Bounded skill optimization
Skill w3rdist-creator/agent-intelligence-economy/skills/bounded-skill-optimization
Obsidian + Hermes agent intelligence economy kit: clippings harvest, skill optimization, token efficiency, verification, loop scoring.
npx -y skills add w3rdist-creator/agent-intelligence-economy --skill bounded-skill-optimizationAssembled 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 author says it does
Copied from the file, not written here
Improve agent skills and runbooks through evidence-backed, bounded, validated patches.
SKILL.md
0.7 KB, 105 tokens by cl100k_base, as published. Nobody here has run it
Bounded Skill Optimization
Trigger after difficult sessions, repeated failures, useful source harvests, cron reviews, or stale skill behavior.
Loop: observed run evidence -> recurring success/failure pattern -> localized candidate edit -> validation gate -> accepted patch or rejected-edit record -> later review.
Acceptance criteria:
- grounded in observed evidence;
- reusable across future runs;
- smaller than the problem it prevents;
- belongs in this artifact;
- not a stale one-off fact;
- does not loosen safety or privacy boundaries.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.