yak-bench SKILL.md skillA
yak-bench from webreactiva/yesyak is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add webreactiva/yesyak/yak-bench@git:20261030.4afff19Pins git:20261030.4afff19 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- webreactiva/yesyak
- Path
.claude/skills/yak-bench/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261030.4afff19, committed Oct 30, 2026
- First version recorded
- Oct 22, 2026
- Size
- 14,276 bytes
- Repository stars
- 3
- License
- MIT
Internal benchmark of this repository. It takes a small real project, drives a weaker agent (OpenCode in tmux, as a puppet) through the YesYak process to build a feature or fix a bug, acting as the human user, then scores the run, records it in bench/LOG.md, turns the confirmed findings into skill changes and cuts a release. Use it whenever the user asks to run the benchmark, repeat it, "otra vuelta", test YesYak on a project, measure the process, or apply what the last runs found.
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
# Yak bench The goal is always to improve YesYak. A run is evidence; a skill change is the result. This skill belongs to this repository only. It is not in `skills/`, so `install.sh` never copies it to other projects. ## Roles - **You are the human.** You choose the project and the task, answer the agent's questions, approve or reject, and correct it when a real user would. You never do its work, never edit its files, and never name a skill or a step that a real user would not name. - **The puppet** is OpenCode with a cheaper model, or Claude Code (`turn-claude.sh`) when the user asks for it. It sees only the project and a frozen copy of `skills/`: no global skills, plugins, MCP servers or CLAUDE.md (`turn.sh` isolates it). A weaker model shows where the skills are not clear enough. ## Tools All in `scripts/`. Runs live in `.scratchpad/bench/<run-id>/` of this repository (ignored by git). The clone itself lives in `/Users/Shared/yak-bench/<run-id>` and `repo` links to it: OpenCode reads `.agents/skills` in every parent folder, so a clone inside the user's home would see the user's own skills. | Script | Does | | --- | --- | …
Read the whole file at its exact version.
How to install
mdr add webreactiva/yesyak/yak-bench@sha256:f42f005a80615431The line at the top of this page pins the label git:20261030.4afff19, 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_gtraufupkqdydrgn)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Oct 22, 2026 and Oct 30, 2026, about one every 2 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261030.4afff19 latest | 2026-10-30 | 4afff19 | 14,276 B | A | view · diff |
| git:20261023.f220ca2 | 2026-10-23 | f220ca2 | 13,865 B | A | view · diff |
| git:20261022.75ef8c7 | 2026-10-22 | 75ef8c7 | 13,646 B | A | view · diff |
| git:20261022.d8e44da | 2026-10-22 | d8e44da | 13,343 B | A | view · diff |
| git:20261022.a088e01 | 2026-10-22 | a088e01 | 12,661 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 (14276 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
webreactiva/yesyak · 3 stars · license MIT · pushed 2026-10-31 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gtraufupkqdydrgn GET https://markdownregistry.com/api/v1/resolve?ref=webreactiva/yesyak/yak-bench GET https://markdownregistry.com/api/v1/blob/f42f005a80615431ee50c779d1a5647c53f909629d2694ecc77b2bed854f7829
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.