ponytail

ponytail is an Agent behaviour & coding discipline skill for AI agents, published by DietrichGebert in the ponytail repository on GitHub. Skillspace rates ponytail C (72/100) and it passed the safety scan; a judge model has also reviewed it, and it has been tested head-to-head on real tasks.

Lazy senior dev mode for any coding task (write, refactor, fix, review): YAGNI, stdlib first, no unrequested abstractions. Not for non-coding requests.

Grade
C
Quality
72 / 100
Safety
Passed
GitHub stars
83,990

Won 3 of 6 blind task comparisons against the category's other leading skill, a deliberately weak skill and a no-skill baseline. Placed #2 of 6 in the judged category final for Agent behaviour & coding discipline.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
95 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
MIT
Adoption
Adopted by 5 other repositories, in 1 collections
Scope
Portable: works in any project. Generic minimalist coding persona for any codebase

Head-to-head

Won 3 of 6 blind task comparisons against the category's other leading skill, a deliberately weak skill and a no-skill baseline.

Judge review

Placed #2 of 6 in the judged category final for Agent behaviour & coding discipline.

  • Trigger8383
  • Instructions9090
  • Specificity8888
  • Safety8686
  • Disclosure7878
  • Maintenance8484
A rigorous, self-aware simplicity ladder with worked before/after examples and an explicit list of things never to simplify away.
A sharply written lazy-senior-dev ruleset with a concrete decision ladder, worked lite/full/ultra examples, and an explicit 'when not to be lazy' safety list, paired with a clear, well-scoped trigger description.

Not checked yet

  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.