メニュー
Launch a model evaluation batch. Use when running interactive/foreground eval runs — parameter collection, pre-flight checks, execution, and post-run analysis. NOT for: long-running batches that need tmux isolation (use overnight-eval instead).
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/SamyakJhaveri/loam --skill eval-runコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Advisor for selecting an optimal model tier (Opus/Sonnet/Haiku) for a specific task. Use before launching an agent team, before a multi-file refactor, or when deciding whether to drop from Opus to Haiku for transactional work (commits, formatting). Analyzes reasoning depth, blast radius, domain expertise, output length, correctness cost. NOT for switching models mid-task once work is underway - it advises the allocation before you start.
Generate ranked, evidence-backed creative ideas the user has not asked for, aimed at a named goal, then execute the cheapest one immediately as proof. Use when the user says "surprise me", "what am I missing", "creative or elegant ideas", "how can we do this better", asks how to increase the chances of a goal succeeding, or asks "what are we not seeing/doing/thinking about" or "what capabilities do you have that I am not asking you to use yet". NOT for routine task execution, and never for ideas that only sound good but the user cannot verify.
Fast 30s session bootstrap briefing. Use when resuming work after any break, at the start of a fresh session, or when unsure of current project state. Reports git status, recent commits, environment state, memory-index staleness, pending tasks, and red flags (uncommitted changes, detached HEAD, stale memory). NOT for deep code exploration or planning - it only reports state, it does not change it.
SOC 職業分類に基づく
SKILL.md を表示中
| name | eval-run |
| description | Launch a model evaluation batch. Use when running interactive/foreground eval runs — parameter collection, pre-flight checks, execution, and post-run analysis. NOT for: long-running batches that need tmux isolation (use overnight-eval instead). |
| auto-activate | false |
Launch a model evaluation batch with automatic parameter collection, exclusion checks, API key verification, and post-batch analysis.
Trigger: When user types /eval-run with optional arguments.
$ARGUMENTS — optional shorthand or explicit flags for the eval script.
Omit entirely to be prompted interactively.Extract parameters from $ARGUMENTS. Prompt for missing required values.
| Parameter | Notes |
|---|---|
| Suite/dataset | Which benchmark suite or dataset to evaluate |
| Configuration | Model config, direction, or task variant |
| Models | Which models to evaluate |
| Samples | Number of samples per task |
| Resume | Whether to resume from previous partial run |
=== EVAL BATCH PRE-FLIGHT ===
Dataset: <name>
Models: <model1>, <model2>, ...
Config: <config details>
Exclusions: <N> known-failing cases excluded
Total tasks: <N models> x <N tasks> = <total>
API keys: all verified / <which missing>
Proceed? (yes / no / modify params)
Run the evaluation script with collected parameters. Monitor live output. If many consecutive failures appear, surface them to the user and confirm before continuing.
After batch completes:
/post-eval for full post-processing pipeline/overnight-eval for long-running campaigns/eval-grader for result classification