Skill loading and relevance during task execution

NousResearch/hermes-agent · cluster 58340 · skills

Data as of

2 open items. No fix on record.

The short answer

2open issues
0open PRs
3items grouped
Known?
Yes. 3 related items grouped here, 1 issue already closed.
Fix event
No merged or attempted fix PR is on record for this cluster.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
2 issues and 0 PRs. Broad area: open items may be separate problems.

These items concern a gap where skills—whether auto-created or manually defined—are not loaded or surfaced contextually before tasks run. The requests involve both diagnosing why auto-learned skills go unused and adding context-aware skill retrieval prior to execution.

Open issues2

  • Issue#58340[Feature Request] Auto-load relevant skills before task execution
  • Issue#66180Auto-created skills are never loaded during task execution — the auto-learning loop creates output that only describes past mistakes but never prevents future ones, turning it into a net negative for budget-model users

Open PRs0

No open pull requests.

Closed issues · 1
  • Closed#62475Agent misses relevant skills in flat 69-skill list — needs context-aware boosting
How this cluster was grouped
  • Link evidence (automated judgement only): no structural link between members; the grouping rests entirely on an automated relevance judgement over their text.
  • Read the members yourself before treating them as one problem.
  • Pairwise link density 0.24: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. 1.00 means every pair is linked.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Subsystem
skills
Closed issues
1
Attempts
0 PRs closed without merging

For your agent

The same facts, typed.