agentsclimarketplace
Sign in

Deep naming study

Skill sapochat/deep-naming-study

Use when naming work has reached like-but-dont-love, repeated synonym loops, or an inspiration whose effect is hard to reproduce. Recover the mechanism, generate from independent theories, criticize blindly, and test finalists in use.From its SKILL.md

Install
npx -y skills add sapochat/deep-naming-study

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.5 KB, 219 tokens by cl100k_base, as published. Nobody here has run it

Deep Naming Study

Trigger

Use after several adjacent naming rounds, when explanations improve but names do not, or when domain availability starts distorting taste.

Method

  1. Build one brief: purpose, future range, voice, source inspiration, load-bearing mechanism, dislikes, phonetic hazards, dead lanes, and rubric.
  2. Research primary or archival source language where relevant.
  3. Run independent passes by theory: semantic mechanism, editorial voice, institutional vocabulary, alternate grammar, hostile critique.
  4. Keep artifacts separate and do not expose earlier favorites as conclusions.
  5. Merge by theory, not proposal frequency.
  6. Give blind critics the brief and slate without domains or prior rankings. Require them to kill at least half.
  7. Treat disagreement as diagnostic; never average rankings into a winner.
  8. Check collisions, spoken quality, and domains only after taste qualification.
  9. Simulate finalists over five issue titles, a descriptor, an About paragraph, a masthead, and a spoken introduction.
  10. Conclude honestly: solved, close, or wrong field.

What ships with it: 9 files

8.4 KB alongside SKILL.md, 4 of them executable

examples/

src/

tests/

Gives 0 of the 12 instructions most learn study skills give in 219 tokens

Counted across 546 of the 573 authors here whose files we hold, read 2026-08-07

  • Calculate the zone of proximal development before teachingin 25 of 546, across 8 files
  • Produce self-contained HTML lessonsin 24 of 546, across 8 files
  • Record user preferences in a notes filein 23 of 546, across 5 files
  • Maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
  • Find high-quality resources before writing lessonsin 19 of 546, across 5 files
  • Make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
  • Create reusable components for lessonsin 19 of 546, across 5 files
  • Create compressed reference documents for quick lookupin 19 of 546, across 3 files
  • Update the mission file and records upon mission changesin 16 of 546, across 2 files
  • Set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
  • Populate the mission file before teachingin 15 of 546, across 1 file
  • Include interactive feedback loops in lessonsin 15 of 546, across 1 file

Said here and by no other author read

  • build one naming brief
  • research source language
  • run independent naming passes by theory
  • keep artifacts separate
  • merge by theory not frequency
  • give blind critics the brief and slate

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,144. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.