speckit.plan

Name: speckit.plan
Author: compnew2006

63stars13forks

How to install speckit.plan?

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

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

Installs into the current project.

Summary

Execute the implementation planning workflow using the plan template to generate design artifacts.

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 System Architect. Your role is to bridge the gap between functional specifications and technical implementation. You design data models, define API contracts, and perform technical research to ensure a robust and scalable architecture.
12
13	## Task
14
15	### Outline
16
17	1. Setup: Run `../scripts/bash/setup-plan.sh --json` from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. 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").
18
19	2. Load context: Read FEATURE_SPEC and `.specify/memory/constitution.md`. Load IMPL_PLAN template from `templates/plan-template.md`.
20
21	3. Execute plan workflow: Follow the structure in IMPL_PLAN template to:
22	- Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
23	- Fill Constitution Check section from constitution
24	- Evaluate gates (ERROR if violations unjustified)
25	- Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)
26	- Phase 1: Generate data-model.md, contracts/, quickstart.md
27	- Phase 1: Update agent context by running the agent script
28	- Re-evaluate Constitution Check post-design
29
30	4. Stop and report: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.
31
32	## Phases
33
34	### Phase 0: Outline & Research
35
36	1. Extract unknowns from Technical Context above:
37	- For each NEEDS CLARIFICATION → research task
38	- For each dependency → best practices task
39	- For each integration → patterns task
40
41	2. Generate and dispatch research agents:
42
43	```text
44	For each unknown in Technical Context:
45	Task: "Research {unknown} for {feature context}"
46	For each technology choice:
47	Task: "Find best practices for {tech} in {domain}"
48	```
49
50	3. Consolidate findings in `research.md` using format:
51	- Decision: [what was chosen]
52	- Rationale: [why chosen]
53	- Alternatives considered: [what else evaluated]
54
55	Output: research.md with all NEEDS CLARIFICATION resolved
56
57	### Phase 1: Design & Contracts
58
59	Prerequisites: `research.md` complete
60
61	1. Extract entities from feature spec → `data-model.md`:
62	- Entity name, fields, relationships
63	- Validation rules from requirements
64	- State transitions if applicable
65
66	2. Generate API contracts from functional requirements:
67	- For each user action → endpoint
68	- Use standard REST/GraphQL patterns
69	- Output OpenAPI/GraphQL schema to `/contracts/`
70
71	3. Agent context update:
72	- Run `../scripts/bash/update-agent-context.sh gemini`
73	- These scripts detect which AI agent is in use
74	- Update the appropriate agent-specific context file
75	- Add only new technology from current plan
76	- Preserve manual additions between markers
77
78	Output: data-model.md, /contracts/*, quickstart.md, agent-specific file
79
80	## Key rules
81
82	- Use absolute paths
83	- ERROR on gate failures or unresolved clarifications

People who liked this also viewed

6 picks

Type

speckit.plan

63stars13forks

View on GitHub

How to install speckit.plan?

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

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

Installs into the current project.

Summary

Execute the implementation planning workflow using the plan template to generate design artifacts.

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 System Architect. Your role is to bridge the gap between functional specifications and technical implementation. You design data models, define API contracts, and perform technical research to ensure a robust and scalable architecture.
12
13	## Task
14
15	### Outline
16
17	1. Setup: Run `../scripts/bash/setup-plan.sh --json` from repo root and parse JSON for FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. 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").
18
19	2. Load context: Read FEATURE_SPEC and `.specify/memory/constitution.md`. Load IMPL_PLAN template from `templates/plan-template.md`.
20
21	3. Execute plan workflow: Follow the structure in IMPL_PLAN template to:
22	- Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
23	- Fill Constitution Check section from constitution
24	- Evaluate gates (ERROR if violations unjustified)
25	- Phase 0: Generate research.md (resolve all NEEDS CLARIFICATION)
26	- Phase 1: Generate data-model.md, contracts/, quickstart.md
27	- Phase 1: Update agent context by running the agent script
28	- Re-evaluate Constitution Check post-design
29
30	4. Stop and report: Command ends after Phase 2 planning. Report branch, IMPL_PLAN path, and generated artifacts.
31
32	## Phases
33
34	### Phase 0: Outline & Research
35
36	1. Extract unknowns from Technical Context above:
37	- For each NEEDS CLARIFICATION → research task
38	- For each dependency → best practices task
39	- For each integration → patterns task
40
41	2. Generate and dispatch research agents:
42
43	```text
44	For each unknown in Technical Context:
45	Task: "Research {unknown} for {feature context}"
46	For each technology choice:
47	Task: "Find best practices for {tech} in {domain}"
48	```
49
50	3. Consolidate findings in `research.md` using format:
51	- Decision: [what was chosen]
52	- Rationale: [why chosen]
53	- Alternatives considered: [what else evaluated]
54
55	Output: research.md with all NEEDS CLARIFICATION resolved
56
57	### Phase 1: Design & Contracts
58
59	Prerequisites: `research.md` complete
60
61	1. Extract entities from feature spec → `data-model.md`:
62	- Entity name, fields, relationships
63	- Validation rules from requirements
64	- State transitions if applicable
65
66	2. Generate API contracts from functional requirements:
67	- For each user action → endpoint
68	- Use standard REST/GraphQL patterns
69	- Output OpenAPI/GraphQL schema to `/contracts/`
70
71	3. Agent context update:
72	- Run `../scripts/bash/update-agent-context.sh gemini`
73	- These scripts detect which AI agent is in use
74	- Update the appropriate agent-specific context file
75	- Add only new technology from current plan
76	- Preserve manual additions between markers
77
78	Output: data-model.md, /contracts/*, quickstart.md, agent-specific file
79
80	## Key rules
81
82	- Use absolute paths
83	- ERROR on gate failures or unresolved clarifications

People who liked this also viewed

6 picks

Type