scenario-lab

Agent Skills › YSLAB-ai/scenario-lab › scenario-lab

scenario-lab

GitHub

指导使用 Scenario Lab CLI 进行场景实验运行、证据管理与报告生成的工作流。通过结构化适配器驱动确定性对话循环，避免手动编排底层命令，支持从启动运行到模拟审查的全流程自动化操作。

adapters/codex/scenario-lab/skills/scenario-lab/SKILL.md YSLAB-ai/scenario-lab

Trigger Scenarios

需要创建或检查场景实验运行记录处理场景实验室的证据摄入与批准流程使用 Scenario Lab CLI 进行自动化测试或仿真

Install

npx skills add YSLAB-ai/scenario-lab --skill scenario-lab -g -y

More Options

Non-standard path

npx skills add https://github.com/YSLAB-ai/scenario-lab/tree/main/adapters/codex/scenario-lab/skills/scenario-lab -g -y

Use without installing

npx skills use YSLAB-ai/scenario-lab@scenario-lab

指定 Agent (Claude Code)

npx skills add YSLAB-ai/scenario-lab --skill scenario-lab -a claude-code -g -y

安装 repo 全部 skill

npx skills add YSLAB-ai/scenario-lab --all -g -y

预览 repo 内 skill

npx skills add YSLAB-ai/scenario-lab --list

SKILL.md

Frontmatter

{
    "name": "scenario-lab",
    "description": "Use the local Scenario Lab CLI to create and inspect scenario runs from curated evidence."
}

From the checked-out Scenario Lab repo/workspace, create or activate a Python 3.12+ virtualenv and install the shared core package with pip install -e 'packages/core[dev]'.
Use the query-style commands to drive the workflow instead of loading raw run artifacts into active context.
Prefer direct structured input over temporary JSON files for the normal adapter path.
The underlying raw commands still exist, including scenario-lab start-run, scenario-lab save-intake-draft, and scenario-lab draft-conversation-turn, but the packaged runtime is the normal path.
Bootstrap a workflow slice with scenario-lab run-adapter-action --root <root> --run-id <run> --revision-id r1 --action start-run --domain-pack <slug>.
after each workflow mutation, keep using scenario-lab run-adapter-action --root <root> [--candidate-path <dir>] --run-id <run> --revision-id <rev> --action <action-name> ... and treat the returned turn as the user-facing next step. The default evidence corpus is <root>/corpus.db; only pass --corpus-db <db> when intentionally using a separate evidence database.
Use turn.recommended_runtime_action as the default next runtime action and turn.actions as the ordered set of allowed next steps. This keeps the conversation loop deterministic without manually sequencing raw workflow commands.
Do not manually sequence scenario-lab draft-intake-guidance, scenario-lab draft-retrieval-plan, or scenario-lab draft-ingestion-plan in the normal path. Consume those payloads only through the packaged runtime turn.context.
When the evidence-stage runtime context includes ingestion_recommendations, prefer --action batch-ingest-recommended before --action draft-evidence-packet. If no corpus exists yet, first save gathered evidence files under <root>/evidence-candidates/ and pass that directory as --candidate-path. Then trim the packet in place with --action curate-evidence-draft.
After approval, keep using the packaged runtime to reach simulation, report review, and begin-revision-update. Prefer scenario-lab summarize-revision / scenario-lab summarize-run before reading full report files.
Raw commands such as scenario-lab draft-evidence-packet, scenario-lab curate-evidence-draft, scenario-lab draft-approval-packet, scenario-lab approve-revision, scenario-lab begin-revision-update, scenario-lab simulate, scenario-lab summarize-run, scenario-lab summarize-revision, scenario-lab save-evidence-draft, and scenario-lab generate-report remain available for inspection or manual recovery outside the packaged runtime path. save-evidence-draft now also accepts repeated --item-json payloads for direct structured evidence replacement when a file handoff is unnecessary.