Individual skill
skill-benchmark
Use when the user runs /skill-benchmark to score skills, compare models, or gate a skill release. Modes: score (default) and gate. Not for editing skills: use agent-surface-forge.
.devin/skills/skill-benchmark/SKILL.md
Source commit b0e8ce89a19fac880251dc3ea1babfeb4503a4fe
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 55
- Repository last updated
- Sep 28, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- odd Repository topic
- odin Repository topic
- outline Repository topic
- outlines Repository topic
- coding-paradigm Repository topic
- outline-driven-development Repository topic
- claude-plugins Repository topic
- codex-cli Repository topic
- gemini-cli-extensions Repository topic
- outline-driven Repository topic
- writing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 11,341 bytesagents/openai.yamlasset · 209 bytes
Read excerpt
# Skill benchmark
## Contract
| Field | Bound contract |
|---|---|
| Trigger | The user runs /skill-benchmark to score skills via LLM judges, compare candidate models on a shared task set, or gate a skill release. |
| Authority | Human-gated: previews the benchmark target, judge or candidate models, rubric or task set, and estimated spend before any LLM call; in gate mode, may open follow-up issues after confirmation. Every other write is reversible local, with version control as rollback. No remote mutation without explicit human confirmation in gate mode; no remote mutation in score mode. |
| Side effect | Writes benchmark artifacts under `.odin/benchmark-reports/` and incurs LLM inference spend; in gate mode, also writes gate logs and run-log entries and may open follow-up issues. |
| Done | A scored skill-quality report or model-comparison table (score mode) or a reproducible PASS/FAIL record (gate mode) is written and returned to the human. |
## Inputs
- **Mode** (required): `score` (default) or `gate`.