skills.rest
Unsupervisedcom
UnsupervisedcomOFFICIAL
Explore all skills by this author →
WebsiteGitHub

manual_tests.run_fire_tests

Execute six DeepWork 'should fire' tests in serial sub-agents with resets.

49|3|Updated Jan 11, 2026
Search Tags:#QA#test-automation#sub-agent#DeepWork#serial-execution#fire-tests
One-click install
npx skills add https://github.com/Unsupervisedcom/deepwork --skill manual-tests-run-fire-tests
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: manual_tests.run_fire_tests
Source: https://github.com/Unsupervisedcom/deepwork/tree/main/.claude/skills/manual_tests.run_fire_tests
Command: npx skills add https://github.com/Unsupervisedcom/deepwork --skill manual-tests-run-fire-tests

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the execution of six manual 'should fire' tests in serial sub-agents to verify that DeepWork rules fire correctly.

Core Features & Use Cases

  • Serial execution of test cases ensures isolation and predictable outcomes when validating hook behavior.
  • Sub-agent orchestration automatically spawns and monitors sub-agents to perform the required file edits and observe rule firing.
  • Automated result capture records per-test pass/fail, observed hook behavior, and resets the environment between tests.

Quick Start

Use the manual_tests.run_fire_tests skill to execute all six 'should fire' tests in serial sub-agents, recording results after each test. The workflow uses the Task tool to spawn sub-agents with model haiku and max_turns 5, then performs the prescribed reset steps between tests.

Frequently Asked Questions about manual_tests.run_fire_tests

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate 'should fire' tests in serial to validate DeepWork rules?▼

You can automate 'should fire' test execution by spawning serial sub-agents that perform file edits, observe rule firing, and record pass/fail outcomes. This validates DeepWork hook behavior while applying automated environment resets between each test run.

What is the best way to isolate test runs when validating hook behavior in QA scenarios?▼

Isolating test runs for hook behavior validation requires strict serial execution and automated environment resets after each test. This approach ensures predictable outcomes by preventing state overlap between individual test cases during QA validation.

Can I use sub-agents with specific constraints to run fire-tests?▼

Yes, running fire-tests uses sub-agent spawning configured with model haiku and a max_turns limit of 5. This enforces strict execution boundaries to observe hook behavior and generate a consolidated fire_results log.

How do I record results when executing manual test automation for rule firing?▼

Recording results during manual test automation involves capturing per-test pass or fail statuses and observed hook behavior. The workflow outputs a consolidated fire_results log after all six tests complete their serial execution.

Why do my hook behavior tests fail when running multiple cases without resets?▼

Hook behavior tests fail without resets because previous test states interfere with subsequent runs. Strict sequencing and per-test environment resets are required to maintain isolation and ensure predictable outcomes across all six test cases.

Related Skills

Explore More Software Engineering Skills→
UnsupervisedcomUnsupervisedcom
49

manual_tests.run_not_fire_tests

Run six manual safety tests in parallel Haiku sub-agents to verify no rules fire.

Official
Basic
GeneralReasoningGeneralReasoning
4

analyze-ci

Analyze failed GitHub Actions jobs for a pull request and output a failure summary.

Official
Intermediate
mtsatryanmtsatryan
1

qa-expert

Identify test coverage gaps and strengthen software quality across development lifecycles.

Community
Advanced
jmaglyjmagly
175

pytest-runner

Execute pytest test suites with coverage reporting and failure diagnostics.

Community
Intermediate