improve(skills): /loop and /fullsolve run affected tests, not the full npm test (#1349 follow-up)
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 83/100
- Issue type
- Documentation
- Clarity
- Clearly specified
- Activity status
- Active
- Tech stack
- typescript
- Domain
- developer-experience
Research direction
Read .claude/skills/loop/SKILL.md, .claude/skills/fullsolve/SKILL.md, and the “Affected tests” rules in exec’s skill section; also inspect scripts/affected-tests-skill.test.ts and ADR-0010. Update the two skills to refer to exec’s rules, then run the affected-tests skill test and npm run lint:skill-sync; done when both acceptance criteria pass.
Written by the indexing model from the issue text.
Description
Summary
/loop and /fullsolve still tell the agent to run the full npm test. #1349 (PR #1358) moved /exec and /qa to the affected-tests rules. Give these two skills the same rules, or point them at exec's section.
Current State
.claude/skills/loop/SKILL.mdhas 3npm testinstructions and.claude/skills/fullsolve/SKILL.mdhas 2 (counted at the time #1349 was QA'd).- ADR-0010 (
docs/adr/0010-phases-run-affected-tests.md) lists them under Consequences. - Under
sequant run, a loop iteration that runs the full suite meets the same 600 s Bash cap and 30-minute no-progress wall #1349 fixed for exec and qa.
Acceptance Criteria
- AC-1: loop and fullsolve contain no step that tells the agent to run the bare
npm test; they refer to exec's "Affected tests" rules — Evidence: extendscripts/affected-tests-skill.test.ts's "no other step tells the agent to run the bare npm test" overloopandfullsolve, mutation-verified - AC-2: skill mirrors in sync — Evidence:
npm run lint:skill-sync
Context
- Follow-up to #1349 (PR #1358).
- Dominant language
- TypeScript
- Stars
- 1
- Forks
- 1
- Avg merge
- 11h 3m
- Merged PRs (30d)
- 84
Getting set up
- No Dockerfile or Docker Compose file
- No pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from sequant-io/sequant
-
graph-2026-11-simplify
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
sequant-io/sequant#1650 ·
Maintainers usually reply within 1 day
-
run: --phases does not suppress the UI-label test phase (determinePhasesForIssue adds it to an explicit list)Possibly taken @admarble claimed this today. Open
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
sequant-io/sequant#1631 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
sequant-io/sequant#1601 ·
Maintainers usually reply within 1 day
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 86/100
sequant-io/sequant#1582 ·
Maintainers usually reply within 1 day
-
Difficulty 1/5 Under an hour Newbie friendliness 76/100
sequant-io/sequant#1381 ·
Maintainers usually reply within 1 day
All issues in sequant-io/sequant
Similar issues
-
content triage
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 82/100
tensorflow/tfjs#8754 ·
-
tool-submission
Difficulty 1/5 Under an hour Newbie friendliness 83/100
BraveOPotato/NoSignups#2348 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
code-yeongyu/oh-my-openagent#12784 ·
Maintainers usually reply within 1 day
-
external-issue to-triage
Difficulty 2/5 1-3 hours Newbie friendliness 71/100
Maintainers usually reply within 1 day