Cairn
NousResearch/hermes-agent

Learning graph incorrectly marks skills as learned

Cluster 80596 · skills. Data as of

Nothing open on GitHub. Fix merged in #111363 on 15 Sep 2026. Check it covers your case.

The short answer

0open issues
0open PRs
3items grouped
Known?
Yes. 3 related items grouped here, 1 issue already closed.
Fix event
A fix was merged to main in PR #111363. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
Nothing open on GitHub.

These items address a bug where skills created or installed outside of direct user learning interactions are incorrectly flagged as 'learned' in the learning graph, causing inaccurate use counts and premature journey visibility.

Open issues0

No open issues.

Open PRs0

No open pull requests.

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #111363 fix(journey): a skill created by /learn or skill_manage shows in /journey before its first use (#111317, salvage #111327)

    merged to main

    files: agent/learning_graph.py, apps/desktop/src/app/starmap/share-code.test.ts, apps/desktop/src/app/starmap/share-code.ts, apps/desktop/src/app/starmap/text.ts, hermes_cli/curator.py, tests/agent/test_learning_graph.py, tests/tools/test_skill_manager_tool.py, tests/tools/test_skill_usage.py, tools/skill_usage.py, website/docs/user-guide/features/curator.md, website/docs/user-guide/features/memory.md

1 PR closed without merging

From the close comments: superseded by another PR 1

  • #80599 fix(agent): only mark agent-created skills as learned in learning graph · superseded by another PR → #111363, #80599
Closed issues · 1
  • Closed#80596bug(desktop): learning graph marks externally-installed skills as 'learned' (use_count inflation)
How this cluster was grouped
  • Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
  • Pairwise link density 0.67: 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
Merged PRs
#111363
Closed issues
1
Attempts
1 PR closed without merging
Fix link checked
15 Sep 2026

For your agent

The same facts, typed.

cluster/80596.json
cluster/80596.md