finalize SKILL.md skillA
finalize from skillberry-ai/cap-evolve is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add skillberry-ai/cap-evolve/finalize@git:20260822.888a816Pins git:20260822.888a816 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- skillberry-ai/cap-evolve
- Path
skills/phases/finalize/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260822.888a816, committed Aug 22, 2026
- First version recorded
- Jun 15, 2026
- Size
- 5,822 bytes
- Repository stars
- 66
- License
- Apache-2.0
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.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# finalize — the one honest number Optimization hill-climbs on val: every accept decision consumed val as a tuning signal, so by the end of search val is *optimistic* — it has been selected against. The number you **report** must come from data nothing was tuned against. finalize scores the run's best candidate on the sealed `test` split, once, and writes `final.json`. That file is the run's result. ## One finalize is two evals, not one A bare test number cannot be defended — a reader cannot tell whether it beat the capability you started with. So one finalize scores test **twice**: the best candidate as tag `FINAL`, and the untouched `seed` candidate as `FINAL_seed` (`harness.finalize`). `final.json` therefore carries `test`, `test_baseline`, `baseline_id`, and `test_delta` — the held-out *improvement*, which is the figure `report`, the dashboard, and the event stream all headline. If the best candidate IS the seed (nothing was accepted), the second eval is skipped and `test_delta` is 0 by construction. So budget `--n-trials 3` as 3 trials × **2 candidates** × |test| rollouts — twice what the flag looks like it buys on a paid benchmark. …
Read the whole file at its exact version.
How to install
mdr add skillberry-ai/cap-evolve/finalize@sha256:ec7a5600c2f499fdThe line at the top of this page pins the label git:20260822.888a816, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_knkk53jqdz4rccbu)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Jun 15, 2026 and Aug 22, 2026, about one every 23 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260822.888a816 latest | 2026-08-22 | 888a816 | 5,822 B | A | view · diff |
| git:20260617.92b5c65 | 2026-06-17 | 92b5c65 | 3,496 B | A | view · diff |
| git:20260616.306ff98 | 2026-06-16 | 306ff98 | 3,171 B | A | view · diff |
| git:20260615.59b72de | 2026-06-15 | 59b72de | 3,171 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5822 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
skillberry-ai/cap-evolve · 66 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_knkk53jqdz4rccbu GET https://markdownregistry.com/api/v1/resolve?ref=skillberry-ai/cap-evolve/finalize GET https://markdownregistry.com/api/v1/blob/ec7a5600c2f499fdaa47d67393f3b87f469d9816461bc257dce1a2b4963b811a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from skillberry-ai/cap-evolve
Every file in skillberry-ai/cap-evolve