ai-trace-remover
Skill10 starsChanged 6 days agoMITView on GitHub
Removes template sentences from a manuscript and scores its 0–100 "AI-likeness" with English and Chinese lexicons. It rewrites only matched patterns and always reports what it changed.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/chelate-shell.mdcCursor rule
- 3d-modelerSkill
- bibtex-normalizerSkill
- capstone-labmateSkill
- conflict-detectorSkill
- data-profilerSkill
- document-evolution-trackerSkill
- formula-validatorSkill
- fulltext-extractorSkill
- latex-exporterSkill
- literature-retrieverSkill
- longitudinal-analysisSkill
- ml-auditorSkill
- multi-dim-managerSkill
- quantitative-validatorSkill
- reference-auditorSkill
- sci-visualizerSkill
- security-guardSkill
- task-organizerSkill
- video-trackerSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Run this exact form — do not read the source tree:
- Distinctive: line 65
No match yields a score of 0 — a valid result, not an error.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ai-trace-remover
Strips formulaic phrasing and grades the residue. It never rewrites your argument and never deletes a sentence silently.
- Stage:
processors· Sandbox: no · Dependencies: stdlib only
Quick Execution
Run this exact form — do not read the source tree:
python run.py --root <WS> --action scan -- <file>- Everything after
--is forwarded to the legacy CLI, which takes the manuscript path positionally. - The gate lands in
<WS>/process/gates/ai-trace-remover_<ts>.json.
When to use
- A draft is about to be delivered and formulaic phrasing must go.
- A text's template density must be measured.
When NOT to use
- The content itself must be improved — that is writing, not cleaning.
- The user wants a sentence deleted outright without a report.
Actions
--action | Does | Extra arguments |
scan | Scan and clean, then score | <file> [-o <out>] |
report | Re-emit the score report | <file> |
Hard constraints
- Only matched patterns are touched.
- Every change is reported — the diff is part of the output.
Outputs
- The cleaned text (when an output path is given) under
process/. <WS>/process/gates/ai-trace-remover_<ts>.json— the gate result and score.
Failure handling
- A missing file exits non-zero with a clear message.
- No match yields a score of 0 — a valid result, not an error.
Limitations
- Lexicon-based; it cannot judge whether prose is genuinely original.
- The score is a heuristic, not a detector verdict.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.