top-edit
Skill7 starsChanged 18 days agoMITView on GitHub
Use this as the last mechanical pass before publishing, to screen AI tells and house-style misses that a slop word-list can skip.
In this repository19 other files it gives its agents.
- whetstone-signalSkill
- design-a-grok-botSkill
- overheard-setupSkill
- overheardSkill
- routine-healthcheckSkill
- transcript-healthcheckSkill
- diagram-designSkill
- engineering-playbookSkill
- show-meSkill
- chatgpt-images-browser-playbookSkill
- aeo-geo-siteSkill
- exact-match-intent-seoSkill
- coachSkill
- draftSkill
- no-ai-slopSkill
- outlineSkill
- social-copywritingSkill
- source-checkSkill
- x-articleSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 52
If the same pattern hits 10 times, flag the first 3 and count the rest.
≈ “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
Top edit
Checklist pass. Pattern-matching, not a vibe critique. Run after No AI slop. Do not edit the draft in this pass. Report flags with line, quote, and a fix.
AI tells
- Vague This/That openers with no noun
- Correlatives: not only/but also, both/and
- Formulaic transitions: moreover, furthermore, additionally, indeed, in fact
- Hedging: it could be argued, it seems, one might say
- Marketing speak: game-changing, groundbreaking, unlock, empower
- Signposts: let's dive in, as we'll see, here's the thing
- False drama fragments
- Artificial triads of three
- Balanced on-the-other-hand that refuses a position
- Consultant-speak: moving the needle, low-hanging fruit, key takeaway
- Banned words: leverage, comprehensive, pivotal, delve, showcase, tapestry, robust, seamless
- Em dashes
- Formula: not just X but Y, in today's world
- Forced symmetry across sections
- Repetition disguised as depth
- Sentence-initial But/And overuse
- Contrastive reframing more than twice in a long piece
House
- Opening is a scene or lived fact, not an abstract thesis
- Arc is concrete then mechanism then implications
- Major claims have a named source
- Teach test in one sentence
- Specificity: could someone else have written this?
Prose
- Same word twice in close range
- Passive clusters
- Five sentences of similar length
- Dead metaphors
Verdict
CLEAN (0–2 minor), LIGHT FIXES (3–5), or NEEDS WORK (6+ or structural). One-sentence recommendation.
If the same pattern hits 10 times, flag the first 3 and count the rest.
Source: adapted from Nadiem Mahmoud, top-edit. MIT; see third-party notices. Run No AI slop first.
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.