agent-optimize SKILL.md skillA

agent-optimize from skillberry-ai/cap-evolve is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add skillberry-ai/cap-evolve/agent-optimize@git:20261013.db330d5

Pins git:20261013.db330d5 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/algorithms/agent-optimize/SKILL.md
Versions recorded
21
Latest version
git:20261013.db330d5, committed Oct 13, 2026
First version recorded
Sep 23, 2026
Size
11,544 bytes
Repository stars
66
License
Apache-2.0

Free-form optimization algorithm for agent orchestration mode: the conversational agent owns the whole search — reading a digest, proposing big coherent capability edits against failure-cluster hypotheses, probing only missing cells, promoting or pruning on a posterior, merging complementary branches, and sealing test once. Use when orchestration_mode is agent and algorithm_skill is agent-optimize. For a deterministic loop use hill-climb, gepa or skillopt instead.

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

# agent-optimize — the loop you own

You are the optimizer. `cap-evolve run` (agent mode) does check -> baseline and hands you `R`. Everything
else is six `act.py` verbs and one `digest.py`; the scripts decide, you judge.

## Honest statistics (read twice)

1. Noise sd of a full-val mean is ~0.05 (30 tasks x 3 trials): only big effects are resolvable. Never
   re-test a within-noise delta; make a bigger edit instead.
2. Never view test traces. Test is sealed, scored ONCE at finalize, and development-exposed after use.

Details only when needed: [`references/stats.md`](references/stats.md).

## Setup

The loop REQUIRES the new engine. Put this in `capevolve.yaml` (or export `CAPEVOLVE_<NAME>=1`):

```yaml
optimizer:
  ablation: {dag_parallel: true, active_eval: true, smart_merge: true, cost_gating: true,
             failure_clustering: true, pregate: true, context_digest: true}
```

Stock default has `active_eval` OFF: `probe --auto` then silently runs FULL val. The digest prints
`!! CONFIG: ...` at the top (after any INFRA line) when any switch is off; fix it before looping. Switches: [`references/ablation.md`](references/ablation.md).

```bash
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add skillberry-ai/cap-evolve/agent-optimize@sha256:cf4aa5fb1fb258c6

The line at the top of this page pins the label git:20261013.db330d5, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_niziebaacfbfdedl.svg)](https://markdownregistry.com/a/art_niziebaacfbfdedl)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 21 versions of this file, between Sep 23, 2026 and Oct 13, 2026, about one every day.

versioncommittedcommitsizeaudit
git:20261013.db330d5 latest2026-10-13 db330d5 11,544 BA view · diff
git:20261013.fa2a7122026-10-13 fa2a712 11,198 BA view · diff
git:20261013.fbe3d822026-10-13 fbe3d82 10,995 BA view · diff
git:20261013.7cb68492026-10-13 7cb6849 10,586 BA view · diff
git:20261012.bf143852026-10-12 bf14385 9,843 BA view · diff
git:20261010.2b564812026-10-10 2b56481 9,434 BA view · diff
git:20261008.476d4312026-10-08 476d431 20,792 BA view · diff
git:20261008.46573d12026-10-08 46573d1 20,824 BA view · diff
git:20261008.a46ff172026-10-08 a46ff17 20,791 BA view · diff
git:20261007.e2128c82026-10-07 e2128c8 20,762 BA view · diff
git:20261006.1d40d162026-10-06 1d40d16 20,779 BA view · diff
git:20261002.9c870f72026-10-02 9c870f7 20,787 BA view · diff
git:20261002.d51d2692026-10-02 d51d269 20,795 BA view · diff
git:20261002.4d5b1692026-10-02 4d5b169 20,798 BA view · diff
git:20260930.f01d31c2026-09-30 f01d31c 20,802 BA view · diff
git:20260930.211c8cf2026-09-30 211c8cf 20,790 BA view · diff
git:20260929.78e0caa2026-09-29 78e0caa 20,781 BA view · diff
git:20260928.1346db32026-09-28 1346db3 20,792 BA view · diff
git:20260928.7f9816e2026-09-28 7f9816e 20,764 BA view · diff
git:20260928.a452b702026-09-28 a452b70 20,792 BA view · diff
git:20260923.016a22c2026-09-23 016a22c 20,789 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11544 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

GitHub

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_niziebaacfbfdedl
GET https://markdownregistry.com/api/v1/resolve?ref=skillberry-ai/cap-evolve/agent-optimize
GET https://markdownregistry.com/api/v1/blob/cf4aa5fb1fb258c6e8967588198fff7082b321da18562028ce6e8573e2788b9b

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

CLAUDE.md CLAUDE.md file
skillberry-ai/cap-evolve · CLAUDE.md
git:20261005.6af27e2 · audit A · 66 stars
my_skill SKILL.md skill
skillberry-ai/cap-evolve · examples/tau2_custom/blackbox/seed_capability/my_skill/SKILL.md
git:20260924.bafd81b · audit C · 66 stars
my_skill SKILL.md skill
skillberry-ai/cap-evolve · examples/tau2_sierra_airline/blackbox/seed_capability/my_skill/SKILL.md
git:20261013.01104a5 · audit C · 66 stars
arithmetic-answers SKILL.md skill
skillberry-ai/cap-evolve · examples/toy_skill/seed_capability/SKILL.md · Answers a short arithmetic question with just the number. Use when the user asks to compute a sum, difference, or…
git:20260822.f0fb098 · audit A · 66 stars
llms.txt llms.txt file
skillberry-ai/cap-evolve · llms.txt
git:20260924.bafd81b · audit A · 66 stars
evograph SKILL.md skill
skillberry-ai/cap-evolve · skills/algorithms/evograph/SKILL.md · Deprecated agent-mode algorithm (evo-graph port): a weakness-graph search that dispatched one solver agent per failure…
git:20260904.802badb · audit A · 66 stars
gepa SKILL.md skill
skillberry-ai/cap-evolve · skills/algorithms/gepa/SKILL.md · Runs the GEPA optimization loop (arXiv:2507.19457) — sample-efficient reflective Pareto search. A cheap train-minibatch…
git:20260822.02a1a1d · audit A · 66 stars
hill-climb SKILL.md skill
skillberry-ai/cap-evolve · skills/algorithms/hill-climb/SKILL.md · Runs a global hill-climb optimization loop where the parent is always the current best candidate and the val…
git:20261012.bf14385 · audit A · 66 stars
skillopt SKILL.md skill
skillberry-ai/cap-evolve · skills/algorithms/skillopt/SKILL.md · Runs the SkillOpt single-lineage optimization loop, which organizes a hill-climb into epochs over mini-batches of train…
git:20260822.02a1a1d · audit A · 66 stars
mcp-tool SKILL.md skill
skillberry-ai/cap-evolve · skills/capabilities/mcp-tool/SKILL.md · Optimize the tool surface of an EXTERNAL MCP server — one the agent talks to but does not implement. Use when an agent…
git:20260822.10e53e1 · audit A · 66 stars
skill-package SKILL.md skill
skillberry-ai/cap-evolve · skills/capabilities/skill-package/SKILL.md · Optimize an Agent Skill package itself — its SKILL.md (frontmatter + body), its references, and its bundled scripts…
git:20261008.03e3727 · audit A · 66 stars
system-prompt SKILL.md skill
skillberry-ai/cap-evolve · skills/capabilities/system-prompt/SKILL.md · Optimize an agent's system prompt, developer message, or policy text — the instructions that shape its behavior. Use…
git:20261015.ac1f1f4 · audit A · 66 stars

Every file in skillberry-ai/cap-evolve

Browse by kind, by grade A, or by owner.