workflow-orchestration
Workflow Orchestration
Prerequisites
MUST read references/bootstrap.md when the task modifies AGENTS.md or CLAUDE.md.
Workflow
1. Plan Node Default
- Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
- If something goes sideways, STOP and re-plan immediately - don't keep pushing
- Use plan mode for verification steps, not just building
- Write detailed specs upfront to reduce ambiguity
2. Subagent Strategy
- Use subagents liberally to keep main context window clean
- Offload research, exploration, and parallel analysis to subagents
- For complex problems, throw more compute at it via subagents
- One task per subagent for focused execution
3. Self-Improvement Loop
- After ANY correction from the user: update
docs/tasks/lessons.mdwith the pattern - Write rules for yourself that prevent the same mistake
- Ruthlessly iterate on these lessons until mistake rate drops
- Review lessons at session start for relevant project
- This lessons update is NON-REPLACEABLE, even when other process skills are active
4. Verification Before Done
- Never mark a task complete without proving it works
- Diff behavior between main and your changes when relevant
- Ask yourself: "Would a staff engineer approve this?"
- Run tests, check logs, demonstrate correctness
5. Demand Elegance (Balanced)
- For non-trivial changes: pause and ask "is there a more elegant way?"
- If a fix feels hacky: "Knowing everything I know now, implement the elegant solution"
- Skip this for simple, obvious fixes - don't over-engineer
- Challenge your own work before presenting it
6. Autonomous Bug Fixing
- When given a bug report: just fix it. Don't ask for hand-holding
- Point at logs, errors, failing tests - then resolve them
- Zero context switching required from the user
- Go fix failing CI tests without being told how
Task Management
- Plan First: Create a task tracker with checkable items before implementation.
- Cross-Skill Compatibility (Task Tracker): If another active skill defines its own task-tracking artifact, respect that artifact as the primary tracker (this may replace
docs/tasks/todo.md). - Verify Plan: Check in before starting implementation.
- Track Progress: Mark items complete as you go.
- Explain Changes: Provide a high-level summary at each step.
- Document Results: Record a final review in the active task-tracking artifact.
- Capture Lessons (Hard Requirement): Update
docs/tasks/lessons.mdafter corrections. This cannot be replaced bytodo,progress,findings, or any other skill artifact.
Cross-Skill Priority
- Task tracking: Follow the active skill's tracker format when multiple process skills are loaded.
- Lessons:
docs/tasks/lessons.mdis always required for user corrections while this skill is active.
Core Principles
- Simplicity First: Make every change as simple as possible. Impact minimal code.
- No Laziness: Find root causes. No temporary fixes. Senior developer standards.
- Minimal Impact: Changes should only touch what's necessary. Avoid introducing bugs.
More from shihyuho/skills
lessons-learned
Use when starting, executing, or finishing non-trivial implementation tasks where reusable constraints may matter. Recall relevant lessons before work, capture reusable corrections or discoveries during and after work, and keep project memory in `docs/lessons/`.
101fanfuaji
Use when user requests Chinese terminology conversion, checking, or ensuring terminology - "使用繁體中文", "使用台灣用語", "轉換成台灣用語", "確保都是台灣用語", "統一台灣用語", "改成台灣用語", "用台灣的說法", "簡體轉繁體", "繁體轉簡體", "全部改成繁體", "轉成台灣繁體", check/ensure Taiwan/Hong Kong/China terminology, simplified/traditional conversion, or phonetic transcription (Pinyin/Bopomofo)
60executing-plans-preflight
Use before any implementation start — auto-detects and fixes git state issues (branch, dirty files, remote sync) with one confirmation per fix. Trigger on "start implementation", "implement this plan", "start coding", "execute plan", "開始實作", "執行計劃", or any signal that coding is about to begin.
42agent-install-guide
Use when creating INSTALL.md, setup guides, or configuration instructions intended to be executed by AI agents.
35harvest
Capture project memory from planning-with-files source-of-truth into Obsidian-compatible second-brain notes in docs/notes. Use for milestone summaries, decision capture, and timeline snapshots. Trigger on: harvest, /harvest, harvest this, save this to second brain, save what we just did, document this work, capture this knowledge.
29skill-design
Design and refactor Agent Skills with concise, high-signal instructions and explicit trigger metadata. Use when creating a new skill, revising SKILL.md/README.md structure, or improving skill discoverability and portability.
27