finalize
From the author
Score the best candidate on the held-out TEST split exactly once and seal the run. Use as the last evaluation step, after optimization stops. The run dir enforces the seal — a second finalize raises an error — so the headline number is produced once on data the optimizer never saw, the way an honest benchmark result must be.
Install
npx skills add skillberry-ai/cap-evolve --skill finalize -a claude-code
Installs to .claude/skills/finalize/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 76
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- evaluateskillberry-ai/cap-evolveScore a candidate on a split with honest, variance-aware evaluation. Use whenever you need a number for a candidate (the algorithm calls it internally; you can also call it directly to inspect). Runs the target via the adapter for each task, scores each rollout, aggregates mean + standard error, and reports pass^k when trials > 1. Never touches the test split (that is finalize's sealed job).Testing★ 66
- reportskillberry-ai/cap-evolveSummarize a run for a human — baseline val → best val → sealed test, the winning candidate, iterations spent, and pass^k. Use after finalize. Writes report.md and prints a compact JSON summary; the source of truth for "did this optimization actually work, and by how much".Testing★ 66
- optimize-loopgaasher/Agent-Loop-SkillsUse when the user wants to iteratively improve an artifact under a hard correctness bound while minimizing a measured cost — refactoring a code module to cut complexity while its test suite stays green, OR speeding up a SQL query while it returns the same rows. Each iteration applies one focused change, checks a correctness gate that must pass, measures a metric that must drop, and keeps the change only if both hold, else reverts; loops to a plateau or budget. Not for adding features, fixing bugs, or any change that is allowed to alter behaviour or results.Testing★ 178
- baselineskillberry-ai/cap-evolveEstablish the starting point. Use after implement-and-check and before any algorithm. Creates the run directory, freezes the seeded train/val/test split (written once), scores the unmodified seed capability on val, and records it as the candidate every algorithm must beat. Reports the remaining headroom so a saturated seed stops the run before it spends budget.Testing★ 66
- performance-optimizationDevelopersGlobal/ai-agent-skillsMeasure first, optimize second. Data-driven performance improvements with before/after benchmarks and production validation.Other★ 216
- testavibebuilder/claude-primeUse when the user wants to know if something works — the answer requires running code, not analyzing it. Output is a verdict backed by evidence: passed, failed, or broken. Primary triggers: 'run the tests', 'does X still work after my change?', 'did the merge break anything?', 'verify the fix worked', 'check if the endpoint returns X', 'confirm nothing regressed', 'run tests/unit/test_foo.py', 'let me know the results', 'make sure my changes didn't break anything'. Hard stops — do NOT use for: reviewing test code for quality/coverage gaps, debugging why test infrastructure/databases/seed scripts are misbehaving, writing or fixing tests, diagnosing root causes of unexpected behavior. The deciding question: is the user asking for the result of executing something, or asking for help understanding/analyzing/improving something? If it's the latter, use diagnose or review-code instead.Testing★ 120
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in