agentsclimarketplace

Test saill in skill

Skill HorizonBrute/Standardized_AI_Looping_Language-SAILL/skills/test_saill_in_skill

Standardized AI Looping Language

Install
npx -y skills add HorizonBrute/Standardized_AI_Looping_Language-SAILL --skill test_saill_in_skill

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

  • 1 stars1 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 author says it does

Copied from the file, not written here

Proof-of-concept SAILL-in-skill. Replaces a wordy dirtree-check skill with a tight SAILL block. Audits tested_implementations nonce coverage via the Nonce Trace Audit team.

SKILL.md

1.1 KB, as published. Nobody here has run it

Skill: /test_saill_in_skill

Model preference: #midcost

"For every dir with a trace nonce file, send a haiku agent to report agents.md files loaded."

Nonce Trace Audit

  1. Scanner (#lowcost) — globs **/testing_nonce.md under -context:root-; emits directory list as -context:dirs-.
  2. Readers[ Nonce-Reader (#lowcost, parallel) per -context:dirs- ] (wait) — one haiku agent per dir; reads testing_nonce.md and walks parent dirs for agents.md trace lines; returns CSV row: dir,trace1|trace2|...,nonce.
  3. Synthesizer (#midcost) — collects CSV rows; builds fenced markdown directory tree (nonce ✓, chain depth per node, MISSING flagged).
  4. Writer (#lowcost) — writes tree to documentation/lastrun_dirtree_check.md with run header; appends sha256: <hash>.

Send the Nonce Trace Audit team against -context-

Keep looking

Skills are one crate of 328,083. 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.