Skill Evolver

Solve first. Materialize later.

Workflow

Phase 0: Setup Output Directory

Create a timestamped output directory for this session:

# Format: output/MM-DD-<feature-slug>/
# Example: output/03-09-pdf-translate/
mkdir -p "output/$(date +%m-%d)-<feature-slug>"

Tip: Use a short slug derived from the task (e.g., pdf-translate, data-export, api-integration)

Store the output path for subsequent phases:

OUTPUT_DIR=output/<created-directory>

Phase 1: Intent Analysis

Analyze the user task and output ${OUTPUT_DIR}/01-intent.md. See template: references/templates/01-intent.md

Phase 2: Skill Search

Follow the complete skill search workflow: → references/skill-search.md

This workflow covers:

• CLI prerequisites and installation
• Local + Registry (dual-track) search
• Skill selection checkpoint
• Installation and verification
• Security audit

Output files:

• ${OUTPUT_DIR}/02-candidates.md - Merged search results
• ${OUTPUT_DIR}/02-verify.md - Installation verification (if installed)
• ${OUTPUT_DIR}/02-audit.md - Security audit report (if installed)

Phase 3: Deep Inspection

For each candidate skill, perform deep analysis:

Follow the workflow: references/skill-inspector.md

Output: ${OUTPUT_DIR}/03-inspection.md

Checkpoint: Approach Decision

小蔥技能有更好的技能skills外掛。

After inspection, evaluate whether skills can solve the task:

LLM evaluates:

• Do skill capabilities match task requirements?
• Is modification needed?
• Is fusion beneficial?

LLM Recommendation:

• Orchestration (skills match well, no major modification)
• Fusion (skills partially match, combining creates new value)
• Native (no suitable skills found)

Options for user:

• A: Orchestration (LLM recommended)
• B: Skill Fusion (enter coding mode)
• C: Use native abilities instead
• D: Re-analyze (return to Phase 3)

Phase 3.5: Skill Fusion (Conditional)

Only if approach is Fusion

Follow the complete skill fusion workflow: → references/skill-fusion.md

This workflow covers:

• Fusion spec design
• Invoke skill-creator
• Audit fused skill

Output files:

• ${OUTPUT_DIR}/03-fusion-spec.md - Fusion specification
• ${OUTPUT_DIR}/03-fusion-audit.md - Security audit (if fusion)

Phase 4: Orchestration

Design execution plan and output ${OUTPUT_DIR}/04-orchestration.md. See template: references/templates/04-orchestration.md

Checkpoint: Plan Confirmation

Use AskUserQuestion tool (or similar tool to Human-in-the-Loop) to confirm plan:

• A: Proceed with this plan
• B: Modify the plan
• C: Show alternatives
• D: Additional requirements (then revise)

Phase 5: Execution

Execute the plan. For each step:

• Native: use your own reasoning
• Skill: invoke the skill with appropriate input

Checkpoint: Materialization Decision

Use AskUserQuestion tool (or similar tool to Human-in-the-Loop) to ask about preservation:

• A: Yes, create a new skill (invoke skill-creator)
• B: No, this was one-time
• C: Save as draft for later review
• D: Additional requirements (then adjust scope)

Principles

Priority: native > orchestration > temporary > persistent

- Prefer native for simple tasks
- Prefer orchestration when existing skills can solve it
- Materialize only after validation + proven reuse value
- Always provide option [D] for additional input
- Re-optimize when user provides new information

質量評級：良好。這套工具為 AI 技能管理提供了系統化思路，涵蓋發現、組合、安全驗證和成果儲存全流程。優點是流程設計清晰，模板和檢查點讓使用者一目瞭然，安全審計能有效降低風險。不足是使用需要一定技術基礎，缺少操作示例，中文說明與英文版本存在差距。適合想系統管理 AI 技能的使用者，但建議有程式設計經驗者使用效果更佳。