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.
Next step: if this matches your report, add to an open issue below rather than opening a new one.
Pick up a Lab taskThese 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
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 0.36.1.00means 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 LabAt a glance
- Subsystem
- skills
- Closed issues
- 1
- Attempts
- 0 PRs closed without merging