workflows
The workflow for AI-assisted development: complexity detection (LOW/MEDIUM/HIGH), problem-type routing, branch strategy across repositories, and the create - analyze - implement - archive flow for a spec. Use when: starting work on a spec, deciding how much analysis a task needs, planning a change that spans several projects, checking which branch belongs where. Do NOT use for: the spec files' own layout (use the spec-structure skill), how to run tests (that is the testing rule).
Target: Design & content creation. Automatically collected · unverified.
Excerpt from the author’s documentation
Extracted from a fixed version of SKILL.md in its original language. This is the author’s documentation; installation, compatibility and runtime results have not been verified by this site.
Read the original English text
Topics in the source
- Workflows for AI-assisted development
- Table of contents
- Complexity detection
- LOW complexity (Quick Fix)
- MEDIUM complexity
- HIGH complexity
- Problem type routing (Quick Reference)
- Branch strategy
Complexity detection LOW complexity (Quick Fix) MEDIUM complexity HIGH complexity Problem type routing (Quick Reference) Branch strategy The spec workflows See also -- Principle: Match the scope of the documentation to the complexity of the task. Grading: the grade is set once the code has been read, by the risk of the change. The criteria and two worked examples are in aide-analyze's complexity-and-analysis.md, section "Classification", and nowhere else. Each level below says what its grade means for the analysis and for the documents. Analysis scope: Read ONLY the mentioned file Documentation: Short and concise (< 200 lines total) Estimate: Minutes to hours (< 2 hours) -- Analysis scope: Find files related to the component/module Find related tests and usage sites, and stop there Documentation: Moderate detail (100-300 lines total) Estimate: Hours to days (2-16 hours) -- Analysis scope: Search the codebase broadly for patterns Categorize files by complexity Analyze API impact (frontend - backend) Identify edge cases and risks Documentation: Comprehensive analysis (300-800 lines total) Estimate: Days to weeks (1-10 days) -- Start every problem type from the project's OWN documenta
This is an excerpt. Refer to the complete source and its current requirements.
- Source repository
- ragnarwestad/aide
- Source file
- core/skills/workflows/SKILL.md
- Fixed revision
- 4accd2a3379f990472d375916c4972aa2a1d0c8b
Requirements
- Only the author’s Skill metadata is included. Read the full instructions to check dependencies, licensing and conditions of use.
A small first task
先阅读原作者说明，再决定是否在自己的 AI 工具中使用。
Instructions for your AI tool
- Claude Desktop: resource-specific guide not available yet
- Claude Code: resource-specific guide not available yet
- Cursor: resource-specific guide not available yet
- Codex: resource-specific guide not available yet
Author documentation is not live verification by this site. Without evidence, we do not mark a resource as compatible, safe or free.
Sources and evidence
This record was collected automatically. Its documentation, suitability and runtime behavior have not been manually verified.
Author: ragnarwestad/aide · original repository metadata. Documentation review: Not reviewed. Last source check: 2026-11-10T13:00:43.340Z.
Categories are inferred from names, descriptions and paths. They do not establish compatibility.
License and attribution
MIT. Third-party content and copyright remain with their authors. Refer to the original license and terms.
Original license ↗Synchronization, copying and user-reported success do not mark a resource as runtime-tested.
Limitations and notes
- Collecting metadata does not mean this site has installed, adapted, runtime-tested or security-reviewed the resource.