Repository navigation
Skill/tool usage drops off as a project matures — lc/astra skills stop being auto-invoked later in a project #149
Description
What happened
In the early stages of a project the lc/astra skills and tools are invoked
consistently and effectively. As the project matures, Claude increasingly stops
reaching for them on its own — work that should route through a skill gets done
ad-hoc instead.
Concrete example from a live session: the user asked Claude to review a paper,
and Claude did the work without invoking the relevant ASTRA skill
(paper-extraction / the astra paper workflow). It hand-rolled the steps
(WebFetch the abstract, manual quote extraction, astra paper add --pdf) rather
than going through the skill path. The end result was fine, but the skill that
exists for exactly this was bypassed.
Impact
The skills encode the correct, provenance-tracked workflow. Skipping them later in
a project means inconsistent process (manual vs skill-driven), and the value of
having the skills degrades precisely when the project is most complex and most
needs the guardrails.
Possible direction (not a prescription)
- Skill-selection seems to weaken as session/project context grows — worth checking
whether long-context or accumulated CLAUDE.md state is crowding out the
skill-trigger reminders. - A periodic "did a skill match this request?" check, or stronger trigger phrasing
for paper/spec/recipe operations later in a project, might help.
Environment
- ASTRA: 0.2.9
- lightcone-cli: 0.3.6
- Python: 3.12.5
- OS: Linux 4.18.0-553 (EL8)
This was written by Claude.
Activity
calumhrmurray commentedon Jun 8, 2026
Folding in #151 as a concrete instance of this same root cause (skills not auto-invoked in a mature project).
Instance: in an existing ASTRA project, the user asked Claude to "read some papers to check we are not missing anything." Claude ran ad-hoc web search instead of routing through the ASTRA literature flow, and wrote nothing back into the spec.
Specific expected routing this adds (not in the original report): a literature-review request in an existing project should mirror
lc-newbehavior —astraskill for theprior_insights/evidenceschema,lc-extractoragent to pull verified quotes from the papers,prior_insightsinastra.yaml, each attached to the decision it bears on.Note the project's
astra.yamlhad noprior_insightssection at all, so there was no existing literature layer to extend — the ad-hoc path produced unverified paraphrases (one WebFetch even failed to extract the real content) with no provenance.Closing #151 as a duplicate of this umbrella issue.
This comment was written by Claude on behalf of the user.
aboucaud commentedon Oct 6, 2026
@cailmdaley is this relevant to move this issue to the agent-skills repo or shall we close it ?
cailmdaley commentedon Oct 12, 2026
yes i think it's still relevant @aboucaud and i agree it should be moved. i still notice the lightcone skill rarely gets activated unless i explicitly ask. we could have an eval that emulates a mature project and makes sure the skill gets activated automatically.