Skip to content

jscraik/Agent-Skills / Infrastructure/tests/fixtures/skills_sdk/scenario_quality_skill

skills-sdk-scenario-quality-fixture

Verified

Fixture skill with promotable eval scenario metadata.

FileKindSize
SKILL.mdskill md213 B
references/evals.yamlconfig983 B

references/evals.yaml

View on GitHub
schema_version: '2.0'
skill_name: skills-sdk-scenario-quality-fixture
cases:
  - id: happy-scenario-quality
    name: Happy scenario quality
    category: happy
    unit: package evidence boundary
    eval_modes:
      - smoke
    realistic: true
    should_trigger: true
    prepend_skill: true
    given: A skill maintainer has a package-shape receipt but no current validation output.
    should: Produce evidence-backed validation output without claiming release readiness.
    prompt: A skill maintainer needs a concise validation summary for a package-shape receipt that does not include current runtime or hosted evidence. Explain what can be claimed and what remains unproven.
    deterministic_checks:
      forbidden_commands:
        - curl
        - wget
        - rm -rf
    acceptance:
      - type: expected_signal
        value: Separates package-shape evidence from runtime or hosted readiness claims.
      - type: regex
        value: '(?is)(evidence|validation)'
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall