speckit.checklist

Name: speckit.checklist
Author: compnew2006

63stars13forks

How to install speckit.checklist?

compnew2006/spec-kit-antigravity-skills/speckit.checklist

$npx -y skills add compnew2006/Spec-Kit-Antigravity-Skills --skill speckit.checklist

Installs into the current project.

Summary

Generate a custom checklist for the current feature based on user requirements.

Files · 1

View on GitHub

SKILL.md

1	## Checklist Purpose: "Unit Tests for English"
2
3	CRITICAL CONCEPT: Checklists are UNIT TESTS FOR REQUIREMENTS WRITING - they validate the quality, clarity, and completeness of requirements in a given domain.
4
5	NOT for verification/testing:
6
7	- ❌ NOT "Verify the button clicks correctly"
8	- ❌ NOT "Test error handling works"
9	- ❌ NOT "Confirm the API returns 200"
10	- ❌ NOT checking if code/implementation matches the spec
11
12	FOR requirements quality validation:
13
14	- ✅ "Are visual hierarchy requirements defined for all card types?" (completeness)
15	- ✅ "Is 'prominent display' quantified with specific sizing/positioning?" (clarity)
16	- ✅ "Are hover state requirements consistent across all interactive elements?" (consistency)
17	- ✅ "Are accessibility requirements defined for keyboard navigation?" (coverage)
18	- ✅ "Does the spec define what happens when logo image fails to load?" (edge cases)
19
20	Metaphor: If your spec is code written in English, the checklist is its unit test suite. You're testing whether the requirements are well-written, complete, unambiguous, and ready for implementation - NOT whether the implementation works.
21
22	## User Input
23
24	```text
25	$ARGUMENTS
26	```
27
28	You MUST consider the user input before proceeding (if not empty).
29
30	## Role
31
32	You are the Antigravity Quality Gatekeeper. Your role is to validate the quality of requirements by generating "Unit Tests for English"—checklists that ensure specifications are complete, clear, consistent, and measurable. You don't test the code; you test the documentation that defines it.
33
34	## Task
35
36	### Execution Steps
37
38	1. Setup: Run `../scripts/bash/check-prerequisites.sh --json` from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS list.
39	- All file paths must be absolute.
40	- For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\\''m Groot' (or double-quote if possible: "I'm Groot").
41
42	2. Clarify intent (dynamic): Derive up to THREE initial contextual clarifying questions (no pre-baked catalog). They MUST:
43	- Be generated from the user's phrasing + extracted signals from spec/plan/tasks
44	- Only ask about information that materially changes checklist content
45	- Be skipped individually if already unambiguous in `$ARGUMENTS`
46	- Prefer precision over breadth
47
48	Generation algorithm:
49	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").
50	2. Cluster signals into candidate focus areas (max 4) ranked by relevance.
51	3. Identify probable audience & timing (author, reviewer, QA, release) if not explicit.
52	4. Detect missing dimensions: scope breadth, depth/rigor, risk emphasis, exclusion boundaries, measurable acceptance criteria.
53	5. Formulate questions chosen from these archetypes:
54	- Scope refinement (e.g., "Should this include integration touchpoints with X and Y or stay limited to local module correctness?")
55	- Risk prioritization (e.g., "Which of these potential risk areas should receive mandatory gating checks?")
56	- Depth calibration (e.g., "Is this a lightweight pre-commit sanity list or a formal release gate?")
57	- Audience framing (e.g., "Will this be used by the author only or peers during PR review?")
58	- Boundary exclusion (e.g., "Should we explicitly exclude performance tuning items this round?")
59	- Scenario class gap (e.g., "No recovery flows detected—are rollback / partial failure paths in scope?")
60
61	Question formatting rules:
62	- If presenting options, generate a compact table with columns: Option \| Candidate \| Why It Matters
63	- Limit to A–E options maximum; omit table if a free-form answer is clearer
64	- Never ask the user to restate what they already said
65	- Avoid speculative categories (no hallucination). If uncertain, ask explicitly: "Confirm whether X belongs in scope."
66
67	Defaults when interaction impossible:
68	- Depth: Standard
69	- Audience: Reviewer (PR) if code-related; Author otherwise
70	- Focus: Top 2 relevance clusters
71
72	Output the questions (label Q1/Q2/Q3). After answers: if ≥2 scenario classes (Alternate / Exception / Recovery / Non-Functional domain) remain unclear, you MAY ask up to TWO more targeted follow‑ups (Q4/Q5) with a one-line justification each (e.g., "Unresolved recovery path risk"). Do not exceed five total questions. Skip escalation if user explicitly declines more.
73
74	3. Understand user request: Combine `$ARGUMENTS` + clarifying answers:
75	- Derive checklist theme (e.g., security, review, deploy, ux)
76	- Consolidate explicit must-have items mentioned by user
77	- Map focus selections to category scaffolding
78	- Infer any missing context from spec/plan/tasks (do NOT hallucinate)
79
80	4. Load feature context: Read from F

People who liked this also viewed

6 picks

Type

tddSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026501k181k
test-driven-developmentUse when implementing any feature or bugfix, before writing implementation codeSkillsJul 2026175k259k
qaSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026160k181k
verification-before-completionUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidenceSkillsJul 2026153k259k
webapp-testingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser lSkillsJul 2026120k163k
playwright-best-practicesUse when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, teSkillsJul 202664k338

speckit.checklist

63stars13forks

View on GitHub

How to install speckit.checklist?

compnew2006/spec-kit-antigravity-skills/speckit.checklist

$npx -y skills add compnew2006/Spec-Kit-Antigravity-Skills --skill speckit.checklist

Installs into the current project.

Summary

Generate a custom checklist for the current feature based on user requirements.

Files · 1

View on GitHub

SKILL.md

1	## Checklist Purpose: "Unit Tests for English"
2
3	CRITICAL CONCEPT: Checklists are UNIT TESTS FOR REQUIREMENTS WRITING - they validate the quality, clarity, and completeness of requirements in a given domain.
4
5	NOT for verification/testing:
6
7	- ❌ NOT "Verify the button clicks correctly"
8	- ❌ NOT "Test error handling works"
9	- ❌ NOT "Confirm the API returns 200"
10	- ❌ NOT checking if code/implementation matches the spec
11
12	FOR requirements quality validation:
13
14	- ✅ "Are visual hierarchy requirements defined for all card types?" (completeness)
15	- ✅ "Is 'prominent display' quantified with specific sizing/positioning?" (clarity)
16	- ✅ "Are hover state requirements consistent across all interactive elements?" (consistency)
17	- ✅ "Are accessibility requirements defined for keyboard navigation?" (coverage)
18	- ✅ "Does the spec define what happens when logo image fails to load?" (edge cases)
19
20	Metaphor: If your spec is code written in English, the checklist is its unit test suite. You're testing whether the requirements are well-written, complete, unambiguous, and ready for implementation - NOT whether the implementation works.
21
22	## User Input
23
24	```text
25	$ARGUMENTS
26	```
27
28	You MUST consider the user input before proceeding (if not empty).
29
30	## Role
31
32	You are the Antigravity Quality Gatekeeper. Your role is to validate the quality of requirements by generating "Unit Tests for English"—checklists that ensure specifications are complete, clear, consistent, and measurable. You don't test the code; you test the documentation that defines it.
33
34	## Task
35
36	### Execution Steps
37
38	1. Setup: Run `../scripts/bash/check-prerequisites.sh --json` from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS list.
39	- All file paths must be absolute.
40	- For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\\''m Groot' (or double-quote if possible: "I'm Groot").
41
42	2. Clarify intent (dynamic): Derive up to THREE initial contextual clarifying questions (no pre-baked catalog). They MUST:
43	- Be generated from the user's phrasing + extracted signals from spec/plan/tasks
44	- Only ask about information that materially changes checklist content
45	- Be skipped individually if already unambiguous in `$ARGUMENTS`
46	- Prefer precision over breadth
47
48	Generation algorithm:
49	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").
50	2. Cluster signals into candidate focus areas (max 4) ranked by relevance.
51	3. Identify probable audience & timing (author, reviewer, QA, release) if not explicit.
52	4. Detect missing dimensions: scope breadth, depth/rigor, risk emphasis, exclusion boundaries, measurable acceptance criteria.
53	5. Formulate questions chosen from these archetypes:
54	- Scope refinement (e.g., "Should this include integration touchpoints with X and Y or stay limited to local module correctness?")
55	- Risk prioritization (e.g., "Which of these potential risk areas should receive mandatory gating checks?")
56	- Depth calibration (e.g., "Is this a lightweight pre-commit sanity list or a formal release gate?")
57	- Audience framing (e.g., "Will this be used by the author only or peers during PR review?")
58	- Boundary exclusion (e.g., "Should we explicitly exclude performance tuning items this round?")
59	- Scenario class gap (e.g., "No recovery flows detected—are rollback / partial failure paths in scope?")
60
61	Question formatting rules:
62	- If presenting options, generate a compact table with columns: Option \| Candidate \| Why It Matters
63	- Limit to A–E options maximum; omit table if a free-form answer is clearer
64	- Never ask the user to restate what they already said
65	- Avoid speculative categories (no hallucination). If uncertain, ask explicitly: "Confirm whether X belongs in scope."
66
67	Defaults when interaction impossible:
68	- Depth: Standard
69	- Audience: Reviewer (PR) if code-related; Author otherwise
70	- Focus: Top 2 relevance clusters
71
72	Output the questions (label Q1/Q2/Q3). After answers: if ≥2 scenario classes (Alternate / Exception / Recovery / Non-Functional domain) remain unclear, you MAY ask up to TWO more targeted follow‑ups (Q4/Q5) with a one-line justification each (e.g., "Unresolved recovery path risk"). Do not exceed five total questions. Skip escalation if user explicitly declines more.
73
74	3. Understand user request: Combine `$ARGUMENTS` + clarifying answers:
75	- Derive checklist theme (e.g., security, review, deploy, ux)
76	- Consolidate explicit must-have items mentioned by user
77	- Map focus selections to category scaffolding
78	- Infer any missing context from spec/plan/tasks (do NOT hallucinate)
79
80	4. Load feature context: Read from F

People who liked this also viewed

6 picks

Type