test
Use this skill after implementation passes the quality gate and the user wants verification. Runs capability-based checks from the task document, including unit, integration, browser, API, CLI, CI, or manual checks, and writes docs/testing/*.md.
How do I install this agent skill?
npx skills add https://github.com/eljun/claude-workflow-skills --skill testIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill facilitates testing and verification by reading task documentation and running associated commands. It presents a surface for indirect prompt injection because it processes untrusted data from the repository without strict sanitization or clear boundary markers.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
test - Verification Stage
Invariants
- Verify against the task document acceptance criteria.
- Use the best available project verification path.
- Do not require one specific browser automation tool in core workflow.
- Always write one final report to
docs/testing/. - When tests pass and the user approves, update
TASKS.mdtoApprovedand re-read the tracker to confirm the row moved. A stale tracker blocks downstream and headless sessions.
Runtime adapters may expose this stage as a slash command, menu action, or natural-language skill invocation. The portable stage name is test.
Workflow
- Read
AGENTS.md. - Resolve the task ID and read
docs/task/{ID}-{task-name}.md. - Confirm the task reached the quality gate.
- Build a verification plan from
Acceptance CriteriaandVerification Approach. - Prefer existing project commands and CI-compatible checks.
- Run safe verification commands.
- Use browser automation or manual checks only when required by the task.
- Write
docs/testing/{ID}-{task-name}.mdfrom the project'sdocs/templates/test-report.mdif it exists, otherwise fromtemplates/test-report.mdbundled next to this file. - Move the task to
Approvedonly after tests pass and the user approves, or leave it inTestingif fixes are needed. - If the move was made, re-read
TASKS.mdand verify the task row is inApprovedand absent fromTesting. If the row is not in the expected section, the move was missed — perform the edit now before handoff.
Verification Priority
Use the narrowest reliable check first:
- Unit tests for pure logic.
- Integration tests for API, database, service, or cross-module behavior.
- Browser or end-to-end checks for user-visible workflows.
- Static checks such as typecheck, lint, or build where they are part of project quality.
- Manual inspection only when automation is unavailable or not cost-effective.
If no viable verification path exists, write a BLOCKED report explaining what is missing.
Evidence Rules
- Run each criterion's check and compare it with the task doc's
Baseline. Record both values. A criterion passes only when its check ran and showed the expected result. - Grade the oracle. A check that asserts source text, file structure or a mock's call count shows the code has a shape, not that it behaves. Mark such results weak evidence and, where a behaviour or output check is possible, run that instead.
- No-regression checks are required, not optional: re-run the behaviour the task says must not change.
- Never mark PASS from reasoning alone. If a check couldn't run, the result is SKIPPED or BLOCKED, with the reason.
Live Verification
Passing tests show the code is right; they don't show the change is live. When the change ships through separately deployed parts (services, functions, workers, migrations):
- Verify output in the running system (the rows, messages or records the change should produce), not liveness (status codes, "job succeeded", a deployed version number).
- Name any check that needs a deploy or an owner action first as Deferred, with the exact step, instead of marking it PASS.
Report Rules
- Write the final report only under
docs/testing/. - Do not scatter temporary reports in the repo root.
- Record commands exactly as run.
- Record skipped checks with reasons.
- Include enough evidence for the implementation stage to fix failures without session history.
Handoff
PASS:
Verification passed for task {ID}
Report: docs/testing/{ID}-{task-name}.md
Next stage after user approval: document {ID}
FAIL or BLOCKED:
Verification failed or blocked for task {ID}
Report: docs/testing/{ID}-{task-name}.md
Return to implementation with the report context.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/eljun/claude-workflow-skills/test">View test on skillZs</a>