AGENT SKILL

requirement-gaps

Finds gaps in requirements before tests or code exist: missing acceptance criteria, vague words, undefined limits, error behavior, states and conflicts, with proposed answers. Use when the user asks 'is this story testable' or 'what is missing in this spec'. Not for comparing spec and code (use spec-drift).

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
requirement-gaps
license
Apache-2.0
description
Finds gaps in requirements before tests or code exist: missing acceptance criteria, vague words, undefined limits, error behavior, states and conflicts, with proposed answers. Use when the user asks 'is this story testable' or 'what is missing in this spec'. Not for comparing spec and code (use spec-drift).
argument-hint
[spec, story, ticket or contract]

02 资源文件 1

03 SKILL.md 正文

requirement-gaps

Objective

Tests can only be as good as the rules behind them. A gap in a requirement becomes a bug or a wrong test later, and it costs more each phase. This skill finds what the requirement does not say, and turns each gap into a question with a proposed answer. It does not write tests or code.

Context

  1. Read .agents/qa-project-context.md if it exists. Use its requirement ID format and the glossary.
  2. If it does not exist, continue with the requirement source alone.

Discovery questions

  1. Where is the requirement: a file, a ticket, a contract, a design? Get all related sources.
  2. Who answers the questions: a product owner, an analyst, a domain expert?

Workflow

  1. Inventory. List each requirement as one line, with its ID (give R1, R2, ... if there is none). Keep the original words.
  2. Check each requirement against the gap checklist. Write one finding for each gap, with the exact quote.
  3. Check the set:
    • contradictions between requirements
    • objects or states that no requirement defines
    • "create" with no rule for update, delete or read
    • roles that may and may not act
    • non-functional needs that the domain implies (audit, privacy, performance, accessibility)
  4. Rank: high (money, security, data loss, legal, irreversible), medium (wrong result for some users), low (wording).
  5. Ask the high gaps first. For each one, propose a concrete answer that the owner can accept or change.

Output

## Requirement gaps: <source>

<n> requirements | high <h> | medium <m> | low <l>

| # | Req | Area | Quote | Gap | Risk | Question (proposed answer) |
|---|---|---|---|---|---|---|

Set-level gaps: ...
Ready for test design: <requirement IDs>

Anti-patterns

  • Inventing rules. A gap is a question, not an answer. The owner decides.
  • Reading the code to find the rule. The code can be wrong.
  • Wording-only review. Spelling and style are low value. Missing errors and limits are high value.

Done when

  • Each requirement was checked against the checklist.
  • Each gap has a quote, a risk and a question with a proposed answer.
  • The requirements that are ready for test design are listed.

Related skills

  • edge-case-hunter: the edge cases of the clarified requirement.
  • test-case-designer: the test cases.
  • spec-drift: compares the requirement with the code and the tests later.

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