hill-climb SKILL.md skillA
hill-climb 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/hill-climb@git:20261012.bf14385Pins git:20261012.bf14385 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/hill-climb/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261012.bf14385, committed Oct 12, 2026
- First version recorded
- Jun 17, 2026
- Size
- 9,899 bytes
- Repository stars
- 66
- License
- Apache-2.0
Runs a global hill-climb optimization loop where the parent is always the current best candidate and the val significance gate decides acceptance. Use as the algorithm for most runs — the first run on a new project, binary pass/fail scorers, and small task sets. Pick how each iteration's reflection is focused with --focus all (every failing val task), cyclic (one task at a time), or hardest-first (lowest-scoring first). Switch to gepa when rollouts are expensive and per-task feedback is rich…
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
# hill-climb — one loop, three focus schedules Greedy search over candidates: the parent is always the run's current best, and a child replaces it only by clearing the val significance gate. The test split is never touched here — that is `finalize`. **Requires `baseline` first.** Without `--resume` the loop reads the seed's val result from `<run-dir>/baseline.json` (`scripts/run.py:121-122`); with no run state it raises `FileNotFoundError: no run state at .../state.json`. `--resume` instead reads the current best's val from its stored rollouts, falling back to `baseline.json` when the run has no best yet (`run.py:118-122`). ## One iteration, end to end This is the mechanism the other algorithm skills vary; they describe only their differences and point back here. One iteration is `harness.run_step` (`core/cap_evolve/harness.py:1409`): 1. **Pick the parent — always the current best** (`harness.py:2224`, `run_dir.candidate_dir(run_dir.best_id)`). Copy it to `work/<cand_id>/`; the optimizer edits that copy in place, so the parent is never mutated (`harness.py:1454-1458`). 2. **Build the prompt.** The parent's val per-task rows are split into …
Read the whole file at its exact version.
How to install
mdr add skillberry-ai/cap-evolve/hill-climb@sha256:3b9cf4bcd3d77142The line at the top of this page pins the label git:20261012.bf14385, 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_hq2ehu3rt574d5ku)
3 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 Oct 12, 2026, about one every 29 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261012.bf14385 latest | 2026-10-12 | bf14385 | 9,899 B | A | view · diff |
| git:20260822.57eed81 | 2026-08-22 | 57eed81 | 9,232 B | A | view · diff |
| git:20260822.ae71aa8 | 2026-08-22 | ae71aa8 | 9,188 B | A | view · diff |
| git:20260722.5d6d913 | 2026-07-22 | 5d6d913 | 3,395 B | A | view · diff |
| git:20260617.92b5c65 | 2026-06-17 | 92b5c65 | 2,780 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 (9899 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_hq2ehu3rt574d5ku GET https://markdownregistry.com/api/v1/resolve?ref=skillberry-ai/cap-evolve/hill-climb GET https://markdownregistry.com/api/v1/blob/3b9cf4bcd3d77142451e8581bbbee7d0f55d07a27cded43d57b8438dfd6d83c4
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.