agentsclimarketplace

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.

One thing to look at

  • 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

tests/

Keep looking

Skills are one crate of 613,373. 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.