer  In today's world, riders want a seamless experience — and tubeless
  FAIL  banned:3  seamless  In today's world, riders want a seamless experience — and tubeless tyr
  FAIL  phrases:3  In today's world  In today's world, riders want a seamless experience — and tub
  FAIL  banned:5  robust  It's not just about fewer flats. It's about confidence. When it comes to c
  FAIL  phrases:5  When it comes to  It's not just about fewer flats. It's about confidence. When it
  FAIL  cluster:7  actually, honestly, just  Honestly, the conversion is actually simpler than most
  FAIL  em-dash:0  4 on latin lines, budget 2 (long copy)
  warn  adverbs:5  just  ...
  warn  soft:13  Ultimately  Ultimately, the best tyre is the one that gets you home.
  score 0/100 (214.8 weighted hits per 1,000 words, 128 words)

Exit 1. The same post rewritten in the shop's voice:

== examples/fernhill-bikes/draft-clean.md  [long copy]
  warn  no-source:3  241  Ticket 241: a courier with four flats in a month, all thorns, all on the s
  no hard hits: review the warnings, then read for the patterns
  score 84/100 (5.8 weighted hits per 1,000 words, 173 words)

Exit 0. The warning is a number with no source next to it; here it is the shop's own ticket, so it stays.

python3 skills/voice-extractor/scripts/voice_stats.py examples/fernhill-bikes/samples/*.md --draft examples/fernhill-bikes/draft-sloppy.md
| dashes_per_1k | 0.0-0.0 | 0.0 | 30.3 | DRIFT |
| question_share | 0.0-0.0 | 0.0 | 0.14 | DRIFT |
| first_person_per_100 | 0.8-3.3 | 2.02 | 0.0 | DRIFT |
...
7 drift flags

The clean draft gets 0 drift flags. The detect report, the critic loop run and the voice check for both drafts are in [examples/fernhill-bikes/](examples/fernhill-bikes/).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 15 lines
  1. {
  2. "name": "anti-slop-kit",
  3. "plugins": [
  4. {
  5. "name": "anti-slop-kit",
  6. "source": "./",
  7. "description": "Agent skills that make AI-assisted writing read like its author: a grep gate that exits 1 on banned words, empty phrases, dash overuse and clusters of soft tells, a by-hand pattern check, a five-dimension critic loop with a retry cap, a voice profile from real samples and a drift check against it. Optional Ukrainian and Russian packs.",
  8. "version": "0.1.0"
  9. }
  10. ],
  11. "owner": {
  12. "name": "Artem Mavrin",
  13. "url": "https://github.com/mavrin-xv"
  14. }
  15. }
README.md · README · 162 lines
  1. ![anti-slop-kit](assets/banner.png)
  2. # anti-slop-kit
  3. **Four agent skills that make AI-assisted writing read like the person who signs it: a grep gate that exits 1 on banned words and clusters, a by-hand pattern check for what no script sees, a five-dimension critic loop with a retry cap, and a voice profile your drafts are checked against.**
  4. Drafts written with a model share the same tells: the same twenty words, the same "it's not X, it's Y", a dash in every sentence, a moral at the end. Readers spot them in one line and stop trusting the rest.
  5. [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
  6. ![Works with](https://img.shields.io/badge/works%20with-Claude%20Code%20%7C%20Codex%20%7C%20any%20SKILL.md%20agent-black)
  7. ![Python](https://img.shields.io/badge/scripts-Python%203.8%2B%2C%20stdlib%20only-green)
  8. ![Network](https://img.shields.io/badge/network-none-lightgrey)
  9. ![Example output](assets/example.png)
  10. ```bash
  11. git clone https://github.com/mavrin-xv/anti-slop-kit && cd anti-slop-kit
  12. ./install.sh # or: ./install.sh --project
  13. ```
  14. <!-- install-notes:start -->
  15. Other ways in: as a Claude Code plugin, run `/plugin marketplace add mavrin-xv/anti-slop-kit` and then `/plugin install anti-slop-kit@anti-slop-kit`. For Codex or another agent that reads `SKILL.md`, copy the folders under `skills/` into its skills directory. On Windows, run `install.sh` from Git Bash or WSL and type `py -3` where these docs say `python3`.
  16. <!-- install-notes:end -->
  17. Then tell your agent: `check this draft for slop` or `does this sound like me?` or `score this post before I publish it`
  18. ---
  19. ## What it solves
  20. | Pain | What the pack does |
  21. |---|---|
  22. | The same AI words in every draft | `slop_grep.py` checks a word list, empty phrases and context-aware patterns (a "10x position" in finance is not flagged; a marketing use of the same verb is) and exits 1 on a hard hit |
  23. | Dashes everywhere | A dash budget per format: none in short copy, one per 150 words in long copy, not counted in scripts read aloud |
  24. | One soft word is fine, five in a paragraph is a tell | Adverbs are warnings alone; three different ones in one paragraph are a hard `cluster` hit |
  25. | The text passes the word list and still reads as machine-written | The reading half: 18 named patterns plus four structural tells, and a rule that any three together fail |
  26. | "Is this better or worse than last time?" | A score out of 100 from weighted hits per 1,000 words, where repeats cost more than variety, and `--min-score` as a gate |
  27. | A draft that feels done but is not | `critic-loop`: five dimensions with fixed bars, the lowest fixed line by line, two retries, then a human decides |
  28. | "That does not sound like me" | `voice-extractor` builds a seven-field profile from 5 to 30 samples with quoted evidence; `voice-check` scores six dimensions of drift and quotes each one |
  29. | Rhythm that drifted, but nobody can say how | `voice_stats.py` measures sentence length, spread, fragments, dashes, questions and first person, and flags draft metrics outside the samples' range |
  30. | Ukrainian or Russian copy | Optional packs, loaded automatically for Cyrillic text; the long dash there is grammar and is never counted |
  31. ## What's inside
  32. | Skill | What it does | What to say |
  33. |---|---|---|
  34. | `no-ai-slop` | Detect (name and quote) or edit (minimum rewrite plus What changed); the grep gate, the pattern half, an eval checklist, a copy layer for selling surfaces, UA and RU packs | "check this for slop", "make this sound less like AI", "audit this before it ships" |
  35. | `critic-loop` | Hook, facts, economy, reader path, slop-free; surgical fixes, at most two retries | "score this draft", "critique this post", "tighten this before I publish" |
  36. | `voice-extractor` | Seven fields with evidence and confidence, measured rhythm, a falsifiability test, a three-round test loop with the owner | "capture my writing style", "build a voice profile from these posts" |
  37. | `voice-check` | Six drift dimensions against the profile, measured drift, a slop floor, drift vs evolution, a five-point fingerprint | "does this sound like me", "check the ghostwriter's draft" |
  38. ## Quick start
  39. Everything runs offline on Fernhill Bikes, an invented repair shop.
  40. ```bash
  41. python3 skills/no-ai-slop/scripts/slop_grep.py examples/fernhill-bikes/draft-sloppy.md
  42. ```
  43. ```
  44. == examples/fernhill-bikes/draft-sloppy.md [long copy]
  45. FAIL banned:3 game-changer In today's world, riders want a seamless experience — and tubeless
  46. FAIL banned:3 seamless In today's world, riders want a seamless experience — and tubeless tyr
  47. FAIL phrases:3 In today's world In today's world, riders want a seamless experience — and tub
  48. FAIL banned:5 robust It's not just about fewer flats. It's about confidence. When it comes to c
  49. FAIL phrases:5 When it comes to It's not just about fewer flats. It's about confidence. When it
  50. FAIL cluster:7 actually, honestly, just Honestly, the conversion is actually simpler than most
  51. FAIL em-dash:0 4 on latin lines, budget 2 (long copy)
  52. warn adverbs:5 just ...
  53. warn soft:13 Ultimately Ultimately, the best tyre is the one that gets you home.
  54. score 0/100 (214.8 weighted hits per 1,000 words, 128 words)
  55. ```
  56. Exit 1. The same post rewritten in the shop's voice:
  57. ```
  58. == examples/fernhill-bikes/draft-clean.md [long copy]
  59. warn no-source:3 241 Ticket 241: a courier with four flats in a month, all thorns, all on the s
  60. no hard hits: review the warnings, then read for the patterns
  61. score 84/100 (5.8 weighted hits per 1,000 words, 173 words)
  62. ```
  63. Exit 0. The warning is a number with no source next to it; here it is the shop's own ticket, so it stays.
  64. ```bash
  65. python3 skills/voice-extractor/scripts/voice_stats.py examples/fernhill-bikes/samples/*.md --draft examples/fernhill-bikes/draft-sloppy.md
  66. ```
  67. ```
  68. | dashes_per_1k | 0.0-0.0 | 0.0 | 30.3 | DRIFT |
  69. | question_share | 0.0-0.0 | 0.0 | 0.14 | DRIFT |
  70. | first_person_per_100 | 0.8-3.3 | 2.02 | 0.0 | DRIFT |
  71. ...
  72. 7 drift flags
  73. ```
  74. The clean draft gets 0 drift flags. The detect report, the critic loop run and the voice check for both drafts are in [examples/fernhill-bikes/](examples/fernhill-bikes/).
  75. ## How it works
  76. ```
  77. samples (5-30) --> voice-extractor --> voice-profile.md
  78. |
  79. draft --> no-ai-slop -----------------> critic-loop ------------> voice-check --> ship
  80. 1. slop_grep.py exit 0? 5 dimensions, bars 6 drift dims
  81. 2. pattern half < 3 tells? fix lowest, retry <= 2 voice_stats --draft
  82. 3. edit + eval.md else hand back slop floor exit 0
  83. ```
  84. The script is a floor, not a verdict. It catches the vocabulary and the counting; the reading half catches shape, which is where most of the tells live. Every later skill re-runs the gate, so no score can carry an exit-1 draft through.
  85. ## Configure
  86. | Setting | Where | Default |
  87. |---|---|---|
  88. | Word lists | `skills/no-ai-slop/references/slop-tokens.txt`, `references/packs/*.txt`; one entry per line, `re: ` for a regex | English core; `ua`, `ru` packs |
  89. | Packs | `--pack auto`, `none`, or a list such as `ua` | auto: all packs when 30% of words are Cyrillic |
  90. | Your own list | `--tokens my-list.txt` | the core file |
  91. | Mode | `--mode short`, `long`, `spoken`, `auto` | auto from the file name: `*.spoken.txt` spoken, `slides.md` short, else long |
  92. | Dash budget | `EM_BUDGET` at the top of `slop_grep.py` | short 0, long max(2, words/150), spoken not counted |
  93. | Cluster size | `CLUSTER_AT` in `slop_grep.py` | 3 different soft words in one paragraph |
  94. | Score gate | `--min-score N` | off |
  95. | Critic bars | `skills/critic-loop/SKILL.md` | hook 8 (first line 9), facts 8, economy 8, reader path 3/5 |
  96. | Drift range | `voice_stats.py` | sample min to max, widened by a quarter of the range |
  97. Install without the script: copy the folders in `skills/` to `~/.claude/skills/` (or your agent's skills folder).
  98. ## Honest limits
  99. - The word list catches vocabulary, not authorship. A clean exit means no listed tell, not "a human wrote this". The skills never claim to detect who wrote a text.
  100. - The score is a trend number on one draft over its edits. Do not compare scores across formats or authors.
  101. - The reading half depends on the model reading carefully. It is a checklist, not a detector.
  102. - Word lists age as models change their habits. Expect to add entries; `tests/fixtures/` is where each one gets a test.
  103. - `voice_stats.py` splits sentences with a regex. Abbreviations and odd punctuation shift the counts a little; read drift rows next to the samples.
  104. - The Ukrainian and Russian packs are smaller than the English core and were checked on a few hand-written texts only.
  105. - All example businesses and texts are invented. Tested on Windows with Git Bash and Python 3.12; not tested on macOS or Linux, and `install.sh` was not run end to end.
  106. ## Credits
  107. - Based on / inspired by https://github.com/petergyang/no-ai-slop (MIT): the two jobs, the editing principles, the patterns to cut and the eval checklist, lightly trimmed
  108. - Based on / inspired by https://github.com/boringmarketer/boring-marketing-skills (MIT): the structural tells and the density rule, the seven voice fields and the test loop, the six-dimension drift check, extra word-list entries
  109. - Based on / inspired by https://github.com/eric-tramel/slop-guard (MIT): the density score with exponential decay and the repeat penalty
  110. - Based on / inspired by https://github.com/conorbronsdon/avoid-ai-writing (MIT): severity tiers where soft tells count only in a cluster, and evals that test the checker
  111. - Based on / inspired by https://github.com/blader/humanizer (MIT): strong patterns that fail on one sighting, and the draft, audit, final pass
  112. - Based on / inspired by https://github.com/hardikpandya/stop-slop (MIT): scoring with a pass bar before a draft ships
  113. - Based on / inspired by https://github.com/jdkato/voices (MIT): fixtures that must fire and fixtures that must stay silent
  114. - Based on / inspired by https://github.com/sam-paech/slop-forensics (MIT) and https://github.com/sam-paech/antislop-sampler (Apache-2.0): profiling over-used words against a baseline, the idea behind the fingerprint candidates in `voice_stats.py`
  115. - Based on / inspired by https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing (Wikipedia, CC BY-SA): the catalogue of tells by section; ideas restated, no text copied
  116. ## Contributing
  117. See [CONTRIBUTING.md](CONTRIBUTING.md). Notes for coding agents are in [AGENTS.md](AGENTS.md).
  118. <!-- author:start -->
  119. ## Author
  120. Built and maintained by [Artem Mavrin](https://github.com/mavrin-xv). This repo is one of a set of agent skill packs for marketing and operations work. Each one installs on its own; the full list is in [agent-skill-packs](https://github.com/mavrin-xv/agent-skill-packs). If a pack saved you an afternoon, a star helps other people find it.
  121. <!-- author:end -->
  122. ## License
  123. MIT. See [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.