Recalibrate skill-curator inventory health score to frozen 5-band scale - #10
Merged
Merged
Conversation
…and scale score() was a lenient deduct-from-100 model whose small penalties clustered any not-badly-broken inventory near 100 (top-saturated, non-discriminating). Recalibrate: - Start at 96 (mild curation tax; no near-free perfect score). - Steeper, graduated deductions for the common sprawl findings (duplicate surfaces, collision clusters, near-dupes, prune candidates) so scores spread. - Replace A-F letters with the frozen bands shared with plugin-audit: 92-100 Exceptional | 82-91 Strong | 68-81 Solid | 50-67 Needs work | <50 Poor. - Band the rounded (displayed) score so the label never contradicts the number. - render_md health line now prints the band label (via the same grade variable). - selftest asserts a clean inventory reaches Exceptional and a sprawl-heavy fixture lands demonstrably lower (Solid/Needs work/Poor). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
RasputinKaiser
added a commit
that referenced
this pull request
Jul 21, 2026
Recalibrated both audit scorers to be demanding and discriminating: - Graduated credit + leanness rewards; skill_quality gains machine signal (floor 60->74.4) - N/A dimensions redistribute weight instead of a free max (hooks no-hooks free-10 removed) - Frozen 5-band grade scale (Exceptional/Strong/Solid/Needs work/Poor); 92+ genuinely hard - NEW scripts/calibrate.py saturation meter + CI guardrail; self-score floor 57->70 - Integration fix: repoint calibrate selftest fixtures to score.py tier builders Landed via PRs #10-#14. Merged-tree: validate 11/11, curator 87/87, score+calibrate selftests green, calibrate --check passes over the real inventory. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Recalibrates
skills/skill-curator/scripts/curator.py'sscore(findings)so the inventory health score discriminates instead of top-saturating near 100.Why
The old model started at 100 and subtracted small penalties, so any inventory that wasn't badly broken trivially scored ~90-100. It didn't discriminate among decent inventories and the A-F bands were lenient.
Changes (scoring surface only)
grade_band()helper).render_mdhealth line now prints the band label (unchanged interpolation of thegradevariable).selftestscore assertions updated: a clean inventory reaches Exceptional; a sprawl-heavy fixture lands demonstrably lower (Solid/Needs work/Poor).score()keeps its(int, str)return arity. No other files, versions, or release metadata touched.Verification
python3 scripts/validate.py→ PASS 11/11python3 skills/skill-curator/scripts/curator.py selftest→ 87/87 passedreport --no-plugins --root skillshealth line →Strong (86/100)(frozen band label)🤖 Generated with Claude Code