qe-judge
Gives an independent qestack verdict on the tagged tests of one feature with the qe-test-judge agent and the rubric, and changes no code. Use in a qestack repository when the user asks if the tests of a feature are correct or trustworthy. Not for a whole untagged suite (use qe-audit).
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- qe-judge
- license
- Apache-2.0
- description
- Gives an independent qestack verdict on the tagged tests of one feature with the qe-test-judge agent and the rubric, and changes no code. Use in a qestack repository when the user asks if the tests of a feature are correct or trustworthy. Not for a whole untagged suite (use qe-audit).
- argument-hint
- [feature, for example 003-order-discount]
- compatibility
- Needs the qestack engine (Python 3.11+), git and a shell. Full guard only in Claude Code.
03 SKILL.md 正文
qe-judge
Steps
- Preflight. Do the preflight of the
qestackskill. The feature is$ARGUMENTS. If it is empty, find it as the preflight says. - Scope. The tests in scope carry the feature tag (
qestack context --feature <feature>showsfeature_tag). If the tests have no tags, useqe-auditinstead, or help the user add tags first. - Fresh gate data. Run
qestack lint --feature <feature>andqestack trace --feature <feature>. If mutation or seeded-fault results are older than the tests, say so: the judge gives better scores with fresh data. - Judge. Start
qestack:qe-test-judge(Feature, Mode: test-review, Iteration: n). Use n = the next number after the last entry in<runs_dir>/history.jsonl, or 1. - Score. Run
qestack score --feature <feature> --iteration <n>. This adds an entry tohistory.jsonl, which a laterqe-hardenrun counts. Tell the user. - Report: verdicts (accept, revise, reject), the most important findings with file and line, suspected product bugs, and the judge gate status. Offer
qe-hardento fix the findings.
Rules
- The judge must not be the agent that wrote the tests in this session. If you wrote the tests yourself in this conversation, say so and still use the separate judge agent.
- Do not change tests in this skill.
- For a review from many angles outside the gated workflow (no feature tag, no engine), use the
test-review-panelskill. It gives findings, not a gate verdict.
04 同仓库更多 Skills
unit-testing
Writes, fixes or improves unit tests for rules, calculations, validation and state logic: arrange-act-assert, exact oracles, boundary sets, doubles only at boundaries, controlled clock and randomness. Use when the user says 'write unit tests', 'TDD this' or 'mock this dependency'. Not for HTTP endpoints (use api-testing).
ui-automation
Writes, fixes or structures browser end-to-end tests for critical journeys: role, label or test ID locators, auto-waiting assertions, API data setup, page objects, auth reuse and traces. Use when the user says 'UI test', 'end-to-end test' or 'our UI tests are brittle'. Not for business rules (use unit-testing).
testcase-reviewer
Reviews automated tests or manual test cases like a senior test architect: scores fidelity, oracles, assertion depth, edge cases and determinism, and finds tests that pass on wrong code. Use when the user says 'review my tests', 'test smells' or 'review AI-written tests'. Not for fault injection (use mutation-probe).
testability-review
Scores how testable a feature, module or design is before tests exist (seams for clock, randomness and network, hidden state, observability) and gives the smallest production change per blocker. Use when the user asks 'is this testable' or 'why is this hard to test'. Not for writing the tests (use unit-testing).
test-strategy
Writes a test strategy for a product, system or team: quality goals, test levels and their share, environments, data, automation scope, non-functional testing, metrics and a roadmap. Use when the user says 'test strategy' or 'QA strategy'. Not for one sprint or release plan (use test-planning).
test-runner
Finds how a project runs its tests, runs the right subset, and triages each failure as product bug, test defect, environment problem or flaky test, with evidence. Use when the user says 'run the tests' or asks 'which tests fail and why'. Not for pipeline design (use ci-cd-integration).