capability-execute-manual-tests

Executes manual test suites against released artifacts and generates structured PASS/FAIL reports.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/learnn-com/engineering-kb --skill capability-execute-manual-tests-learnn-com
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: capability-execute-manual-tests
Source: https://github.com/learnn-com/engineering-kb/tree/main/.skills/capability-execute-manual-tests
Command: npx skills add https://github.com/learnn-com/engineering-kb --skill capability-execute-manual-tests-learnn-com

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Running a project's manual test suite by hand after each release is slow, inconsistent, and hard to audit. This Skill automates the execution of critical-path test cases against released artifacts (websites, CLI packages, registries) and produces a standardized, evidence-backed report. ## Core Features & Use Cases - Automated Suite Execution: Discovers CP*.md critical path files, resolves variables like version and base URL, and runs each test case with PASS/FAIL/BLOCKED verdicts. - Adaptive Tooling: Selects the best available tool per action (agent-browser, Playwright MCP, curl, Bash) and gracefully degrades when tools or network access are missing. - Structured Reporting: Generates a report from the manual-test-report template with per-CP summaries, failure evidence, and an overall PASS/FAIL result stored under .tmp/manual-test-reports/. - Use Case: After publishing release v1.0.1 of your CLI, invoke this Skill to run all P0 blocker tests against the published package and website, then attach the generated report to your release review. ## Quick Start Run the manual test suite in the qa directory against version 1.0.1 and generate the execution report.

Frequently Asked Questions about capability-execute-manual-tests

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

FAQPage Schema
How do I run a manual test suite against a released version?▼

Point the Skill at your test suite directory containing CP*.md critical path files, optionally passing the version under test. It resolves variables, executes each test case, and writes a structured report to .tmp/manual-test-reports/.

How to limit manual test execution to critical tests only?▼

Use the scope argument to select specific critical paths (e.g. CP1,CP2) and the priority argument to set a minimum level. Setting priority to P0 runs only blocker tests, which is the default for post-merge validation.

What happens if browser automation tools are not available?▼

The Skill falls back from agent-browser to Playwright MCP, then to WebFetch or curl for HTTP checks. Tests requiring unavailable interactive tools are marked BLOCKED rather than failing the run.

Can manual test execution run without internet access?▼

Yes, but tests requiring network access such as website, registry, or download checks are skipped and marked BLOCKED with a reason. Local tests like CLI execution and file checks still run normally.

Why are some manual tests marked BLOCKED instead of FAIL?▼

Tests are marked BLOCKED when a precondition test failed, a required variable cannot be resolved, or the needed tool is unavailable. BLOCKED indicates the test could not execute, not that the artifact failed.