best-of-n SKILL.md skillA
best-of-n from x1jiang/clawagents_py is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add x1jiang/clawagents_py/best-of-n@git:20260716.365ef3dPins git:20260716.365ef3d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- x1jiang/clawagents_py
- Path
src/clawagents/skills/best-of-n/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260716.365ef3d, committed Jul 16, 2026
- Size
- 1,649 bytes
- Repository stars
- 18
- License
- MIT
Implement a task N ways in parallel and pick the best. Spawns multiple subagents in isolated worktrees, evaluates candidates, and applies the winner. Use when asked to "best of n", "try multiple approaches", "parallel implementations", "/best-of-n", or "/bon".
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
# /best-of-n — Parallel Implementation Tournament
Implement a task multiple different ways in parallel, evaluate all candidates,
and apply the best one.
## Usage
`/best-of-n [N] <task>`
- If the first token is a number 2–8, it sets the candidate count; the rest is the task.
- If omitted, N defaults to 3.
## Steps
1. Parse **N** (default 3, clamp 2–8) and the **task description**.
2. Spawn **N** subagents in one turn (parallel tool calls). For each candidate use `task` with:
- `isolation`: `"worktree"`
- `description`: `"Candidate <i>"`
- `prompt`: the task plus
`"You are candidate <i> of <N>. Implement fully. Summarize approach and files changed."`
3. Wait for all candidates (`get_task_output` / wait semantics if available).
4. Evaluate each on: correctness → completeness → simplicity → risk.
5. Apply the winner's changes into the main workspace (review diffs; merge carefully).
6. End with `WINNER: <number>` (1–N).
## Guardrails
- Do not claim a winner without reading each candidate summary.
- Prefer the smallest correct change when quality ties.
- If all candidates fail, report failure — do not invent a merge.Read the whole file at its exact version.
How to install
mdr add x1jiang/clawagents_py/best-of-n@sha256:eec208e7b53218bfThe line at the top of this page pins the label git:20260716.365ef3d, 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_2mvpna5e3jq5ciia)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 16, 2026.
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 (1649 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
x1jiang/clawagents_py · 18 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2mvpna5e3jq5ciia GET https://markdownregistry.com/api/v1/resolve?ref=x1jiang/clawagents_py/best-of-n GET https://markdownregistry.com/api/v1/blob/eec208e7b53218bf87c5a8e9bd0b67f9b25c230ebfa0bc7051519535cd1a2842
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.