Not in the top 1,000 by GitHub stars

seyedehsanhadi/sloptrim

A local detector for AI-writing patterns. Scores every prose file your agent saves. Python standard library only, no network, no model.

Claude Code Cursor Engineering Writing

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

9b3e2efe6ab6 → 9b3e2efe6ab6

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 9b3e2efe6ab6

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 9b3e2efe6ab64d9b60c214ad1213b2b30bbddb27

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/seyedehsanhadi/sloptrim.git .hotskills/seyedehsanhadi-sloptrim && git -C .hotskills/seyedehsanhadi-sloptrim checkout --detach 9b3e2efe6ab64d9b60c214ad1213b2b30bbddb27
# Copy each selected skill directory from .hotskills/seyedehsanhadi-sloptrim into .claude/skills/<skill-name>/

Version-pinned installation · Cursor

git clone --filter=blob:none --no-checkout https://github.com/seyedehsanhadi/sloptrim.git .hotskills/seyedehsanhadi-sloptrim && git -C .hotskills/seyedehsanhadi-sloptrim checkout --detach 9b3e2efe6ab64d9b60c214ad1213b2b30bbddb27
# Copy each selected skill directory from .hotskills/seyedehsanhadi-sloptrim into .cursor/skills/<skill-name>/

417GitHub stars

6stars in 7 days

1skill in this repository

6commits in 30 days

Heat

6.6

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

sloptrim /

How it works

sloptrim

When your agent uses it

Use when the user wants to humanize text, trim slop, de-AI or de-slop writing, remove AI tells, fix robotic or ChatGPT-sounding prose, or make writing sound human and natural. Also run before delivering a CV, cover letter, email, report, or essay to be sent. Removes 71 documented AI-writing patterns with a local detector, preserves numbers, names and citations, and rebuilds toward a human voice rather than a flat husk. Mode-aware, so it never fabricates voice on factual content.

What it loads into context

Frontmatter

177 tokens

Always available to the agent

SKILL.md

4,835 tokens

When the skill is activated

Reference documents

17,855 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Silence
Style, chosen silently
Task
Style profiles
Matching the user's own voice
Content type and voice
Critical content preservation
Pattern index
Deterministic detection
Positive style patterns
Reference

Scripts executed separately

hooks/sloptrim-activate.js
hooks/sloptrim-guard.js
hooks/sloptrim-lib.js
hooks/sloptrim-stats.js
hooks/sloptrim-statusline.ps1
hooks/sloptrim-subagent.js
hooks/sloptrim-tracker.js
record/anim.py
record/session_capture.py
scripts/benchmark_frontier.py
scripts/check_docs.py
scripts/detect.py
tests/conftest.py
tests/interp.js
tests/test_benchmark_frontier.py
tests/test_catalogue.py
tests/test_claims_hold.py
tests/test_contract_reach.py
tests/test_corpus.py
tests/test_coverage.py
tests/test_decisive_floors.py
tests/test_detect.py
tests/test_hooks.sh
tests/test_hooks_suite.py
tests/test_no_network.py
tests/test_office.py
tests/test_output_reach.py
tests/test_protected_prose.py
tests/test_reach.py
tests/test_regressions.py
tests/test_skill.py
tests/test_watermark.py
tests/validation_corpus.py

Files

.claude-plugin/marketplace.jsonasset1,060 bytes
.claude-plugin/plugin.jsonasset2,166 bytes
.cursor/rules/sloptrim.mdcasset3,333 bytes
.gitattributesasset45 bytes
.github/workflows/test.ymlasset1,374 bytes
.gitignoreasset303 bytes
CHANGELOG.mddoc7,602 bytes
CITATION.cffasset1,300 bytes
CONTRIBUTING.mddoc4,143 bytes
ETHICS.mddoc2,326 bytes
LICENSE.txtdoc11,347 bytes
NOTICEasset5,595 bytes
README.mddoc9,581 bytes
SECURITY.mddoc2,090 bytes
SKILL.mdcore21,029 bytes
SKILL.mdcore21,029 bytes
SKILL.mdcore21,029 bytes
SKILL.mdcore21,029 bytes
SKILL.mdcore21,029 bytes
SKILL.mdcore21,029 bytes
SKILL.mdcore21,029 bytes
assets/demo-dark.svgasset59,265 bytes
assets/demo-light.svgasset59,265 bytes
assets/detection-dark.svgasset2,772 bytes
assets/detection-light.svgasset2,772 bytes
assets/sloptrim-logo-dark.svgasset47,301 bytes
assets/sloptrim-logo.svgasset47,302 bytes
assets/social-preview.pngasset189,282 bytes
docs/research/frontier-benchmark-results.jsonasset942 bytes
hooks/sloptrim-activate.jsruns2,027 bytes
hooks/sloptrim-guard.jsruns7,222 bytes
hooks/sloptrim-lib.jsruns12,473 bytes
hooks/sloptrim-stats.jsruns3,452 bytes
hooks/sloptrim-statusline.ps1runs964 bytes
hooks/sloptrim-subagent.jsruns1,382 bytes
hooks/sloptrim-tracker.jsruns11,102 bytes
install/sloptrim-command.mddoc206 bytes
record/anim.pyruns17,885 bytes
record/draft.mddoc626 bytes
record/rewrite.mddoc486 bytes
record/session.jsonasset8,770 bytes
record/session_capture.pyruns6,641 bytes
references/patterns.mddoc50,218 bytes
scripts/benchmark_frontier.pyruns6,142 bytes
scripts/check_docs.pyruns33,756 bytes
scripts/detect.pyruns98,512 bytes
tests/conftest.pyruns49 bytes
tests/interp.jsruns1,967 bytes
tests/test_benchmark_frontier.pyruns3,451 bytes
tests/test_catalogue.pyruns5,307 bytes
tests/test_claims_hold.pyruns4,025 bytes
tests/test_contract_reach.pyruns1,827 bytes
tests/test_corpus.pyruns201 bytes
tests/test_coverage.pyruns8,246 bytes
tests/test_decisive_floors.pyruns2,554 bytes
tests/test_detect.pyruns34,713 bytes
tests/test_hooks.shruns18,689 bytes
tests/test_hooks_suite.pyruns1,877 bytes
tests/test_no_network.pyruns2,488 bytes
tests/test_office.pyruns7,307 bytes
tests/test_output_reach.pyruns7,553 bytes
tests/test_protected_prose.pyruns4,309 bytes
tests/test_reach.pyruns2,898 bytes
tests/test_regressions.pyruns7,255 bytes
tests/test_skill.pyruns6,288 bytes
tests/test_watermark.pyruns6,614 bytes
tests/validation_corpus.pyruns6,487 bytes

Read SKILL.md


# Sloptrim

Trims AI slop from text. Works a catalogue of 71 patterns: 62 machine-checked by `scripts/detect.py`, 9 requiring semantic judgment during the rewrite. Of the 62, 50 can move the score; the rest are reported as writing advice and count for nothing. Mode-aware so it does not invent voice on factual content. Preserves facts. Rebuilds the cleaned text toward a selectable human-voice **style profile** so it does not read as a sterile de-AI'd husk.

## Silence

This skill never talks about itself. It hands back the cleaned text and nothing else.

**Never emit:** any announcement that sloptrim ran, style/mode lines, scores or reports, drafts, self-audit notes, facts-preserved lines, change lists, preambles, closing offers.

**Emit only:**
- Text given inline: the final text. Nothing before it, nothing after it.
- A file path given: rewrite the file in place, then one line - the path. Nothing else.
- Fired as a pre-delivery pass on something you were already writing (CV, cover letter, email, report, essay): just deliver the clean text. Do not mention that a pass happened.

View the complete source on GitHub

Skills included

sloptrim

Repository facts

License: Apache-2.0
Created: Aug 13, 2026
Last pushed: Oct 22, 2026
Forks: 30
Open issues: 0
Project activity: Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 16 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
assets/demo-dark.svg:2 Analysis incomplete: physical or joined line exceeds character limit
assets/demo-dark.svg:1 Analysis incomplete: physical or joined line exceeds character limit
assets/demo-light.svg:2 Analysis incomplete: physical or joined line exceeds character limit
assets/demo-light.svg:1 Analysis incomplete: physical or joined line exceeds character limit
assets/sloptrim-logo-dark.svg:4 Analysis incomplete: physical or joined line exceeds character limit
assets/sloptrim-logo-dark.svg:2 Analysis incomplete: physical or joined line exceeds character limit
assets/sloptrim-logo-dark.svg:3 Analysis incomplete: physical or joined line exceeds character limit
assets/sloptrim-logo.svg:4 Analysis incomplete: physical or joined line exceeds character limit
assets/sloptrim-logo.svg:2 Analysis incomplete: physical or joined line exceeds character limit
assets/sloptrim-logo.svg:3 Analysis incomplete: physical or joined line exceeds character limit

1 broad permissionin 1 file: SKILL.md:1
1 dangerous shell commandin 1 file: tests/test_detect.py:477
89 network referencesin 26 files: README.md:15 tests/test_detect.py:133 CHANGELOG.md:3 and 23 more
18 obfuscation signalsin 6 files: tests/test_watermark.py:36 tests/test_detect.py:455 references/patterns.md:614 and 3 more
No instruction overrides
33 executable scriptsin 33 files: hooks/sloptrim-activate.js:1 hooks/sloptrim-guard.js:1 hooks/sloptrim-lib.js:1 and 30 more
11 references to secretsin 7 files: scripts/check_docs.py:21 tests/test_coverage.py:55 tests/test_regressions.py:26 and 4 more
No requests to vote in Hot

Show all 153 signals by file

`.claude-plugin/marketplace.json`

Network accessline 3

"owner": {     "name": "Seyed Ehsan Hadi",     "url": "https://github.com/seyedehsanhadi"

Network accessline 4

"name": "Seyed Ehsan Hadi",     "url": "https://github.com/seyedehsanhadi"   },

Network accessline 5

"url": "https://github.com/seyedehsanhadi"

`.claude-plugin/plugin.json`

Network accessline 5

"author": {     "name": "Seyed Ehsan Hadi",     "url": "https://github.com/seyedehsanhadi"

Network accessline 6

"name": "Seyed Ehsan Hadi",     "url": "https://github.com/seyedehsanhadi"   },

Network accessline 7

"url": "https://github.com/seyedehsanhadi"

Network accessline 8

},   "homepage": "https://github.com/seyedehsanhadi/sloptrim",   "license": "Apache-2.0",

Network accessline 9

"homepage": "https://github.com/seyedehsanhadi/sloptrim",

`.gitignore`

Access to secretsline 20
```
[Credential-related source omitted]
```

`CHANGELOG.md`

Network accessline 3

Format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).

Network accessline 125

[0.9.6]: https://github.com/seyedehsanhadi/sloptrim/releases/tag/v0.9.6

Network accessline 126

[0.9.5]: https://github.com/seyedehsanhadi/sloptrim/releases/tag/v0.9.5

Network accessline 127

[0.9.4]: https://github.com/seyedehsanhadi/sloptrim/releases/tag/v0.9.4

Network accessline 128

[0.9.3]: https://github.com/seyedehsanhadi/sloptrim/releases/tag/v0.9.3

Network accessline 129

[0.9.2]: https://github.com/seyedehsanhadi/sloptrim/releases/tag/v0.9.2

Network accessline 130

[0.9.1]: https://github.com/seyedehsanhadi/sloptrim/releases/tag/v0.9.1

Network accessline 131

[0.9.0]: https://github.com/seyedehsanhadi/sloptrim/releases/tag/v0.9.0

`CITATION.cff`

Network accessline 6

- family-names: Hadi     given-names: Seyed Ehsan repository-code: "https://github.com/seyedehsanhadi/sloptrim"

Network accessline 7

given-names: Seyed Ehsan repository-code: "https://github.com/seyedehsanhadi/sloptrim" license: Apache-2.0

Network accessline 8

repository-code: "https://github.com/seyedehsanhadi/sloptrim"

`LICENSE.txt`

Network accessline 2

Apache License                            Version 2.0, January 2004                         http://www.apache.org/licenses/

Network accessline 4
```
http://www.apache.org/licenses/
```

Network accessline 196

http://www.apache.org/licenses/LICENSE-2.0

`NOTICE`

Network accessline 14

Archivo, version 2.001, subset to the glyphs the wordmark uses   Copyright 2020 The Archivo Project Authors (https://github.com/Omnibus-Type/Archivo)

Network accessline 15

Copyright 2020 The Archivo Project Authors (https://github.com/Omnibus-Type/Archivo)

Network accessline 17
```
http://scripts.sil.org/OFL
```

Network accessline 34

Copyright 2020 The Archivo Project Authors (https://github.com/Omnibus-Type/Archivo)

Network accessline 36

This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: http://scripts.sil.org/OFL

Network accessline 38
```
http://scripts.sil.org/OFL
```

`README.md`

Network accessline 15

[![test](https://github.com/seyedehsanhadi/sloptrim/actions/workflows/test.yml/badge.svg)](https://github.com/seyedehsanhadi/sloptrim/actions/workflows/test.yml)

Network accessline 16

[![Version](https://img.shields.io/badge/version-0.9.6-blue)](CHANGELOG.md)

Network accessline 17

[![License](https://img.shields.io/badge/license-Apache--2.0-blue)](LICENSE.txt)

Network accessline 18

[![Dependencies](https://img.shields.io/badge/dependencies-none-blue)](scripts/detect.py)

Network accessline 19

[![Tests](https://img.shields.io/badge/tests-283-blue)](tests/)

Network accessline 20

[![Python](https://img.shields.io/badge/python-3.9%2B-blue)](scripts/detect.py)

Network accessline 45

Install the sloptrim plugin from https://github.com/seyedehsanhadi/sloptrim

Network accessline 61

git clone https://github.com/seyedehsanhadi/sloptrim.git ~/.claude/skills/sloptrim

Network accessline 111

Sloptrim's public matched benchmark uses five separate 30-human/30-machine arms from the [Human Detectors](https://github.com/jenna-russell/human_detectors)

Network accessline 112

from the [Human Detectors](https://github.com/jenna-russell/human_detectors)

Network accessline 135

git clone https://github.com/jenna-russell/human_detectors.git

Network accessline 170

[Privacyassay](https://privacyassay.com) measures what a website can read from your

Network accessline 171

browser and scores how much of it your browser hides. Same idea applied to a different surface: run the check locally, upload nothing, report what the evidence supports and no more. Source at [seyedehsanhadi/privacyassay](https://github.com

Network accessline 173

no more. Source at [seyedehsanhadi/privacyassay](https://github.com/seyedehsanhadi/privacyassay).

`SECURITY.md`

Network accessline 5

Report privately through [GitHub's advisory form](https://github.com/seyedehsanhadi/sloptrim/security/advisories/new). Please do not open a public issue for a vulnerability.

`SKILL.md`

Broad permissionsline 1
```
Read, Write, Edit, Grep, Glob, Bash
```

`assets/demo-dark.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 800 583" width="800" height="583" role="img" aria-label="A recorded session. The contract arrives at session start, again on the prompt, and again inside a subagent. A saved file scores 4

`assets/demo-light.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 800 583" width="800" height="583" role="img" aria-label="A recorded session. The contract arrives at session start, again on the prompt, and again inside a subagent. A saved file scores 4

`assets/detection-dark.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 756 330" width="756" height="330" role="img" aria-label="Public matched benchmark ROC-AUC. GPT-4o 0.943, Claude 3.5 Sonnet 0.842, o1-pro 0.877, paraphrased GPT-4o 0.832, humanized o1-pro

`assets/detection-light.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 756 330" width="756" height="330" role="img" aria-label="Public matched benchmark ROC-AUC. GPT-4o 0.943, Claude 3.5 Sonnet 0.842, o1-pro 0.877, paraphrased GPT-4o 0.832, humanized o1-pro

`assets/sloptrim-logo-dark.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 358 90" width="358" height="90" role="img" aria-label="sloptrim">

`assets/sloptrim-logo.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 358 90" width="358" height="90" role="img" aria-label="sloptrim">

`docs/research/frontier-benchmark-results.json`

Network accessline 1

{   "dataset_source": "https://github.com/jenna-russell/human_detectors",

Network accessline 2

"dataset_source": "https://github.com/jenna-russell/human_detectors",

`hooks/sloptrim-activate.js`

Executable scriptline 1
```
#!/usr/bin/env node
```

`hooks/sloptrim-guard.js`

Executable scriptline 1
```
#!/usr/bin/env node
```

`hooks/sloptrim-lib.js`

Executable scriptline 1
```
Executable file
```

`hooks/sloptrim-stats.js`

Executable scriptline 1
```
#!/usr/bin/env node
```

`hooks/sloptrim-statusline.ps1`

Executable scriptline 1
```
Executable file
```

`hooks/sloptrim-subagent.js`

Executable scriptline 1
```
#!/usr/bin/env node
```

`hooks/sloptrim-tracker.js`

Executable scriptline 1
```
#!/usr/bin/env node
```

`record/anim.py`

Executable scriptline 1
```
Executable file
```

Network accessline 325

o = ['<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 %d %.0f" width="%d" '

`record/session_capture.py`

Executable scriptline 1
```
Executable file
```

Network accessline 37

W = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"

Access to secretsline 77
```
[Credential-related source omitted]
```

`references/patterns.md`

Possible obfuscationline 614

**Before:** The re<U+200B>port is ready. The invisible character inside the word came from a paste.

Network accessline 648

**Before:** See the full guide at https://example.com/guide?utm_source=chatgpt.com for details.

Network accessline 650

**After:** See the full guide at https://example.com/guide for details.

`scripts/benchmark_frontier.py`

Executable scriptline 1
```
Executable file
```

`scripts/check_docs.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 21
```
[Credential-related source omitted]
```
Access to secretsline 178
```
[Credential-related source omitted]
```
Access to secretsline 233
```
[Credential-related source omitted]
```

`scripts/detect.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Possible obfuscationline 694

_INWORD_ZERO_WIDTH = re.compile(r"(?<=[A-Za-z])[<U+200B><U+200C><U+200D><U+2060><U+FEFF>]+(?=[A-Za-z])")

Network accessline 2202

w = "{http://schemas.openxmlformats.org/wordprocessingml/2006/main}"

`tests/conftest.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 3
```
[Credential-related source omitted]
```

`tests/interp.js`

Executable scriptline 1
```
Executable file
```

`tests/test_benchmark_frontier.py`

Executable scriptline 1
```
Executable file
```

`tests/test_catalogue.py`

Executable scriptline 1
```
Executable file
```

`tests/test_claims_hold.py`

Executable scriptline 1
```
Executable file
```

Network accessline 17

def epub(path, body, decl='xmlns="http://www.w3.org/1999/xhtml"'):

Possible obfuscationline 59

past_the_window = "word " * 200000 + "<U+200B><U+200B><U+200B>"

`tests/test_contract_reach.py`

Executable scriptline 1
```
Executable file
```

`tests/test_corpus.py`

Executable scriptline 1
```
Executable file
```

`tests/test_coverage.py`

Executable scriptline 1
```
Executable file
```

Network accessline 36

W = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"

Access to secretsline 55
```
[Credential-related source omitted]
```
Access to secretsline 91
```
[Credential-related source omitted]
```

`tests/test_decisive_floors.py`

Executable scriptline 1
```
Executable file
```

Network accessline 48

for text in (             "Great question! " + HUMAN,             HUMAN + " See https://example.com/p?utm_source=chatgpt.com for detail.",

Network accessline 49

"Great question! " + HUMAN,             HUMAN + " See https://example.com/p?utm_source=chatgpt.com for detail.",     ):

Network accessline 50

HUMAN + " See https://example.com/p?utm_source=chatgpt.com for detail.",

Network accessline 56

metrics = detector().scan(         "Please see the report [Your Name] here: "         "https://example.com?utm_source=chatgpt.com citeturn0search0"

Network accessline 57

"Please see the report [Your Name] here: "         "https://example.com?utm_source=chatgpt.com citeturn0search0"     )["_metrics"]

Network accessline 58

"https://example.com?utm_source=chatgpt.com citeturn0search0"

`tests/test_detect.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 133

PLACEHOLDER_SAMPLE = "Reach out to [Your Name] at [INSERT EMAIL] before the demo." REF_MARKUP_SAMPLE = "Revenue rose oai_citation last year and citeturn0search2 confirms it." UTM_SAMPLE = "Full writeup at https://example.com/post?utm_source

Network accessline 134

REF_MARKUP_SAMPLE = "Revenue rose oai_citation last year and citeturn0search2 confirms it." UTM_SAMPLE = "Full writeup at https://example.com/post?utm_source=chatgpt.com today." UTM_TRAILING_PERIOD = "Read the rest at https://x.com/a?utm_so

Network accessline 135

UTM_SAMPLE = "Full writeup at https://example.com/post?utm_source=chatgpt.com today."

Network accessline 136

UTM_TRAILING_PERIOD = "Read the rest at https://x.com/a?utm_source=chatgpt.com."

Network accessline 137

UTM_DIFF_DOMAIN = "Visit https://x.com/a?utm_source=chatgpt.com.au for the AU site."

Possible obfuscationline 455

family = "\U0001f468<U+200D>\U0001f469<U+200D>\U0001f467<U+200D>\U0001f466"

Possible obfuscationline 466

if run_clean("Clean prose.<U+200B>\U000e0041") != "Clean prose.":

Dangerous shell operationline 477
```
rm = run_detect(REF_MARKUP_SAMPLE)
```

Network accessline 598

leaky = ("Please see the report [Your Name] here: "              "https://example.com?utm_source=chatgpt.com citeturn0search0")

Network accessline 599

"https://example.com?utm_source=chatgpt.com citeturn0search0")

Network accessline 665

if "63_placeholder_text" in run_detect(             "Use [RAID](https://github.com/liamdugan/raid), licensed [MIT][1]."):

Network accessline 666

"Use [RAID](https://github.com/liamdugan/raid), licensed [MIT][1]."):

`tests/test_hooks.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

`tests/test_hooks_suite.py`

Executable scriptline 1
```
Executable file
```

`tests/test_no_network.py`

Executable scriptline 1
```
Executable file
```

Network accessline 63

for sample in ("import urllib.request", "const r = await fetch(url)",

Network accessline 64

"Invoke-WebRequest -Uri $u", "curl -sSL https://example.com",

`tests/test_office.py`

Executable scriptline 1
```
Executable file
```

Network accessline 20

W = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"

Network accessline 21

A = "http://schemas.openxmlformats.org/drawingml/2006/main"

Network accessline 22

P = "http://schemas.openxmlformats.org/spreadsheetml/2006/main"

Network accessline 93

z.writestr(             "chapter.xhtml",             '<?xml version="1.0"?><html xmlns="http://www.w3.org/1999/xhtml">'

Network accessline 94

"chapter.xhtml",             '<?xml version="1.0"?><html xmlns="http://www.w3.org/1999/xhtml">'             "<body>%s</body></html>" % body,

Network accessline 95

'<?xml version="1.0"?><html xmlns="http://www.w3.org/1999/xhtml">'

`tests/test_output_reach.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 33
```
[Credential-related source omitted]
```

Network accessline 119

assert '1_ai_vocabulary' in detect.scan(r'\$10. ' + SLOP,syntax='latex')     assert '1_ai_vocabulary' in detect.scan(r'$$x\\$$ ' + SLOP,syntax='latex')     assert '1_ai_vocabulary' in detect.scan(r'\href{https://example.org}{'+SLOP+'}',synt

Network accessline 121

assert '1_ai_vocabulary' in detect.scan(r'\href{https://example.org}{'+SLOP+'}',syntax='latex')

Network accessline 128

def test_docx_marked_code_is_excluded_without_mutating_the_document(tmp_path, properties):     p=tmp_path/'code.docx'     xml=('<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'

Network accessline 129

p=tmp_path/'code.docx'     xml=('<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'          '<w:body><w:p>'+properties+'<w:t>'+escape(SLOP)+' a\u200bb</w:t></w:r></w:p>'

Network accessline 130

xml=('<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'

Network accessline 142

def test_docx_monospace_manuscript_is_still_readable(tmp_path):     p=tmp_path/'manuscript.docx'     xml=('<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'

Network accessline 143

p=tmp_path/'manuscript.docx'     xml=('<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'          '<w:body><w:p><w:r><w:rPr><w:rFonts w:ascii="Courier New"/></w:rPr>'

Network accessline 144

xml=('<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'

`tests/test_protected_prose.py`

Executable scriptline 1
```
Executable file
```

`tests/test_reach.py`

Executable scriptline 1
```
Executable file
```

`tests/test_regressions.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 26
```
[Credential-related source omitted]
```
Access to secretsline 140
```
[Credential-related source omitted]
```

`tests/test_skill.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`tests/test_watermark.py`

Executable scriptline 1
```
Executable file
```

Possible obfuscationline 36

("zero-width space in English", "The pump<U+200B>moves 40 litres."),

Possible obfuscationline 37

("zero-width non-joiner between Latin letters", "The pum<U+200C>p moves."),

Possible obfuscationline 38

("zero-width joiner between Latin letters", "The pum<U+200D>p moves."),

Possible obfuscationline 39

("word joiner", "The pump<U+2060>moves 40 litres."),

Possible obfuscationline 40

("byte-order mark mid-text", "The pump<U+FEFF>moves 40 litres."),

Possible obfuscationline 41

("left-to-right mark with no RTL", "The pump<U+200E>moves 40 litres."),

Possible obfuscationline 44

("variation selector with no glyph base", "Report ready<U+FE00> for review."),

Possible obfuscationline 49

("interlinear annotation", "The pump<U+FFF9>moves<U+FFFA>40<U+FFFB> litres."),

Possible obfuscationline 58

("emoji joined family", "We shipped \U0001f468<U+200D>\U0001f469<U+200D>\U0001f467 today."),

Possible obfuscationline 62

("Devanagari joiner", "क्<U+200D>ष in Hindi."),

Possible obfuscationline 64

("Thai zero-width word breaks", "สวัสดี<U+200B>ครับ"),

Possible obfuscationline 69

("soft hyphen inside a word", "Do<U+00AD>nau<U+00AD>dampf<U+00AD>schiff"),

`tests/validation_corpus.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Possible obfuscationline 128

smug = detect(human[:40] + "<U+200B>" + human[40:])["_metrics"]

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 3 facts

Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentionrecord/anim.py:325High confidence
Contacts schemas.openxmlformats.org, which SKILL.md, the README and the plugin manifest do not mentionrecord/session_capture.py:37High confidence
Contacts schemas.openxmlformats.org, which SKILL.md, the README and the plugin manifest do not mentionscripts/detect.py:2202High confidence

Hidden characters: 5 facts

Joiner U+200C outside an emoji or a script that needs it, in codescripts/detect.py:694High confidence
Joiner U+200D outside an emoji or a script that needs it, in codetests/test_detect.py:455High confidence
Joiner U+200C outside an emoji or a script that needs it, in codetests/test_watermark.py:37High confidence
Joiner U+200D outside an emoji or a script that needs it, in codetests/test_watermark.py:38High confidence
Joiner U+200D outside an emoji or a script that needs it, in codetests/test_watermark.py:58High confidence

Signal confidence: 127 facts

Network access in prose of documentationCHANGELOG.md:3Low confidence
Network access in prose of documentationCHANGELOG.md:125Low confidence
Network access in prose of documentationCHANGELOG.md:126Low confidence
Network access in prose of documentationCHANGELOG.md:127Low confidence
Network access in prose of documentationCHANGELOG.md:128Low confidence
Network access in prose of documentationCHANGELOG.md:129Low confidence
Network access in prose of documentationCHANGELOG.md:130Low confidence
Network access in prose of documentationCHANGELOG.md:131Low confidence
Network access in prose of documentationLICENSE.txt:2Low confidence
Network access in prose of documentationLICENSE.txt:4Low confidence
Network access in prose of documentationLICENSE.txt:196Low confidence
Network access in prose of documentationREADME.md:15Low confidence
Network access in prose of documentationREADME.md:16Low confidence
Network access in prose of documentationREADME.md:17Low confidence
Network access in prose of documentationREADME.md:18Low confidence
Network access in prose of documentationREADME.md:19Low confidence
Network access in prose of documentationREADME.md:20Low confidence
Network access in code of documentationREADME.md:45Low confidence
Network access in code of documentationREADME.md:61Low confidence
Network access in prose of documentationREADME.md:111Low confidence
Network access in prose of documentationREADME.md:112Low confidence
Network access in code of documentationREADME.md:135Low confidence
Network access in prose of documentationREADME.md:170Low confidence
Network access in prose of documentationREADME.md:171Low confidence
Network access in prose of documentationREADME.md:173Low confidence
Network access in prose of documentationSECURITY.md:5Low confidence
Broad permissions in the frontmatter of the SKILL.mdSKILL.md:1High confidence
Executable script in code of a file that runshooks/sloptrim-activate.js:1High confidence
Executable script in code of a file that runshooks/sloptrim-guard.js:1High confidence
Executable script in a comment of a file that runshooks/sloptrim-lib.js:1Low confidence
Executable script in code of a file that runshooks/sloptrim-stats.js:1High confidence
Executable script in a comment of a file that runshooks/sloptrim-statusline.ps1:1Low confidence
Executable script in code of a file that runshooks/sloptrim-subagent.js:1High confidence
Executable script in code of a file that runshooks/sloptrim-tracker.js:1High confidence
Executable script in prose of a file that runsrecord/anim.py:1Low confidence
Network access in code of a file that runsrecord/anim.py:325High confidence
Executable script in prose of a file that runsrecord/session_capture.py:1Low confidence
Network access in code of a file that runsrecord/session_capture.py:37High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuerecord/session_capture.py:77Low confidence
Possible obfuscation in prose of documentationreferences/patterns.md:614Low confidence
Network access in prose of documentationreferences/patterns.md:648Low confidence
Network access in prose of documentationreferences/patterns.md:650Low confidence
Executable script in prose of a file that runsscripts/benchmark_frontier.py:1Low confidence
Executable script in prose of a file that runsscripts/check_docs.py:1Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/check_docs.py:21Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/check_docs.py:178Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/check_docs.py:233Low confidence
Executable script in code of a file that runsscripts/detect.py:1High confidence
Possible obfuscation in code of a file that runsscripts/detect.py:694High confidence
Network access in code of a file that runsscripts/detect.py:2202High confidence

and 77 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Manifest .claude-plugin/marketplace.json	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Native	Path .cursor/rules/sloptrim.mdc	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

seyedehsanhadi/sloptrim

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

sloptrim

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

.claude-plugin/marketplace.json

.claude-plugin/plugin.json

.gitignore

CHANGELOG.md

CITATION.cff

LICENSE.txt

NOTICE

README.md

SECURITY.md

SKILL.md

assets/demo-dark.svg

assets/demo-light.svg

assets/detection-dark.svg

assets/detection-light.svg

assets/sloptrim-logo-dark.svg

assets/sloptrim-logo.svg

docs/research/frontier-benchmark-results.json

hooks/sloptrim-activate.js

hooks/sloptrim-guard.js

hooks/sloptrim-lib.js

hooks/sloptrim-stats.js

hooks/sloptrim-statusline.ps1

hooks/sloptrim-subagent.js

hooks/sloptrim-tracker.js

record/anim.py

record/session_capture.py

references/patterns.md

scripts/benchmark_frontier.py

scripts/check_docs.py

scripts/detect.py

tests/conftest.py

tests/interp.js

tests/test_benchmark_frontier.py

tests/test_catalogue.py

tests/test_claims_hold.py

tests/test_contract_reach.py

tests/test_corpus.py

tests/test_coverage.py

tests/test_decisive_floors.py

tests/test_detect.py

tests/test_hooks.sh

tests/test_hooks_suite.py

tests/test_no_network.py

tests/test_office.py

tests/test_output_reach.py

tests/test_protected_prose.py

tests/test_reach.py

tests/test_regressions.py

tests/test_skill.py

tests/test_watermark.py

tests/validation_corpus.py

How the signals fit together

Works with

You might also use

DietrichGebert/ponytail

tzachbon/smart-ralph

gregkozakiewicz/roast-my-design-system

arslanrakh/write-human

KKKKhazix/khazix-skills

NVIDIA/skills

`SKILL.md`

`.claude-plugin/marketplace.json`

`.claude-plugin/plugin.json`

`.gitignore`

`CHANGELOG.md`

`CITATION.cff`

`LICENSE.txt`

`NOTICE`

`README.md`

`SECURITY.md`

`SKILL.md`

`assets/demo-dark.svg`

`assets/demo-light.svg`

`assets/detection-dark.svg`

`assets/detection-light.svg`

`assets/sloptrim-logo-dark.svg`

`assets/sloptrim-logo.svg`

`docs/research/frontier-benchmark-results.json`

`hooks/sloptrim-activate.js`

`hooks/sloptrim-guard.js`

`hooks/sloptrim-lib.js`

`hooks/sloptrim-stats.js`

`hooks/sloptrim-statusline.ps1`

`hooks/sloptrim-subagent.js`

`hooks/sloptrim-tracker.js`

`record/anim.py`

`record/session_capture.py`

`references/patterns.md`

`scripts/benchmark_frontier.py`

`scripts/check_docs.py`

`scripts/detect.py`

`tests/conftest.py`

`tests/interp.js`

`tests/test_benchmark_frontier.py`

`tests/test_catalogue.py`

`tests/test_claims_hold.py`

`tests/test_contract_reach.py`

`tests/test_corpus.py`

`tests/test_coverage.py`

`tests/test_decisive_floors.py`

`tests/test_detect.py`

`tests/test_hooks.sh`

`tests/test_hooks_suite.py`

`tests/test_no_network.py`

`tests/test_office.py`

`tests/test_output_reach.py`

`tests/test_protected_prose.py`

`tests/test_reach.py`

`tests/test_regressions.py`

`tests/test_skill.py`

`tests/test_watermark.py`

`tests/validation_corpus.py`