AGENT SKILL

qe-grill-spec

Checks a spec before qestack test design: finds requirements without IDs, vague rules, missing examples and missing error behavior, and asks one question at a time. Use before qe-plan in a qestack repository, or when a spec has [NEEDS CLARIFICATION] items.

License 许可
Apache-2.0
所属仓库
quark-sri/qestack
最近更新
2026-11-14
Stars
★ 1
Forks
0

01 前言 Front Matter

name
qe-grill-spec
license
Apache-2.0
description
Checks a spec before qestack test design: finds requirements without IDs, vague rules, missing examples and missing error behavior, and asks one question at a time. Use before qe-plan in a qestack repository, or when a spec has [NEEDS CLARIFICATION] items.
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-grill-spec

Good tests need clear rules and concrete examples. This skill finds the gaps in the spec before anyone designs tests. It does not write tests.

Steps

  1. Feature. The feature is $ARGUMENTS. If it is empty, find the folder under specs/ (speckit layout: specs/<NNN-name>/spec.md). If it is not clear, ask the user.
  2. IDs. Run qestack trace --feature <feature> --plan-only. Use only the list of requirement IDs that it prints. Before a test plan exists, every ID shows "MISSING IN PLAN" and the exit code is 1. That is expected. Requirements without an ID are not traceable.
  3. Read spec.md, and contracts/ and data-model.md if they exist. For each requirement, check:
    • ID: It has an ID (FR-###, or a numbered acceptance scenario under a "User Story" heading).
    • Example: It has at least one concrete example with input and expected output.
    • Limits: Each number, size or date limit says if the limit itself is included.
    • Errors: Invalid input has a defined result (status, error code, message key).
    • Effects: It says what is saved, what events are sent, and what does NOT change on failure.
    • Measurable: It has no vague words ("fast", "user-friendly", "appropriate", "etc.").
    • Conflicts: It does not contradict another requirement or a contract.
  4. Make a numbered list of gaps, highest risk first (money, security, data integrity).
  5. Ask the user about the gaps, one question at a time. For each question, suggest a concrete answer that the user can accept or change.
  6. Collect the answers. Show the proposed spec changes as a diff. Write them to spec.md only after the user says "yes". (With speckit, the user can also run /speckit.clarify.)
  7. Open gaps. For each gap that is still open, propose a marker [NEEDS CLARIFICATION: <question>] at the requirement in spec.md. Add the markers after the user says "yes". The engine and qe-plan read these markers, and the test plan lists them as open questions.
  8. Report: gaps found, gaps closed, open markers added. Next step: qe-plan.

Rules

  • Do not invent business rules. Ask.
  • Do not read the implementation to "find" the rule. The spec is the source of truth.

04 同仓库更多 Skills

quark-sri
quark-sri/qestack

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).

★ 1
quark-sri
quark-sri/qestack

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).

★ 1
quark-sri
quark-sri/qestack

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).

★ 1
quark-sri
quark-sri/qestack

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).

★ 1
quark-sri
quark-sri/qestack

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).

★ 1
quark-sri
quark-sri/qestack

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).

★ 1