Scenario Lab
Apps & Automationscenario-labScenario Lab is an Agent Skill for apps & automation published in the YSLAB-ai/scenario-lab repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use the local Scenario Lab CLI from Claude Code without loading full run artifacts into active context.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/YSLAB-ai/scenario-lab/blob/HEAD/adapters/claude/scenario-lab/skills/scenario-lab/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/scenario-lab, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
- 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 full 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, andscenario-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 returnedturnas 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_actionas the default next runtime action andturn.actionsas 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, orscenario-lab draft-ingestion-planin the normal path. Consume those payloads only through the packaged runtimeturn.context. - When the evidence-stage runtime context includes
ingestion_recommendations, prefer--action batch-ingest-recommendedbefore--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. Preferscenario-lab summarize-revision/scenario-lab summarize-runbefore opening 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, andscenario-lab generate-reportremain available for inspection or manual recovery outside the packaged runtime path.save-evidence-draftnow also accepts repeated--item-jsonpayloads for direct structured evidence replacement when a file handoff is unnecessary.