scenario-verification-harness
Applies the Robota scenario verification loop by checking scope, preserving canonical ownership, re-recording only when necessary, and stopping on strict-policy failures. Use when scenario files, example flows, or execution-path behavior changes.
Best use case
scenario-verification-harness is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Applies the Robota scenario verification loop by checking scope, preserving canonical ownership, re-recording only when necessary, and stopping on strict-policy failures. Use when scenario files, example flows, or execution-path behavior changes.
Teams using scenario-verification-harness should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/scenario-verification-harness/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How scenario-verification-harness Compares
| Feature / Agent | scenario-verification-harness | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Applies the Robota scenario verification loop by checking scope, preserving canonical ownership, re-recording only when necessary, and stopping on strict-policy failures. Use when scenario files, example flows, or execution-path behavior changes.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Scenario Verification Harness ## Rule Anchor - `AGENTS.md` > "Build Requirements" - `AGENTS.md` > "Execution Safety" - `AGENTS.md` > "Execution Caching" - `AGENTS.md` > "Harness Direction" ## Use This Skill When - Modifying scenario files or example workflows. - Changing execution behavior that may alter scenario output. - Reviewing whether a scenario-related change follows repository execution rules. ## Preconditions - Identify the owning package for the scenario or example. - Identify the example file and scenario identifier. - Prefer the owner package `scenario:verify` command when the scope exposes one. - Prefer the owner package `scenario:record` command when authoritative output must be refreshed. - Confirm whether the change is a real product behavior change or only a scenario-specific patch. - If re-recording is required, ensure the required environment variables are present. ## Execution Steps 1. Confirm the change belongs to a general workflow capability, not a scenario-only shortcut. 2. Check ownership: - no duplicate declarations - no side-channel identity fields when `ownerPath` encodes the relation - no inferred linkage or fallback path 3. If package source changed, build the affected package before verification. 4. Run the package-owned scenario verification command and compare its output with the canonical scenario record artifact. 5. If expected behavior changed intentionally, re-record the scenario using the package-owned record command, then verify again. 6. Treat re-record as an overwrite of the authoritative scenario artifact, not an append to stale output. 7. Stop immediately on: - non-zero exit - strict-policy logs - edge-order violations - missing or empty expected outputs ## Stop Conditions - The change exists only to satisfy a scenario artifact rather than the owned product behavior. - Verification logs contain `[STRICT-POLICY]`, `[EMITTER-CONTRACT]`, or `[EDGE-ORDER-VIOLATION]`. - Scenario outputs are missing, empty, or ambiguous. - The change introduces inferred linkage, delayed linkage, or duplicate suppression patterns. ## Checklist - [ ] Scenario change is justified by owned product behavior. - [ ] Ownership and `ownerPath` modeling remain canonical. - [ ] Affected package is built before verification when source changed. - [ ] Verification is run after any re-record. - [ ] Scenario artifacts are overwritten authoritatively when re-recording. - [ ] Strict-policy and missing-output failures stop the loop. ## Focused Examples ```bash pnpm --filter @robota-sdk/agent-core build ``` ```bash pnpm scenario:verify -- <example-file> <scenario-id> pnpm scenario -- record <example-file> <scenario-id> ``` If the owning package exposes a package-specific verification entrypoint, prefer that owner command over a guessed root alias. ## Anti-Patterns - Adding scenario-only fields, keywords, regex, or inference logic. - Appending to stale scenario outputs instead of overwriting them. - Re-recording without running verification afterward. - Treating a cache miss or verification failure as permission to silently run a live fallback path. ## Related Harness Commands - Current: `pnpm harness:verify -- --scope <packages/foo|apps/bar> --include-scenarios` - Current: `pnpm harness:record -- --scope <packages/foo|apps/bar>` - Current: package-owned scenario record and verify commands
Related Skills
pre-refactor-test-harness
Before modularizing or refactoring a package, analyze the code for extraction points, write characterization tests for current behavior, then modularize under test protection. Use when a package has monolithic files that need to be broken into testable modules.
harness-governance
Governs the Robota harness by checking rule-skill-owner consistency, finding undefined terminology, spotting examples that violate rules, and preferring mechanical checks over duplicated prose. Use when editing AGENTS, skills, or repository guidance.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
vitest-testing-strategy
Defines a practical testing strategy for TypeScript and JavaScript using Vitest across unit, integration, and type-level tests. Use when adding features, refactoring, or preventing regressions with fast feedback loops.
version-management
All packages must have the same version. Use changesets for coordinated version bumps. Never version packages independently.
vercel-react-native-skills
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
user-request-gate
Use immediately when the user requests any implementation, code change, feature addition, fix, or modification. Gates code writing behind a backlog draft document. Read-only exploration is always permitted.
type-boundary-and-ssot
Applies Robota's preferred workflow for trust-boundary validation, strict typing, quality gates, and owner-based SSOT reuse. Use when adding or reviewing type contracts, boundary parsing, shared contract ownership, or running quality checks.
tdd-red-green-refactor
Kent Beck's TDD workflow. Use when writing new code or modifying existing behavior. Enforces the Red-Green-Refactor cycle with small, verifiable steps.
task-tracking
Track work using task files in .agents/tasks/. Use when starting, progressing, or completing a task to maintain a persistent record of work.