gepa SKILL.md skillA
gepa 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/gepa@git:20260822.02a1a1dPins git:20260822.02a1a1d 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/gepa/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260822.02a1a1d, committed Aug 22, 2026
- First version recorded
- Jun 17, 2026
- Size
- 10,528 bytes
- Repository stars
- 66
- License
- Apache-2.0
Runs the GEPA optimization loop (arXiv:2507.19457) — sample-efficient reflective Pareto search. A cheap train-minibatch pre-gate decides whether a proposal is worth an expensive val evaluation, and parents are sampled from a per-instance frontier so specialists survive instead of being averaged away. Use when rollouts are expensive and the scorer returns informative per-task feedback, and you want the most quality per evaluation. Use hill-climb instead for a first baseline run or for…
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
# gepa — sample-efficient reflective Pareto search `algorithms/hill-climb` owns the mechanics every algorithm shares: parent → proposal → val gate → commit, specified once in `algorithms/hill-climb/references/run-step.md`. Read that first. This page states only what GEPA (Agrawal et al., 2025) does **differently**, and why those differences are the paper's actual contribution rather than decoration. A thin wrapper over `cap_evolve.gepa.gepa_loop`. ## The two mechanisms, and why removing either turns GEPA back into hill-climb **1. The parent is sampled from per-instance winners, not from the global best.** A mean is a lossy summary. A candidate that fixes one genuinely hard task while regressing three easy ones has a *worse* mean than the incumbent, so a best-parent rule discards it — and with it the only text in the pool that has ever solved that task. GEPA instead scores per val instance and samples frequency-weighted over candidates that (co-)win at least one, so specialists and stepping-stones stay reachable as parents while their mean is still behind. That is the quality-diversity argument (MAP-Elites): keep the *set* that covers the …
Read the whole file at its exact version.
How to install
mdr add skillberry-ai/cap-evolve/gepa@sha256:962bd00bb6174757The line at the top of this page pins the label git:20260822.02a1a1d, 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_jwgdlvvds6zjyu27)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jun 17, 2026 and Aug 22, 2026, about one every 17 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260822.02a1a1d latest | 2026-08-22 | 02a1a1d | 10,528 B | A | view · diff |
| git:20260822.1806da1 | 2026-08-22 | 1806da1 | 9,927 B | A | view · diff |
| git:20260722.855c6a5 | 2026-07-22 | 855c6a5 | 7,406 B | A | view · diff |
| git:20260722.5d6d913 | 2026-07-22 | 5d6d913 | 7,004 B | A | view · diff |
| git:20260617.4ea12e7 | 2026-06-17 | 4ea12e7 | 6,432 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 (10528 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_jwgdlvvds6zjyu27 GET https://markdownregistry.com/api/v1/resolve?ref=skillberry-ai/cap-evolve/gepa GET https://markdownregistry.com/api/v1/blob/962bd00bb6174757f70502e1a96b89033ffd76838b3201551cc2fbae4bc3d361
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.