Create project guidance documents for topics such as API conventions, testing, security, and deployment. The skill examines existing code patterns and relevant templates, then writes focused documents that agents can use as ongoing project memory.
中文简介正在准备中。当前显示英语简介。
Create custom steering documents for specialized project contexts
安装前可以查看交给 AI 代理的指令内容。
<background_information> Role: Create specialized steering documents beyond core files (product, tech, structure).
Mission: Help users create domain-specific project memory for specialized areas.
Success Criteria:
If steering context is already available from conversation, skip redundant file reads. Otherwise:
{{KIRO_DIR}}/settings/templates/steering-custom/ for available templatesrules/steering-principles.md from this skill's directory for steering principlesAsk user for custom steering needs:
Check if template exists:
{{KIRO_DIR}}/settings/templates/steering-custom/{name}.md if availableAnalyze codebase (JIT) for relevant patterns:
The following research areas are independent and can be executed in parallel:
If multi-agent is enabled, spawn sub-agents for each area above. Otherwise execute sequentially.
After all parallel research completes, synthesize findings for steering document.
Generate custom steering:
rules/steering-principles.md from this skill's directoryCreate file in {{KIRO_DIR}}/steering/{name}.md
Templates available in {{KIRO_DIR}}/settings/templates/steering-custom/:
Load template when needed, customize for project.
From rules/steering-principles.md (in this skill's directory):
ls: Understand relevant structureJIT Strategy: Load template only when creating that type of steering.
Chat summary with file location (file created directly).
✅ Custom Steering Created
## Created:
- {{KIRO_DIR}}/steering/api-standards.md
## Based On:
- Template: api-standards.md
- Analyzed: src/api/ directory patterns
- Extracted: REST conventions, error format
## Content:
- Endpoint naming patterns
- Request/response format
- Error handling conventions
- Authentication approach
Review and customize as needed.
Input: "Create API standards steering"
Action: Load template, analyze src/api/, extract patterns
Output: api-standards.md with project-specific REST conventions
Input: "Document our testing approach"
Action: Load template, analyze test files, extract patterns
Output: testing.md with test organization and mocking strategies
.cursor/, .gemini/, .claude/){{KIRO_DIR}}/specs/ and {{KIRO_DIR}}/steering/ are acceptable; avoid other .kiro/ directories还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Add coding-agent support to cc-sdd through a documented workflow. Research the agent’s official formats, prepare an integration plan, implement registry entries and templates, and verify generated files, including Japanese and English output.
中文简介正在准备中。当前显示英语简介。
Investigate blocked implementation work and recurring failures using error output, code changes, configuration, and dependency evidence. Get a root cause report with a focused repair plan, verification steps, and a recommendation to retry, block, or seek human input.
中文简介正在准备中。当前显示英语简介。
Clarify a development request through structured questions and choose a practical next step: update an existing specification, create new ones, or implement directly. For new specifications, record scope, approach, and dependencies in planning files.
中文简介正在准备中。当前显示英语简介。
Implement approved tasks through test-driven development, writing tests before code. Run all pending tasks sequentially with subagents or select tasks for direct execution, then track completion using reviews and verification evidence.
中文简介正在准备中。当前显示英语简介。
Implement approved development tasks one at a time using test-driven development, which starts with a failing test. Process all pending tasks or selected ones, check changes against requirements and design, and update progress after review and completion verification.
中文简介正在准备中。当前显示英语简介。
Implement approved tasks using test-driven development, writing tests before code. Run all pending tasks one at a time or select specific tasks, with configurable review and verification before updating completion status.
中文简介正在准备中。当前显示英语简介。