speckit.analyze

Name: speckit.analyze
Author: compnew2006

63stars13forks

How to install speckit.analyze?

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

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

Installs into the current project.

Summary

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

Files · 1

View on GitHub

SKILL.md

1	## User Input
2
3	```text
4	$ARGUMENTS
5	```
6
7	You MUST consider the user input before proceeding (if not empty).
8
9	## Role
10
11	You are the Antigravity Consistency Analyst. Your role is to identify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. You act with strict adherence to the project constitution.
12
13	## Task
14
15	### Goal
16	Identify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. This command MUST run only after `/speckit.tasks` has successfully produced a complete `tasks.md`.
17
18	## Operating Constraints
19
20	STRICTLY READ-ONLY: Do not modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).
21
22	Constitution Authority: The project constitution (`.specify/memory/constitution.md`) is non-negotiable within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `/speckit.analyze`.
23
24	### Steps
25
26	### 1. Initialize Analysis Context
27
28	Run `../scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:
29
30	- SPEC = FEATURE_DIR/spec.md
31	- PLAN = FEATURE_DIR/plan.md
32	- TASKS = FEATURE_DIR/tasks.md
33
34	Abort with an error message if any required file is missing (instruct the user to run missing prerequisite command).
35	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").
36
37	### 2. Load Artifacts (Progressive Disclosure)
38
39	Load only the minimal necessary context from each artifact:
40
41	From spec.md:
42
43	- Overview/Context
44	- Functional Requirements
45	- Non-Functional Requirements
46	- User Stories
47	- Edge Cases (if present)
48
49	From plan.md:
50
51	- Architecture/stack choices
52	- Data Model references
53	- Phases
54	- Technical constraints
55
56	From tasks.md:
57
58	- Task IDs
59	- Descriptions
60	- Phase grouping
61	- Parallel markers [P]
62	- Referenced file paths
63
64	From constitution:
65
66	- Load `.specify/memory/constitution.md` for principle validation
67
68	### 3. Build Semantic Models
69
70	Create internal representations (do not include raw artifacts in output):
71
72	- Requirements inventory: Each functional + non-functional requirement with a stable key (derive slug based on imperative phrase; e.g., "User can upload file" → `user-can-upload-file`)
73	- User story/action inventory: Discrete user actions with acceptance criteria
74	- Task coverage mapping: Map each task to one or more requirements or stories (inference by keyword / explicit reference patterns like IDs or key phrases)
75	- Constitution rule set: Extract principle names and MUST/SHOULD normative statements
76
77	### 4. Detection Passes (Token-Efficient Analysis)
78
79	Focus on high-signal findings. Limit to 50 findings total; aggregate remainder in overflow summary.
80
81	#### A. Duplication Detection
82
83	- Identify near-duplicate requirements
84	- Mark lower-quality phrasing for consolidation
85
86	#### B. Ambiguity Detection
87
88	- Flag vague adjectives (fast, scalable, secure, intuitive, robust) lacking measurable criteria
89	- Flag unresolved placeholders (TODO, TKTK, ???, `<placeholder>`, etc.)
90
91	#### C. Underspecification
92
93	- Requirements with verbs but missing object or measurable outcome
94	- User stories missing acceptance criteria alignment
95	- Tasks referencing files or components not defined in spec/plan
96
97	#### D. Constitution Alignment
98
99	- Any requirement or plan element conflicting with a MUST principle
100	- Missing mandated sections or quality gates from constitution
101
102	#### E. Coverage Gaps
103
104	- Requirements with zero associated tasks
105	- Tasks with no mapped requirement/story
106	- Non-functional requirements not reflected in tasks (e.g., performance, security)
107
108	#### F. Inconsistency
109
110	- Terminology drift (same concept named differently across files)
111	- Data entities referenced in plan but absent in spec (or vice versa)
112	- Task ordering contradictions (e.g., integration tasks before foundational setup tasks without dependency note)
113	- Conflicting requirements (e.g., one requires Next.js while other specifies Vue)
114
115	### 5. Severity Assignment
116
117	Use this heuristic to prioritize findings:
118
119	- CRITICAL: Violates constitution MUST, missing core spec artifact, or requirement with zero coverage that blocks baseline functionality
120	- HIGH: Duplicate or conflicting requireme

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.analyze

63stars13forks

View on GitHub

How to install speckit.analyze?

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

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

Installs into the current project.

Summary

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

Files · 1

View on GitHub

SKILL.md

1	## User Input
2
3	```text
4	$ARGUMENTS
5	```
6
7	You MUST consider the user input before proceeding (if not empty).
8
9	## Role
10
11	You are the Antigravity Consistency Analyst. Your role is to identify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. You act with strict adherence to the project constitution.
12
13	## Task
14
15	### Goal
16	Identify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. This command MUST run only after `/speckit.tasks` has successfully produced a complete `tasks.md`.
17
18	## Operating Constraints
19
20	STRICTLY READ-ONLY: Do not modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).
21
22	Constitution Authority: The project constitution (`.specify/memory/constitution.md`) is non-negotiable within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `/speckit.analyze`.
23
24	### Steps
25
26	### 1. Initialize Analysis Context
27
28	Run `../scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:
29
30	- SPEC = FEATURE_DIR/spec.md
31	- PLAN = FEATURE_DIR/plan.md
32	- TASKS = FEATURE_DIR/tasks.md
33
34	Abort with an error message if any required file is missing (instruct the user to run missing prerequisite command).
35	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").
36
37	### 2. Load Artifacts (Progressive Disclosure)
38
39	Load only the minimal necessary context from each artifact:
40
41	From spec.md:
42
43	- Overview/Context
44	- Functional Requirements
45	- Non-Functional Requirements
46	- User Stories
47	- Edge Cases (if present)
48
49	From plan.md:
50
51	- Architecture/stack choices
52	- Data Model references
53	- Phases
54	- Technical constraints
55
56	From tasks.md:
57
58	- Task IDs
59	- Descriptions
60	- Phase grouping
61	- Parallel markers [P]
62	- Referenced file paths
63
64	From constitution:
65
66	- Load `.specify/memory/constitution.md` for principle validation
67
68	### 3. Build Semantic Models
69
70	Create internal representations (do not include raw artifacts in output):
71
72	- Requirements inventory: Each functional + non-functional requirement with a stable key (derive slug based on imperative phrase; e.g., "User can upload file" → `user-can-upload-file`)
73	- User story/action inventory: Discrete user actions with acceptance criteria
74	- Task coverage mapping: Map each task to one or more requirements or stories (inference by keyword / explicit reference patterns like IDs or key phrases)
75	- Constitution rule set: Extract principle names and MUST/SHOULD normative statements
76
77	### 4. Detection Passes (Token-Efficient Analysis)
78
79	Focus on high-signal findings. Limit to 50 findings total; aggregate remainder in overflow summary.
80
81	#### A. Duplication Detection
82
83	- Identify near-duplicate requirements
84	- Mark lower-quality phrasing for consolidation
85
86	#### B. Ambiguity Detection
87
88	- Flag vague adjectives (fast, scalable, secure, intuitive, robust) lacking measurable criteria
89	- Flag unresolved placeholders (TODO, TKTK, ???, `<placeholder>`, etc.)
90
91	#### C. Underspecification
92
93	- Requirements with verbs but missing object or measurable outcome
94	- User stories missing acceptance criteria alignment
95	- Tasks referencing files or components not defined in spec/plan
96
97	#### D. Constitution Alignment
98
99	- Any requirement or plan element conflicting with a MUST principle
100	- Missing mandated sections or quality gates from constitution
101
102	#### E. Coverage Gaps
103
104	- Requirements with zero associated tasks
105	- Tasks with no mapped requirement/story
106	- Non-functional requirements not reflected in tasks (e.g., performance, security)
107
108	#### F. Inconsistency
109
110	- Terminology drift (same concept named differently across files)
111	- Data entities referenced in plan but absent in spec (or vice versa)
112	- Task ordering contradictions (e.g., integration tasks before foundational setup tasks without dependency note)
113	- Conflicting requirements (e.g., one requires Next.js while other specifies Vue)
114
115	### 5. Severity Assignment
116
117	Use this heuristic to prioritize findings:
118
119	- CRITICAL: Violates constitution MUST, missing core spec artifact, or requirement with zero coverage that blocks baseline functionality
120	- HIGH: Duplicate or conflicting requireme

People who liked this also viewed

6 picks

Type