Repository navigation
Optimize the mentoring skill family #1351
Description
Part of #1342 — apply the setup-family optimization recipe to the mentoring family.
4 skills, 14,455 body tokens in total; 4 over the 200-token always-on budget, 0 over the 5,000-token body budget.
| skill | body tokens (budget 5,000) | always-on tokens, est. (budget 200) | lines (cap 500) |
|---|---|---|---|
good-first-issue-sweep |
4,124 | ~225 ⚠ | 372 |
good-first-issue-author |
3,611 | ~273 ⚠ | 277 |
newcomer-issue-explainer |
3,495 | ~234 ⚠ | 302 |
mentoring-welcome |
3,225 | ~203 ⚠ | 249 |
Body tokens are from docs/mode-economics.md; always-on figures are a chars ÷ 4 estimate of description + when_to_use. ⚠ marks a budget exceeded. Line counts include the generated pre-flight block.
Order of work (per the umbrella):
- Trim the frontmatter of every skill marked ⚠ in the always-on column.
- Split any over-cap body, moving sub-action-specific rules into sibling files byte-for-byte.
- Wording pass on the rest, with headings, golden-rule headlines, code blocks and the pre-flight block kept byte-identical.
- Run each touched skill's eval suite before and after, outside the sandbox.
Record any inconsistencies found but not fixed (eval-coupled wording, stale headings) in the PR description.
Activity
anbv29 commentedon Sep 24, 2026
Hi! I’m interested in the mentoring-skill optimization. I’ll begin by mapping the current behavior and suggesting a small measurable improvement. Would that be a useful approach?
potiuk commentedon Sep 24, 2026
Again - use the optimize skill for that - it should guide you step-by-step and you can start one skill at a time.
anbv29 commentedon Oct 1, 2026
i did as you said, it's working for now! let me raise a pull ruquest for this one
perf(mentoring): trim always-on routing metadata of the family's skills
perf(mentoring): trim always-on routing metadata of the family's skills
perf(mentoring): trim always-on routing metadata of the family's skil…