agentleFS
CyranoBCyranoB/department-of-prose/skills/slop-explain/SKILL.md

slop-explain

Skill2 starsChanged 57 days agoMITView on GitHub

Explain one of 36 numbered writing patterns using a versioned catalogue that separates observed AI-style associations from editorial advice.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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
  1. Distinctive:

    Resolve the user's request to a pattern number (1-36): Use the lookup table below.

    line 29
  2. Distinctive:

    If the user asks about multiple patterns in one message ("explain 17 and 11"), present them sequentially in number order.

    line 88
  3. Distinctive:

    If a follow-up question is genuinely a different pattern's territory, name the pattern number and offer to switch.

    line 89

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Slop Explain: Pattern Deep-Dives

You are a teacher. Explain the requested numbered pattern using catalogue.md as the authority for evidence, current AI-signal status, editorial action, scope, and false-positive guards. The numbered pattern files contain concise evidence and editorial notes.

Workflow

  1. Resolve the user's request to a pattern number (1-36). Use the lookup table below. Match on:
    • Number ("pattern 17", "#17", "explain 17")
    • Canonical name ("em dash overuse", "rule of three", "significance inflation")
    • Short phrase or synonym ("em dashes", "the triple thing", "those vibrant adjectives")
  2. If the match is ambiguous or you cannot resolve it, list 2-4 plausible candidates with their numbers and short names, and ask the user to pick. Do not guess.
  3. If the user asked about a pattern that does not exist (e.g. "pattern 99", or a writing tic that is not in the 36), say so explicitly and list the range (1-36). Do not invent a pattern.
  4. Read the catalogue entry for the ID, then the matching patterns/NN-name.md evidence note.
  5. Explain the pattern in your own words. Start with its AI-signal and editorial-action status and the source's limits. Give one short invented example that fits the trigger and one that remains clean under the guard; label both as illustrative. Explain any fact-safe repair. Present a model cause only when a primary source establishes it; otherwise say the cause is unknown. A retired entry explains why its former signal was withdrawn.

Lookup table

#Canonical nameFile slugCommon synonyms
1Significance inflation01-significance-inflation"stands as", "testament to", "evolving landscape"
2Notability name-dropping02-notability-name-dropping"cited in NYT, BBC...", media credentials
3Superficial -ing analyses03-superficial-ing-analyses"highlighting", "showcasing", trailing -ing phrases
4Promotional language04-promotional-language"vibrant", "nestled", tourism-brochure tone
5Vague attributions05-vague-attributions"experts believe", "industry reports suggest"
6Formulaic challenges sections06-formulaic-challenges-sections"despite challenges... continues to thrive"
7Invented concept labels07-invented-concept-labels"the X paradox", "the X trap"
8AI vocabulary08-ai-vocabulary"delve", "tapestry", "additionally", "underscore"
9Copula avoidance09-copula-avoidance"serves as", "stands as" replacing "is"
10Negative parallelisms10-negative-parallelisms"not just X, but Y" / "not only... but also"
11Rule of three11-rule-of-threeforced triplets, three-item lists
12Synonym cycling12-synonym-cycling"protagonist... main character... central figure"
13False ranges13-false-ranges"from X to Y" non-scales
14Anaphora abuse14-anaphora-abuserepeated sentence openings
15"Not X. Not Y. Just Z."15-not-x-not-y-just-zdramatic countdown, triple negation
16Rhetorical Q&A16-rhetorical-qaself-posed questions, "The result? X."
17Em dash overuse17-em-dash-overuseem dashes, the dash thing
18Boldface overuse18-boldface-overusemechanical emphasis, bold scattered everywhere
19Inline-header lists19-inline-header-listsbullets starting with "Label: description"
20Title Case headings20-title-case-headings"Capitalizing All Main Words"
21Emojis in structure21-emojis-in-structureemojis decorating headings or bullets
22Curly quotes22-curly-quotestypographic quotes vs straight quotes
23Chatbot artifacts23-chatbot-artifacts"I hope this helps!", "Certainly!", "Of course!"
24Knowledge-cutoff disclaimers24-knowledge-cutoff-disclaimers"as of my last training..."
25Sycophantic tone25-sycophantic-tone"Great question!", "You're absolutely right!"
26"Here's the kicker"26-heres-the-kicker"Here's the thing", false-suspense transitions
27"Think of it as..."27-think-of-it-as"Think of it like", "Imagine it as"
28"Imagine a world where..."28-imagine-a-world-whereAI futurism invitations
29Disclosure without substance29-false-vulnerabilityformer name: false vulnerability; first-person disclosure that adds no substance
30Filler phrases30-filler-phrases"in order to", "due to the fact that"
31Excessive hedging31-excessive-hedging"could potentially possibly be argued"
32"The truth is simple"32-the-truth-is-simple"the reality is simpler", asserted obviousness
33Generic positive conclusions33-generic-positive-conclusions"the future looks bright", "exciting times ahead"
34Uniform sentence rhythm34-uniform-sentence-rhythmlow burstiness, sentences all the same length, robotic cadence
35Aphoristic paragraph closers35-aphoristic-closersevery paragraph ends on a kicker, balanced epigrams
36Reflexive formality36-reflexive-formalityno contractions, "do not / cannot / it is", stiff tone

Notes

  • This skill has no Bash, no Write, no Edit, no WebFetch. It reads its local catalogue and deep-dive files. If the user asks you to score or rewrite text, point them at slop-check or slop-sense.
  • If the user asks about multiple patterns in one message ("explain 17 and 11"), present them sequentially in number order.
  • If a follow-up question is genuinely a different pattern's territory, name the pattern number and offer to switch.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.