kiro-validate-design

Name: kiro-validate-design
Author: gotalab

3.6kstars271forks

How to install kiro-validate-design?

gotalab/cc-sdd/kiro-validate-design

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

Installs into the current project.

Summary

Interactive technical design quality review and validation

Files · 1

View on GitHub

SKILL.md

1	# Technical Design Validation
2
3	<background_information>
4	- Mission: Conduct interactive quality review of technical design to ensure readiness for implementation
5	- Success Criteria:
6	- Critical issues identified (maximum 3 most important concerns)
7	- Balanced assessment with strengths recognized
8	- Clear GO/NO-GO decision with rationale
9	- Actionable feedback for improvements if needed
10	</background_information>
11
12	<instructions>
13	## Core Task
14	Interactive design quality review for feature $1 based on approved requirements and design document.
15
16	## Execution Steps
17
18	1. Gather Context:
19	- Read `{{KIRO_DIR}}/specs/$1/spec.json` for language and metadata
20	- Read `{{KIRO_DIR}}/specs/$1/requirements.md` for requirements
21	- Read `{{KIRO_DIR}}/specs/$1/design.md` for design document
22	- Core steering context: `product.md`, `tech.md`, `structure.md`
23	- Additional steering files only when directly relevant to architecture boundaries, integrations, runtime prerequisites, domain rules, security/performance constraints, or team conventions that affect implementation readiness
24	- Relevant local agent skills or playbooks only when they clearly match the feature's host environment or use case and provide review-relevant context
25
26	#### Parallel Research
27
28	The following research areas are independent and can be executed in parallel:
29	1. Context & rules loading: Spec documents, core steering, task-relevant extra steering, relevant local agent skills/playbooks, and `rules/design-review.md` from this skill's directory for review criteria
30	2. Codebase pattern survey: Gather existing architecture patterns, naming conventions, and component structure from the codebase to use as reference during review
31
32	If multi-agent is enabled, spawn sub-agents for each area above. Otherwise execute sequentially.
33
34	After all parallel research completes, synthesize findings for review.
35
36	2. Execute Design Review:
37	- Reference conversation history when available: leverage prior requirements discussion and user's stated design intent
38	- Follow design-review.md process: Analysis → Critical Issues → Strengths → GO/NO-GO
39	- Limit to 3 most important concerns
40	- Engage interactively with user — ask clarifying questions, propose alternatives
41	- Use language specified in spec.json for output
42
43	3. Decision and Next Steps:
44	- Clear GO/NO-GO decision with rationale
45	- Provide specific actionable next steps (see Next Phase below)
46
47	## Important Constraints
48	- Quality assurance, not perfection seeking: Accept acceptable risk
49	- Critical focus only: Maximum 3 issues, only those significantly impacting success
50	- Conversation-aware: Leverage discussion history for requirements context and user intent when available
51	- Interactive approach: Engage in dialogue, ask clarifying questions, propose alternatives
52	- Balanced assessment: Recognize both strengths and weaknesses
53	- Actionable feedback: All suggestions must be implementable
54	- Context Discipline: Start with core steering and expand only with review-relevant steering or use-case-aligned local agent skills/playbooks
55	</instructions>
56
57	## Tool Guidance
58	- Read first: Load spec, core steering, relevant local playbooks/agent skills, and rules before review
59	- Grep if needed: Search codebase for pattern validation or integration checks
60	- Interactive: Engage with user throughout the review process
61
62	## Output Description
63	Provide output in the language specified in spec.json with:
64
65	1. Review Summary: Brief overview (2-3 sentences) of design quality and readiness
66	2. Critical Issues: Maximum 3, following design-review.md format
67	3. Design Strengths: 1-2 positive aspects
68	4. Final Assessment: GO/NO-GO decision with rationale and next steps
69
70	Format Requirements:
71	- Use Markdown headings for clarity
72	- Follow design-review.md output format
73	- Keep summary concise
74
75	## Safety & Fallback
76
77	### Error Scenarios
78	- Missing Design: If design.md doesn't exist, stop with message: "Run `/kiro-spec-design $1` first to generate design document"
79	- Design Not Generated: If design phase not marked as generated in spec.json, warn but proceed with review
80	- Empty Steering Directory: Warn user that project context is missing and may affect review quality
81	- Language Undefined: Default to English (`en`) if spec.json doesn't specify language
82
83	### Next Phase: Task Generation
84
85	If Design Passes Validation (GO Decision):
86	- Review feedback and apply changes if needed
87	- Run `/kiro-spec-tasks $1` to generate implementation tasks
88	- Or `/kiro-spec-tasks $1 -y` to auto-approve and proceed directly
89
90	If Design Needs Revision (NO-GO Decision):
91	- Address critical issues identified
92	- Re-run `/kiro-spec-design $1` with improvements
93	- Re-validate with `/kiro-validate-design $1`
94
95	Note: Design va

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-validate-design

3.6kstars271forks

View on GitHub

How to install kiro-validate-design?

gotalab/cc-sdd/kiro-validate-design

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

Installs into the current project.

Summary

Interactive technical design quality review and validation

Files · 1

View on GitHub

SKILL.md

1	# Technical Design Validation
2
3	<background_information>
4	- Mission: Conduct interactive quality review of technical design to ensure readiness for implementation
5	- Success Criteria:
6	- Critical issues identified (maximum 3 most important concerns)
7	- Balanced assessment with strengths recognized
8	- Clear GO/NO-GO decision with rationale
9	- Actionable feedback for improvements if needed
10	</background_information>
11
12	<instructions>
13	## Core Task
14	Interactive design quality review for feature $1 based on approved requirements and design document.
15
16	## Execution Steps
17
18	1. Gather Context:
19	- Read `{{KIRO_DIR}}/specs/$1/spec.json` for language and metadata
20	- Read `{{KIRO_DIR}}/specs/$1/requirements.md` for requirements
21	- Read `{{KIRO_DIR}}/specs/$1/design.md` for design document
22	- Core steering context: `product.md`, `tech.md`, `structure.md`
23	- Additional steering files only when directly relevant to architecture boundaries, integrations, runtime prerequisites, domain rules, security/performance constraints, or team conventions that affect implementation readiness
24	- Relevant local agent skills or playbooks only when they clearly match the feature's host environment or use case and provide review-relevant context
25
26	#### Parallel Research
27
28	The following research areas are independent and can be executed in parallel:
29	1. Context & rules loading: Spec documents, core steering, task-relevant extra steering, relevant local agent skills/playbooks, and `rules/design-review.md` from this skill's directory for review criteria
30	2. Codebase pattern survey: Gather existing architecture patterns, naming conventions, and component structure from the codebase to use as reference during review
31
32	If multi-agent is enabled, spawn sub-agents for each area above. Otherwise execute sequentially.
33
34	After all parallel research completes, synthesize findings for review.
35
36	2. Execute Design Review:
37	- Reference conversation history when available: leverage prior requirements discussion and user's stated design intent
38	- Follow design-review.md process: Analysis → Critical Issues → Strengths → GO/NO-GO
39	- Limit to 3 most important concerns
40	- Engage interactively with user — ask clarifying questions, propose alternatives
41	- Use language specified in spec.json for output
42
43	3. Decision and Next Steps:
44	- Clear GO/NO-GO decision with rationale
45	- Provide specific actionable next steps (see Next Phase below)
46
47	## Important Constraints
48	- Quality assurance, not perfection seeking: Accept acceptable risk
49	- Critical focus only: Maximum 3 issues, only those significantly impacting success
50	- Conversation-aware: Leverage discussion history for requirements context and user intent when available
51	- Interactive approach: Engage in dialogue, ask clarifying questions, propose alternatives
52	- Balanced assessment: Recognize both strengths and weaknesses
53	- Actionable feedback: All suggestions must be implementable
54	- Context Discipline: Start with core steering and expand only with review-relevant steering or use-case-aligned local agent skills/playbooks
55	</instructions>
56
57	## Tool Guidance
58	- Read first: Load spec, core steering, relevant local playbooks/agent skills, and rules before review
59	- Grep if needed: Search codebase for pattern validation or integration checks
60	- Interactive: Engage with user throughout the review process
61
62	## Output Description
63	Provide output in the language specified in spec.json with:
64
65	1. Review Summary: Brief overview (2-3 sentences) of design quality and readiness
66	2. Critical Issues: Maximum 3, following design-review.md format
67	3. Design Strengths: 1-2 positive aspects
68	4. Final Assessment: GO/NO-GO decision with rationale and next steps
69
70	Format Requirements:
71	- Use Markdown headings for clarity
72	- Follow design-review.md output format
73	- Keep summary concise
74
75	## Safety & Fallback
76
77	### Error Scenarios
78	- Missing Design: If design.md doesn't exist, stop with message: "Run `/kiro-spec-design $1` first to generate design document"
79	- Design Not Generated: If design phase not marked as generated in spec.json, warn but proceed with review
80	- Empty Steering Directory: Warn user that project context is missing and may affect review quality
81	- Language Undefined: Default to English (`en`) if spec.json doesn't specify language
82
83	### Next Phase: Task Generation
84
85	If Design Passes Validation (GO Decision):
86	- Review feedback and apply changes if needed
87	- Run `/kiro-spec-tasks $1` to generate implementation tasks
88	- Or `/kiro-spec-tasks $1 -y` to auto-approve and proceed directly
89
90	If Design Needs Revision (NO-GO Decision):
91	- Address critical issues identified
92	- Re-run `/kiro-spec-design $1` with improvements
93	- Re-validate with `/kiro-validate-design $1`
94
95	Note: Design va

People who liked this also viewed

6 picks

Type