performance:hill-climb SKILL.md skillA
performance:hill-climb from bendrucker/claude is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add bendrucker/claude/performance:hill-climb@git:20261027.72c2866Pins git:20261027.72c2866 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- bendrucker/claude
- Path
plugins/performance/skills/hill-climb/SKILL.md- Versions recorded
- 10
- Latest version
- git:20261027.72c2866, committed Oct 27, 2026
- First version recorded
- Sep 28, 2026
- Size
- 12,404 bytes
- Repository stars
- 18
- License
- MIT
Use when asked to hill-climb a program, or to make software faster or leaner (runtime, startup, throughput, memory, bundle size) through repeated measured changes, including resuming a climb from its notes file. For prompts or skills scored by an eval suite, use evals:hill-climb.
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 Goal: a program that is measurably better on the metric the user cares about, where every accepted change carries evidence that it beat run-to-run noise, kept behavior identical, and holds on inputs the climb never tuned against. The user stays in the loop at fixed checkpoints and can reconstruct every decision from one notes file. This skill is the workflow. Load `performance:benchmark` to build the harness and compare arms, and `performance:profile` to find where the time goes. A repo's own benchmark conventions take precedence over the defaults here. ## Arguments - `<target>`: the program or command to climb. Required. - `<notes file>`: where the climb log lives. Default: `CLIMB.md` beside the benchmark harness, or `tmp/climb.md` when the repo has no harness directory. When it already exists, resume from it: skip the Frame items its Rules settle, and keep the line under its title that tells a later session to load this skill. ## Frame Interview the user until each item below is settled and none rests on your assumption: - Ask in rounds with `AskUserQuestion`, one question per open decision. - Settle every item before building anything. …
Read the whole file at its exact version.
How to install
mdr add bendrucker/claude/performance:hill-climb@sha256:4bfbba1e62d85b27The line at the top of this page pins the label git:20261027.72c2866, 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_ab2erasrdtb2tk4w)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Sep 28, 2026 and Oct 27, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261027.72c2866 latest | 2026-10-27 | 72c2866 | 12,404 B | A | view · diff |
| git:20261027.1a0b6ab | 2026-10-27 | 1a0b6ab | 12,408 B | A | view · diff |
| git:20261027.cc75598 | 2026-10-27 | cc75598 | 12,469 B | A | view · diff |
| git:20261027.e2a1460 | 2026-10-27 | e2a1460 | 11,896 B | A | view · diff |
| git:20261027.57d8368 | 2026-10-27 | 57d8368 | 11,271 B | A | view · diff |
| git:20261018.24be224 | 2026-10-18 | 24be224 | 10,560 B | A | view · diff |
| git:20261016.7c36c71 | 2026-10-16 | 7c36c71 | 10,167 B | A | view · diff |
| git:20261016.66632a4 | 2026-10-16 | 66632a4 | 9,997 B | A | view · diff |
| git:20261016.67e26c6 | 2026-10-16 | 67e26c6 | 9,903 B | A | view · diff |
| git:20260928.edc0532 | 2026-09-28 | edc0532 | 8,360 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 (12404 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
bendrucker/claude · 18 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ab2erasrdtb2tk4w GET https://markdownregistry.com/api/v1/resolve?ref=bendrucker/claude/performance:hill-climb GET https://markdownregistry.com/api/v1/blob/4bfbba1e62d85b27ea3edf0d23cc243fe3712470162b4e39c866d7e8c5357ff0
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.