style-check
Skill0 starsChanged 4 months agoMITView on GitHub
Fast deterministic prose-style checker. Wraps research-kit/tools/style_lint.py for file-scoped use. Use when the user invokes /style-check <file>, asks to "check style", "scan for AI tells", "polish before sending", or wants a quick mechanical pass before submission. For LLM whole-document review use /style-review; for section-scoped pre-submission validation use /validate-section.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Mikefluff/skillstheir own version, first seen Aug 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Mikefluff/skills★ 26same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository39 other files it gives its agents.
- anecdotesSkill
- backupSkill
- checkSkill
- cite-syncSkill
- dataSkill
- diariosSkill
- distill-styleSkill
- driveSkill
- dropboxSkill
- fetch-annotationsSkill
- findings-auditSkill
- findingsSkill
- gmailSkill
- handoffSkill
- howtoSkill
- hypothesisSkill
- iatSkill
- ideaSkill
- inboxSkill
- institutionsSkill
- literatureSkill
- llmkitSkill
- meetSkill
- memory-auditSkill
- new-pipelineSkill
- new-projectSkill
- nextSkill
- otterSkill
- outlookSkill
- questionsSkill
- referee-panelSkill
- siteSkill
- style-reviewSkill
- style-reviseSkill
- tactiqSkill
- theorySkill
- validate-sectionSkill
- whatsappSkill
- zoomSkill
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 61
Before sending anything that matters: papers, drafts, emails, slides.
- Distinctive: line 81
Add new patterns there once and all three skills pick them up.
≈ “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
style-check
Fast, deterministic, file-scoped prose-style scan. Wraps the canonical
linter at research-kit/tools/style_lint.py. Runs in milliseconds. No LLM.
How to invoke
python3 ~/research/research-kit/tools/style_lint.py <file> [flags]Common flags:
--format json— JSON output--severity warning— minimum severity (info | warning | error)--rule <name>— only run a named rule (repeatable)<dir>— pass a directory to lint all.texand.mdunder it
See python3 style_lint.py --help for the full surface.
Exits 1 if any violations remain at the requested severity. Useful for gating submissions in CI.
What it checks
Eighteen mechanical rules covering the deterministic part of
research-kit/rules/writing_style.md:
| Rule | Section reference |
ai-tell | §4 |
filler-phrase | §17 (Quick reference) |
throat-clearing | §2 |
editorializing | §2 |
naked-this | §4 |
word-choice | §4 (plain-word table) |
self-categorizing | §13 |
forward-reference | §16 (robot-body linearity) |
hedging-opener | §7 |
sentence-length | §3 |
clause-stacking | §3 |
passive-density | §2 |
connective-opener | §9 |
stacked-adjectives | §4 |
synonym-piling | §17 |
non-stat-significantly | §17 |
decimal-precision | §10 |
abstract-opening | §13 |
cute-quotation | §14 |
Skipped automatically: LaTeX comments, math environments, fenced and inline code, URLs, case/docket numbers, YAML frontmatter.
When to use
- Before sending anything that matters: papers, drafts, emails, slides.
- Cheap enough to run on every commit if you want it as a gate.
When to use vs. the other style skills
| Skill | Scope | Mechanical | LLM | Ledger writes |
/style-check (this) | file | yes | no | no |
/style-review | file (whole) | yes (calls style_lint.py) | yes | no |
/validate-section | one section | yes (calls style_lint.py) | yes | yes |
/style-revise | paragraph | yes (lints its rewrite) | yes | no |
Same patterns underneath. Different scopes and depths. /style-revise
reshapes a rough draft's idea flow rather than auditing finished prose —
use it when the draft is still unpolished, the others when it's near-final.
Implementation
The mechanical layer lives in research-kit/tools/style_lint.py and is
shared across /style-check, /style-review, and /validate-section.
Add new patterns there once and all three skills pick them up.
Severity levels: info (FYI, often the right word in context),
warning (worth addressing), error (blocking — typography violations
in referee mode, abstract-opening violations).
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.