kiro-spec-design

Name: kiro-spec-design
Author: gotalab

3.6kstars271forks

How to install kiro-spec-design?

gotalab/cc-sdd/kiro-spec-design

$npx -y skills add gotalab/cc-sdd --skill kiro-spec-design

Installs into the current project.

Summary

Create comprehensive technical design for a specification

Files · 1

View on GitHub

SKILL.md

1	# Technical Design Generator
2
3	<background_information>
4	- Success Criteria:
5	- All requirements mapped to technical components with clear interfaces
6	- The design makes responsibility boundaries explicit enough to guide task generation and review
7	- Appropriate architecture discovery and research completed
8	- Design aligns with steering context and existing patterns
9	- Visual diagrams included for complex architectures
10	</background_information>
11
12	<instructions>
13	## Execution Steps
14
15	### Step 1: Load Context
16
17	Read all necessary context:
18	- `{{KIRO_DIR}}/specs/$1/spec.json`, `requirements.md`, `design.md` (if exists)
19	- `{{KIRO_DIR}}/specs/$1/research.md` (if exists, contains gap analysis from `/kiro-validate-gap`)
20	- Core steering context: `product.md`, `tech.md`, `structure.md`
21	- Additional steering files only when directly relevant to requirement coverage, architecture boundaries, integrations, runtime prerequisites, security/performance constraints, or team conventions that affect implementation readiness
22	- `{{KIRO_DIR}}/settings/templates/specs/design.md` for document structure
23	- Read `rules/design-principles.md` from this skill's directory for design principles
24	- `{{KIRO_DIR}}/settings/templates/specs/research.md` for discovery log structure
25
26	Validate requirements approval:
27	- If `-y` flag provided ($2 == "-y"): Auto-approve requirements in spec.json
28	- Otherwise: Verify approval status (stop if unapproved, see Safety & Fallback)
29
30	### Step 2: Discovery & Analysis
31
32	Critical: This phase ensures design is based on complete, accurate information.
33
34	1. Classify Feature Type:
35	- New Feature (greenfield) → Full discovery required
36	- Extension (existing system) → Integration-focused discovery
37	- Simple Addition (CRUD/UI) → Minimal or no discovery
38	- Complex Integration → Comprehensive analysis required
39
40	2. Execute Appropriate Discovery Process:
41
42	For Complex/New Features:
43	- Read and execute `rules/design-discovery-full.md` from this skill's directory
44	- Conduct thorough research using WebSearch/WebFetch:
45	- Latest architectural patterns and best practices
46	- External dependency verification (APIs, libraries, versions, compatibility)
47	- Official documentation, migration guides, known issues
48	- Performance benchmarks and security considerations
49
50	For Extensions:
51	- Read and execute `rules/design-discovery-light.md` from this skill's directory
52	- Focus on integration points, existing patterns, compatibility
53	- Use Grep to analyze existing codebase patterns
54
55	For Simple Additions:
56	- Skip formal discovery, quick pattern check only
57
58	#### Parallel Research (sub-agent dispatch)
59
60	The following research areas are independent and can be dispatched as sub-agents. The agent should decide the optimal decomposition based on feature complexity — split, merge, add, or skip sub-agents as needed. Each sub-agent returns a findings summary (not raw data) to keep the main context clean for synthesis.
61
62	Typical research areas (adjust as appropriate):
63	- Codebase analysis: Existing architecture patterns, integration points, code conventions
64	- External research: Dependencies, APIs, latest best practices
65	- Context loading (usually main context): Steering files, design principles, discovery rules, templates
66
67	For simple additions, skip sub-agent dispatch entirely and do a quick pattern check in main context.
68
69	After all findings return, synthesize in main context before proceeding.
70
71	3. Retain Discovery Findings for Step 3:
72	- External API contracts and constraints
73	- Technology decisions with rationale
74	- Existing patterns to follow or extend
75	- Integration points and dependencies
76	- Identified risks and mitigation strategies
77	- Boundary candidates, out-of-boundary decisions, and likely revalidation triggers
78
79	4. Persist Findings to Research Log:
80	- Create or update `{{KIRO_DIR}}/specs/$1/research.md` using the shared template
81	- Summarize discovery scope and key findings (Summary section)
82	- Record investigations in Research Log topics with sources and implications
83	- Document architecture pattern evaluation, design decisions, and risks using the template sections
84	- Use the language specified in spec.json when writing or updating `research.md`
85
86	### Step 3: Synthesis
87
88	Apply design synthesis to discovery findings before writing.
89
90	- Read and apply `rules/design-synthesis.md` from this skill's directory
91	- This step requires the full picture from discovery — do not parallelize or delegate to sub-agents
92	- Record synthesis outcomes (generalizations found, build-vs-adopt decisions, simplifications) in `research.md`
93
94	### Step 4: Generate Design Draf

People who liked this also viewed

6 picks

Type

web-design-guidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".SkillsJul 2026483k29k
lark-slides飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 SkillsJul 2026332k16k
design-taste-frontendTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop SkillsJul 2026280k66k
ui-ux-pro-maxUI/UX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presSkillsJul 2026280k109k
caveman-helpQuick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".SkillsJul 2026249k92k
codebase-designShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-nSkillsJul 2026225k182k

kiro-spec-design

3.6kstars271forks

View on GitHub

How to install kiro-spec-design?

gotalab/cc-sdd/kiro-spec-design

$npx -y skills add gotalab/cc-sdd --skill kiro-spec-design

Installs into the current project.

Summary

Create comprehensive technical design for a specification

Files · 1

View on GitHub

SKILL.md

1	# Technical Design Generator
2
3	<background_information>
4	- Success Criteria:
5	- All requirements mapped to technical components with clear interfaces
6	- The design makes responsibility boundaries explicit enough to guide task generation and review
7	- Appropriate architecture discovery and research completed
8	- Design aligns with steering context and existing patterns
9	- Visual diagrams included for complex architectures
10	</background_information>
11
12	<instructions>
13	## Execution Steps
14
15	### Step 1: Load Context
16
17	Read all necessary context:
18	- `{{KIRO_DIR}}/specs/$1/spec.json`, `requirements.md`, `design.md` (if exists)
19	- `{{KIRO_DIR}}/specs/$1/research.md` (if exists, contains gap analysis from `/kiro-validate-gap`)
20	- Core steering context: `product.md`, `tech.md`, `structure.md`
21	- Additional steering files only when directly relevant to requirement coverage, architecture boundaries, integrations, runtime prerequisites, security/performance constraints, or team conventions that affect implementation readiness
22	- `{{KIRO_DIR}}/settings/templates/specs/design.md` for document structure
23	- Read `rules/design-principles.md` from this skill's directory for design principles
24	- `{{KIRO_DIR}}/settings/templates/specs/research.md` for discovery log structure
25
26	Validate requirements approval:
27	- If `-y` flag provided ($2 == "-y"): Auto-approve requirements in spec.json
28	- Otherwise: Verify approval status (stop if unapproved, see Safety & Fallback)
29
30	### Step 2: Discovery & Analysis
31
32	Critical: This phase ensures design is based on complete, accurate information.
33
34	1. Classify Feature Type:
35	- New Feature (greenfield) → Full discovery required
36	- Extension (existing system) → Integration-focused discovery
37	- Simple Addition (CRUD/UI) → Minimal or no discovery
38	- Complex Integration → Comprehensive analysis required
39
40	2. Execute Appropriate Discovery Process:
41
42	For Complex/New Features:
43	- Read and execute `rules/design-discovery-full.md` from this skill's directory
44	- Conduct thorough research using WebSearch/WebFetch:
45	- Latest architectural patterns and best practices
46	- External dependency verification (APIs, libraries, versions, compatibility)
47	- Official documentation, migration guides, known issues
48	- Performance benchmarks and security considerations
49
50	For Extensions:
51	- Read and execute `rules/design-discovery-light.md` from this skill's directory
52	- Focus on integration points, existing patterns, compatibility
53	- Use Grep to analyze existing codebase patterns
54
55	For Simple Additions:
56	- Skip formal discovery, quick pattern check only
57
58	#### Parallel Research (sub-agent dispatch)
59
60	The following research areas are independent and can be dispatched as sub-agents. The agent should decide the optimal decomposition based on feature complexity — split, merge, add, or skip sub-agents as needed. Each sub-agent returns a findings summary (not raw data) to keep the main context clean for synthesis.
61
62	Typical research areas (adjust as appropriate):
63	- Codebase analysis: Existing architecture patterns, integration points, code conventions
64	- External research: Dependencies, APIs, latest best practices
65	- Context loading (usually main context): Steering files, design principles, discovery rules, templates
66
67	For simple additions, skip sub-agent dispatch entirely and do a quick pattern check in main context.
68
69	After all findings return, synthesize in main context before proceeding.
70
71	3. Retain Discovery Findings for Step 3:
72	- External API contracts and constraints
73	- Technology decisions with rationale
74	- Existing patterns to follow or extend
75	- Integration points and dependencies
76	- Identified risks and mitigation strategies
77	- Boundary candidates, out-of-boundary decisions, and likely revalidation triggers
78
79	4. Persist Findings to Research Log:
80	- Create or update `{{KIRO_DIR}}/specs/$1/research.md` using the shared template
81	- Summarize discovery scope and key findings (Summary section)
82	- Record investigations in Research Log topics with sources and implications
83	- Document architecture pattern evaluation, design decisions, and risks using the template sections
84	- Use the language specified in spec.json when writing or updating `research.md`
85
86	### Step 3: Synthesis
87
88	Apply design synthesis to discovery findings before writing.
89
90	- Read and apply `rules/design-synthesis.md` from this skill's directory
91	- This step requires the full picture from discovery — do not parallelize or delegate to sub-agents
92	- Record synthesis outcomes (generalizations found, build-vs-adopt decisions, simplifications) in `research.md`
93
94	### Step 4: Generate Design Draf

People who liked this also viewed

6 picks

Type