メニュー
Deterministic custom subagent selection helper. Use when you need a reproducible, auditable decision on which custom subagents to activate for a user query (runs scripts/agent_evaluator.py).
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。
SOC 職業分類に基づく
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/arisng/github-copilot-fc --skill agent-evaluator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。
SKILL.md を表示中
| name | agent-evaluator |
| description | Deterministic custom subagent selection helper. Use when you need a reproducible, auditable decision on which custom subagents to activate for a user query (runs scripts/agent_evaluator.py). |
Evaluate a user query against the workspace's available subagents and return a JSON decision payload (activated/required/suggested agents and scoring).
Run the evaluator script (located in scripts folder relative this skill file) with the user query as an argument.:
python scripts/agent_evaluator.py "YOUR_QUERY_HERE"
Optional: include a contextual file path as the second argument:
python scripts/agent_evaluator.py "YOUR_QUERY_HERE" "path/to/file.ext"
activated_agentsrequired_agentssuggested_agentsevaluations (per-agent score + reasoning)Evaluate a query:
python scripts/agent_evaluator.py "Please help refine our custom instruction file"
Evaluate a query with file context:
python scripts/agent_evaluator.py "Update this instruction" "instructions/agent-forced-eval.instructions.md"
Drive a Machina state machine to a deterministic outcome on behalf of an AI agent. USE WHEN: a task is governed by a state machine (a machine definition JSON with states, transitions, guards, actions, tools, checks, scenarios); executing a workflow that must be deterministic and auditable; running a skill whose SKILL.md declares a `machina:` machine; firing events, checking status, satisfying evidence checks, verifying run integrity with `check`, or producing a terminal report for a machine-driven run; escalating a STUCK run to a human conductor. DO NOT USE FOR: authoring or scoring machine definitions (use machina-authoring); modifying the Machina simulator app or its engine (use machina-simulator); implementing or modifying the driver/runtime tooling such as `scripts/machine-driver.py` (engine development) unless you are a maintainer of this skill upgrading the driver itself; general diagramming or XState/SCXML authoring.
Author valid, high-scoring state machines in Machina machine JSON format (spec v3.0.0 / v2.0.0 / v1.0.0). USE WHEN: writing or generating a machine definition (states, transitions, guards, actions, context, scenarios); modeling a real workflow (order fulfillment, refunds, signup, retries) as a Machina state machine; fixing or upgrading a machine JSON for validation or higher compliance score; explaining validation failures or low scores; running the bundled machina-validator.py CLI to validate, score, or generate gaps/scenarios; adding retry guards or cycle protection; or preparing machines for the compliance scorer ("Excellent" ≥90). DO NOT USE FOR: modifying the Machina simulator app, its engine, UI, or SPEC_REGISTRY (use machina-simulator-maintenance), debugging machine-validator.py scripts, XState config authoring, SCXML documents, or general diagramming.
Spawn a new isolated Copilot CLI sub-session from a main Copilot CLI or VS Code session. Use when you need to programmatically create, resume, or chain Copilot CLI sessions with explicit control over session ID, custom agent, model, BYOK provider profile, permissions, and working directory. Triggers: "invoke copilot", "spawn copilot", "copilot sub-session", "programmatic copilot cli", "programmatic copilot subprocess", "copilot cli session id", "resume copilot session", "chain copilot sessions", "isolated copilot session", "subagent copilot cli", "task copilot cli".