You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Optimize the contributor-growth skill family #1348
Part of #1342 — apply the setup-family optimization recipe to the contributor-growth family.
6 skills, 28,197 body tokens in total; 3 over the 200-token always-on budget, 1 over the 5,000-token body budget.
skill
body tokens (budget 5,000)
always-on tokens, est. (budget 200)
lines (cap 500)
contributor-sentiment
4,726
~233 ⚠
463
onboarding-concierge
3,374
~267 ⚠
318
contributor-activity-sweep
3,323
~203 ⚠
366
committer-onboarding
7,310 ⚠
~164
712 ⚠
contributor-nomination
4,761
~179
461
contributor-to-committer
4,703
~185
505 ⚠
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.
For every PR, all quoted routing triggers, confirmation gates, byte-identical headings/golden rules, and eval fixtures will be strictly preserved, with measured_tokens stamps updated.
Phase 2 Progress Update (Skill Body Budget Optimization)
Phase 2 is now complete - both over-budget skills in magpie-contributor-growth have been trimmed well below the $\le 5,000$ token ceiling with zero behavioral changes, all companion references intact, and structural surface hashes reconciled:
committer-onboarding: split per governance model (asf-pmc / github-codeowners / maintainer-roster) and IP-intake model (icla / dco / no-cla) into detail/, so only the configured model's text is read; routing metadata trimmed; maintainer-approved wording pass. Body 8,042 → 4,722 tokens, 780 → 364 lines (back under the 500-line cap); always-on ~205 → ~159.
activity-sweep: four hand-written GraphQL searches (writing to /tmp) replaced by one cached contributor-metrics fetch; counts now dated by the contributor's own activity like the rest of the family.
Fixes: private@ self-subscribe wording, gitbox access in the asf-pmc example, and the committer-onboarding step-1 eval (it never asked for JSON, so 6–7 of 9 cases errored on every run; now 26/27 graded).
About 30 direct gh calls replaced by contract operations: new read operations on contract:change-request and contract:tracker, repository_metadata / put_file on contract:source-control, and a new contract:people. GitHub is one adapter; Jira is a second tracker backend.
contributor-metrics reads code-host and tracker activity separately, so a project reviewing on GitHub with issues in Jira gets correct numbers from both. GitHub-only output is unchanged.
Where the family stands now (body tokens, budget 5,000): activity-sweep 3,490 · calibrate 3,730 · candidate-screen 3,695 · committer-onboarding 4,722 · identity-map 3,486 · onboarding-concierge 3,368 · sentiment 4,618 · contributor-to-committer 5,210 · nomination 5,316. Every skill is under the 500-line cap and the always-on budget. contributor-to-committer and nomination have grown slightly past 5,000 again with the later contract and information-only changes; that is small enough to pick up in a future pass rather than keep this issue open.
Follow-ups, not blocking: GitLab / Forgejo / Bitbucket adapters for the new contract operations, and updating three skill descriptions that still say "GitHub activity" now that the tracker can be Jira.
Activity
Kaap10 commentedon Oct 1, 2026
Hi @potiuk
I'd like to pick up #1348 and optimize the
contributor-growthskill family following the #1342 recipe.To keep reviews atomic and bite-sized, I plan to break the work into focused PRs:
Phase 1: Always-On Frontmatter Trimming (Priority 1 — Target$\le 200$ tokens)
onboarding-concierge(~275 tokens ⚠sentiment(~241 tokens ⚠activity-sweep(~209 tokens ⚠Phase 2: Body Budget Trimming (Target$\le 5,000$ tokens)
contributor-to-committer(5,741 tokens ⚠nomination(5,610 tokens ⚠For every PR, all quoted routing triggers, confirmation gates, byte-identical headings/golden rules, and eval fixtures will be strictly preserved, with
measured_tokensstamps updated.Kaap10 commentedon Oct 2, 2026
Phase 1 Progress Update (Always-On Frontmatter Trimming)
Phase 1 is complete — all 3 target skills are now trimmed well below the$\le 200$ token budget with routing triggers fully intact:
onboarding-conciergesentimentactivity-sweepOutcome: Saved ~350 always-on tokens, reducing
magpie-contributor-growthfootprint from~0.7kto~0.6k.Kaap10 commentedon Oct 2, 2026
Phase 2 Progress Update (Skill Body Budget Optimization)
Phase 2 is now complete - both over-budget skills in$\le 5,000$ token ceiling with zero behavioral changes, all companion references intact, and structural surface hashes reconciled:
magpie-contributor-growthhave been trimmed well below thecontributor-to-committernominationKaap10 commentedon Oct 5, 2026
The optimization recipe for the
contributor-growthskill family is fully delivered and merged:Phase 1: Always-On Frontmatter Trimming ($\le 200$ tokens)
onboarding-concierge(~133 tokens, -51.7%)sentiment(~131 tokens, -45.6%)activity-sweep(~111 tokens, -46.8%)Phase 2: Skill Body Budget Trimming ($\le 5,000$ tokens)
contributor-to-committer(4,592 tokens, -20.0%, brief extraction to companion file)nomination(4,802 tokens, -14.4%, companion surface hash reconciled)potiuk commentedon Oct 6, 2026
Closing: the contributor-growth optimization is complete. Summary of everything that landed:
Phase 1 — always-on frontmatter (≤ 200 tokens) — thanks @Kaap10
onboarding-concierge~275 → ~133sentiment~241 → ~131activity-sweep~209 → ~111Phase 2 — body budget (≤ 5,000 tokens) — thanks @Kaap10
contributor-to-committer~5,741 → 4,592nomination~5,610 → 4,471Phase 3 — second sweep (#1548)
committer-onboarding: split per governance model (asf-pmc / github-codeowners / maintainer-roster) and IP-intake model (icla / dco / no-cla) intodetail/, so only the configured model's text is read; routing metadata trimmed; maintainer-approved wording pass. Body 8,042 → 4,722 tokens, 780 → 364 lines (back under the 500-line cap); always-on ~205 → ~159.activity-sweep: four hand-written GraphQL searches (writing to/tmp) replaced by one cachedcontributor-metricsfetch; counts now dated by the contributor's own activity like the rest of the family.Phase 4 — vendor neutrality (#1549)
ghcalls replaced by contract operations: new read operations oncontract:change-requestandcontract:tracker,repository_metadata/put_fileoncontract:source-control, and a newcontract:people. GitHub is one adapter; Jira is a second tracker backend.contributor-metricsreads code-host and tracker activity separately, so a project reviewing on GitHub with issues in Jira gets correct numbers from both. GitHub-only output is unchanged.Where the family stands now (body tokens, budget 5,000): activity-sweep 3,490 · calibrate 3,730 · candidate-screen 3,695 · committer-onboarding 4,722 · identity-map 3,486 · onboarding-concierge 3,368 · sentiment 4,618 · contributor-to-committer 5,210 · nomination 5,316. Every skill is under the 500-line cap and the always-on budget.
contributor-to-committerandnominationhave grown slightly past 5,000 again with the later contract and information-only changes; that is small enough to pick up in a future pass rather than keep this issue open.Follow-ups, not blocking: GitLab / Forgejo / Bitbucket adapters for the new contract operations, and updating three skill descriptions that still say "GitHub activity" now that the tracker can be Jira.