From subagent-forge
Rank sources by credibility, freshness, firsthand evidence, maintenance health, and shill risk. Use when the user says "are these sources good", "rank these", "which sources should I trust", or when separating signal from SEO sludge.
How this skill is triggered — by the user, by Claude, or both
Slash command
/subagent-forge:source-triageThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when the task involves evaluating the quality of sources, not just collecting them.
Use this skill when the task involves evaluating the quality of sources, not just collecting them.
Prefer, in order:
For repos, do not stop at stars. Check:
Return a ranked source stack:
If sources disagree, keep both and explain which one is carrying more weight.
npx claudepluginhub ildunari/kosta-plugins --plugin subagent-forgeWhole-repo audit for over-engineering: finds dead code, unnecessary abstractions, stdlib-replaceable dependencies. Outputs ranked findings and net line/dep savings.
3plugins reuse this skill
First indexed Mar 25, 2026