SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsspeckit-checklist-zh

speckit-checklist-zh

Testing & quality

View repository

Updated 10-15 15:34

About this skill

Checklist purpose: "unit tests for Chinese"

Key concepts: A checklist isa unit test written for requirements - they verify the quality, clarity, and completeness of requirements in a specific domain.

Not used for verification/testing：

  • ❌ Not "verify the button is clicked correctly"
  • ❌ Not "test whether error handling works"
  • ❌ Not "confirm the API returns 200"
  • ❌ Not checking whether the code/implementation conforms to the specification

Used for requirements quality validation：

  • ✅ "Are visual hierarchy requirements defined for all card types?" (completeness)
  • ✅ "Is 'prominent display' quantified with specific size/positioning?" (clarity)
  • ✅ "Are hover state requirements consistent across all interactive elements?" (consistency)
  • ✅ "Are accessibility requirements defined for keyboard navigation?" (coverage)
  • ✅ "Does the specification define what happens when the logo image fails to load?" (edge case)

Analogy: If your specification is code that has been written, then the checklist is its unit test suite. You are testing whether the requirements are well-written, complete, unambiguous, and ready for implementation - not testing whether the implementation works.

User input

$ARGUMENTS

Youmustconsider user input (if non-empty) before proceeding.

Execution steps

scripts: sh: .specify/scripts/bash/check-prerequisites.sh --json ps: .specify/scripts/powershell/check-prerequisites.ps1 -Json

  1. Setup: Run from the repository root {SCRIPT} and parse the JSON to obtain FEATURE_DIR and the AVAILABLE_DOCS list.

    • All file paths must be absolute.
    • For single quotes in arguments, such as "I'm Groot", use escape syntax: for example 'I'''m Groot' (or use double quotes if possible: "I'm Groot").

  2. Clarify intent (dynamic): Derive up to three initial context clarification questions (no preset catalog). They must:

    • Be generated from the user's wording + signals extracted from the spec/plan/tasks
    • Only ask for information that would substantially change the checklist content
    • If already specified in $ARGUMENTS , skip it separately
    • Prioritize precision over breadth

    Generation algorithm:

    1. Extract signals: feature domain keywords (e.g., auth, latency, UX, API), risk indicators ("critical", "must", "compliance"), stakeholder hints ("QA", "review", "security team"), and explicit deliverables ("a11y", "rollback", "contracts").
    2. Cluster the signals into candidate areas of focus (up to 4) sorted by relevance.
    3. Identify the likely audience and timing (author, reviewer, QA, release) if unclear.
    4. Detect missing dimensions: scope breadth, depth/rigor, risk focus, exclusion boundaries, measurable acceptance criteria.
    5. Formulate questions from these archetypes:
      • Scope refinement (e.g., "Should this include integration touchpoints with X and Y or stay limited to local module correctness?")
      • Risk prioritization (e.g., "Which of these potential risk areas should receive mandatory gating checks?")
      • Depth calibration (e.g., "Is this a lightweight pre-commit sanity list or a formal release gate?")
      • Audience framing (e.g., "Will this be used only by the author or by peers during PR review?")
      • Boundary exclusion (e.g., "Should we explicitly exclude performance tuning items for this round?")
      • Scenario class gaps (e.g., "No recovery flows detected—are rollback/partial failure paths in scope?")

    Question formatting rules:

    • If options are provided, generate a compact table with columns: Option | Candidate | Why It Matters
    • Limit to a maximum of A-E options; omit the table if a free-form answer is clearer
    • Never ask the user to restate what they have already said
    • Avoid speculative categories (no hallucination). If unsure, explicitly ask: "Confirm whether X is in scope."

    Defaults when interaction is not possible:

    • Depth: Standard
    • Audience: Reviewer (PR) if code-related; otherwise Author
    • Focus: Top 2 relevance clusters

    Output questions (marked Q1/Q2/Q3). After answers: if ≥2 scenario classes (alternative/exception/recovery/non-functional domains) remain unclear, you may ask up to two more targeted follow-up questions (Q4/Q5), each with a one-line rationale (e.g., "Unresolved recovery path risk"). Do not exceed five total questions. Skip escalation if the user explicitly declines more questions.

  3. Understand the user request: combined with $ARGUMENTS + clarification answers:

    • Derive checklist topics (e.g., security, review, deployment, user experience)
    • Incorporate explicit must-have items mentioned by the user
    • Map focus selections to category scaffolding
    • Infer any missing context from the spec/plan/tasks (do not hallucinate)

  4. Load feature context: read from FEATURE_DIR:

    • spec.md: feature requirements and scope
    • plan.md (if present): technical details, dependencies
    • tasks.md (if present): implementation tasks

    Context loading strategy：

    • Load only the necessary parts relevant to the active focus areas (avoid full file dumps)
    • Prefer summarizing long passages into concise scenario/requirement bullets
    • Use progressive disclosure: add follow-up retrieval only when gaps are detected
    • If source documents are large, generate intermediate summary items instead of embedding raw text

  5. Generate checklist - create "unit tests for requirements":

    • If it does not exist, create the FEATURE_DIR/checklists/ directory
    • Generate a unique checklist filename:
      • Use a short domain-based descriptive name (e.g.,ux.md, api.md, security.md）
      • Format:[domain].md
      • If the file exists, append to the existing file
    • Number items sequentially starting from CHK001
    • Each speckit-checklist run creates a new file (never overwrites an existing checklist)

    Core principle - test requirements, not implementation: Each checklist item must evaluate the requirement itself:

    • Completeness: Are all necessary requirements present?
    • Clarity: Are the requirements clear and specific?
    • Consistency: Are the requirements aligned with each other?
    • Measurability: Can the requirements be objectively verified?
    • Coverage: Are all scenarios/edge cases addressed?

    Category structure - Group items by requirement quality dimension:

    • Requirement completeness(Are all necessary requirements documented?)
    • Requirement clarity(Are the requirements specific and unambiguous?)
    • Requirement consistency(Are the requirements aligned without conflicts?)
    • Acceptance criteria quality(Are the success criteria measurable?)
    • Scenario coverage(Are all flows/cases addressed?)
    • Edge case coverage(Are boundary conditions defined?)
    • Non-functional requirements(Performance, security, accessibility, etc. - are they specified?)
    • Dependencies and assumptions(Are they documented and verified?)
    • Ambiguities and conflicts(What needs clarification?)

    How to write checklist items - "unit tests for English"：

    ❌ Wrong(testing implementation):

    • "Verify the landing page displays 3 episode cards"
    • "Test whether the desktop hover state works"
    • "Confirm that clicking the logo navigates to the home page"

    ✅ Correct(testing requirement quality):

    • "Is the exact number and layout of featured episodes clearly specified?" [Completeness]
    • "Is 'prominently displayed' quantified with specific dimensions/positioning?" [Clarity]
    • "Are the hover state requirements consistent for all interactive elements?" [Consistency]
    • "Are keyboard navigation requirements defined for all interactive UI?" [Coverage]
    • "Is fallback behavior specified when the logo image fails to load?" [Edge case]
    • "Are loading states defined for asynchronous episode data?" [Completeness]
    • "Does the specification define the visual hierarchy of competing UI elements?" [Clarity]

    Item structure: Each item should follow this pattern:

    • Ask a question about requirement quality
    • Focus on what is written (or not written) in the spec/plan
    • Include the quality dimension in brackets [Completeness/Clarity/Consistency, etc.]
    • Reference the spec section when checking existing requirements [Spec §X.Y]
    • Use [Gap] to mark missing requirements

    Examples by quality dimension：

    Completeness:

    • "Are error handling requirements defined for all API failure modes? [Gap]"
    • "Are accessibility requirements specified for all interactive elements? [Completeness]"
    • "Are mobile breakpoint requirements defined for responsive layouts? [Gap]"

    Clarity:

    • "Is 'fast loading' quantified with specific timing thresholds? [Clarity, Spec §NFR-2]"
    • "Are the selection criteria for 'related episodes' clearly defined? [Clarity, Spec §FR-5]"
    • "Is 'prominent' defined with measurable visual properties? [Ambiguity, Spec §FR-4]"

    Consistency:

    • "Are the navigation requirements aligned across all pages? [Consistency, Spec §FR-10]"
    • "Are the card component requirements consistent between the landing page and the detail page? [Consistency]"

    Coverage:

    • "Are requirements defined for the zero-state scenario (no episodes)? [Coverage, Edge Case]"
    • "Are concurrent user interaction scenarios addressed? [Coverage, Gap]"
    • "Are requirements specified for partial data loading failures? [Coverage, Exception Flow]"

    Measurability:

    • "Are the visual hierarchy requirements measurable/testable? [Acceptance Criteria, Spec §FR-1]"
    • "Can 'balanced visual weight' be objectively verified? [Measurability, Spec §FR-2]"

    Scenario Classification and Coverage(Requirement Quality Focus):

    • Check whether requirements exist: primary, alternative, exception/error, recovery, non-functional scenarios
    • For each scenario category, ask: "Are the [scenario type] requirements complete, clear, and consistent?"
    • If a scenario category is missing: "Are [scenario type] requirements intentionally excluded or missing? [Gap]"
    • Include resilience/rollback for state changes: "Are rollback requirements defined for migration failures? [Gap]"

    Traceability Requirements：

    • Minimum requirement: ≥80% of items must contain at least one traceability reference
    • Each item should reference: spec section [Spec §X.Y], or use the marker:[Gap]、[Ambiguity]、[Conflict]、[Assumption]
    • If no ID system exists: "Has an ID scheme for requirements and acceptance criteria been established? [Traceability]"

    Surfacing and Resolving Issues(Requirement Quality Issues): Ask questions about the requirements themselves:

    • Ambiguity: "Is the term 'fast' quantified with specific metrics? [Ambiguity, Spec §NFR-1]"
    • Conflict: "Do the navigation requirements in §FR-10 and §FR-10a conflict? [Conflict]"
    • Assumption: "Has the assumption of an 'always-available podcast API' been verified? [Assumption]"
    • Dependency: "Are the external podcast API requirements documented? [Dependency, Gap]"
    • Missing Definition: "Is 'visual hierarchy' defined with measurable criteria? [Gap]"

    Content Consolidation：

    • Soft cap: if raw candidate items > 40, prioritize by risk/impact
    • Merge near-duplicates that check the same requirement aspect
    • If >5 low-impact edge cases, create one item: "Are edge cases X, Y, Z addressed in the requirements? [Coverage]"

    🚫 Absolutely Forbidden - These make it an implementation test, not a requirements test:

    • ❌ Any item starting with "verify", "test", "confirm", "check" + implementation behavior
    • ❌ References to code execution, user actions, system behavior
    • ❌ "displays correctly", "works properly", "functions as expected"
    • ❌ "click", "navigate", "render", "load", "execute"
    • ❌ Test cases, test plans, QA procedures
    • ❌ Implementation details (frameworks, APIs, algorithms)

    ✅ Required pattern - These test requirements quality:

    • ✅ "Is [requirement type] defined/specified/documented for [scenario]?"
    • ✅ "Is [ambiguous term] quantified/clarified with specific criteria?"
    • ✅ "Are requirements for [part A] and [part B] consistent?"
    • ✅ "Can [requirement] be objectively measured/verified?"
    • ✅ "Is [edge case/scenario] addressed in the requirements?"
    • ✅ "Does the spec define [missing aspect]?"

  6. Structure reference: Generate the checklist according to the spec template in .specify/templates/checklist-template.md , including title, meta section, category headings, and ID format. If the template is unavailable, use: H1 title, Purpose/Created meta lines, containing - [ ] CHK### <要求项目> lines in the ## category sections, with globally incrementing IDs starting from CHK001.

  7. Report: Output the full path of the created checklist, item count, and remind the user that each run creates a new file. Summary:

    • Chosen focus area
    • Depth level
    • Participants/timing
    • Any explicitly specified required items included by the user

Important: Each speckit-checklist command invocation creates a checklist file with a short descriptive name, unless the file already exists. This allows:

  • Multiple checklists of different types (e.g.,ux.md, test.md, security.md）
  • Simple, memorable file names indicating the checklist purpose
  • Easy identification and navigation in the checklists/ folder

To avoid confusion, use descriptive types and clean up outdated checklists after completion.

Example checklist types and example items

User experience requirements quality: ux.md

Example items (test requirements, not implementation):

  • "Are visual hierarchy requirements defined with measurable criteria? [Clarity, Spec §FR-1]"
  • "Are the number and positioning of UI elements clearly defined? [Completeness, Spec §FR-1]"
  • "Are interaction state requirements (hover, focus, active) consistently defined? [Consistency]"
  • "Are accessibility requirements specified for all interactive elements? [Coverage, Gap]"
  • "Is fallback behavior defined when images fail to load? [Edge case, Gap]"
  • "Can 'prominently displayed' be objectively measured? [Measurability, Spec §FR-4]"

API requirements quality: api.md

Example items:

  • "Are error response formats specified for all failure scenarios? [Completeness]"
  • "Are rate limiting requirements quantified with specific thresholds? [Clarity]"
  • "Are authentication requirements consistent across all endpoints? [Consistency]"
  • "Are retry/timeout requirements defined for external dependencies? [Coverage, Gap]"
  • "Is the version control strategy documented in the requirements? [Gap]"

Performance requirement quality: performance.md

Example project:

  • "Are performance requirements quantified with specific metrics? [Clarity]"
  • "Are performance targets defined for all critical user journeys? [Coverage]"
  • "Are performance requirements specified for different load conditions? [Completeness]"
  • "Can the performance requirements be measured objectively? [Measurability]"
  • "Are degradation requirements defined for high-load scenarios? [Edge case, Gap]"

Security requirement quality: security.md

Example project:

  • "Are authentication requirements specified for all protected resources? [Coverage]"
  • "Are data protection requirements defined for sensitive information? [Completeness]"
  • "Is the threat model documented and aligned with the requirements? [Traceability]"
  • "Are the security requirements consistent with compliance obligations? [Consistency]"
  • "Are security failure/breach response requirements defined? [Gap, Exception flow]"

Counterexamples: what not to do

❌ Wrong - these test the implementation, not the requirements:

- [ ] CHK001 - 验证着陆页显示 3 个剧集卡片 [Spec §FR-001]
- [ ] CHK002 - 测试桌面端悬停状态是否正确工作 [Spec §FR-003]
- [ ] CHK003 - 确认徽标点击导航到主页 [Spec §FR-010]
- [ ] CHK004 - 检查相关剧集部分显示 3-5 个项目 [Spec §FR-005]

✅ Correct - these test requirement quality:

- [ ] CHK001 - 是否明确定义了特色剧集的数量和布局？ [完整性, Spec §FR-001]
- [ ] CHK002 - 是否为所有交互元素一致定义了悬停状态要求？ [一致性, Spec §FR-003]
- [ ] CHK003 - 是否为所有可点击品牌元素明确了导航要求？ [清晰度, Spec §FR-010]
- [ ] CHK004 - 是否记录了相关剧集的选择标准？ [Gap, Spec §FR-005]
- [ ] CHK005 - 是否为异步剧集数据定义了加载状态要求？ [Gap]
- [ ] CHK006 - 是否可以客观测量"视觉层次"要求？ [可测量性, Spec §FR-001]

Key differences:

  • Wrong: testing whether the system works correctly
  • Correct: testing whether the requirements are written correctly
  • Wrong: behavior verification
  • Correct: requirement quality verification
  • Wrong: "Does it do X?"
  • Correct: "Is X clearly defined?"