AgentSkillsCN

new-module-flow

模块脚手架的分步流程。关键词:模块、流程。

SKILL.md
--- frontmatter
name: new-module-flow
description: "Step-by-step flow for module scaffolding. Keywords: module, flow."

Flow: New Module Instance

This doc contains the step-by-step flow. For inputs, tools, outputs, and safety, see /.system/skills/ssot/repo/scaffolding/new-module/SKILL.md.


Step-by-Step Flow (AI + Human)

Step 1: Collect Parameters (AI -> Human)

AI asks human for:

  1. Module ID (validate: unique, snake_case)
  2. Module description
  3. Optional: module_type (if type_graph.yaml exists)
  4. Optional: initial interfaces

Human checkpoint: Confirm parameters before proceeding.

Step 2: Validate Inputs (AI)

AI validates:

  • module_id uniqueness against existing modules
  • module_type exists in /type_graph.yaml (if specified)
  • No naming conflicts

Step 3: Preview Changes (AI)

AI runs orchestrator with --dry-run:

bash
python scripts/devops/scaffold/new_module.py   --module-id <module_id>   --description "<description>"   --dry-run

AI presents planned_changes to human.

Human checkpoint: Review and approve planned changes.

Step 4: Execute Scaffold (AI)

AI runs orchestrator without --dry-run:

bash
python scripts/devops/scaffold/new_module.py   --module-id <module_id>   --description "<description>"

Step 5: Regenerate Derived Registries (AI)

AI triggers Module Runner automation:

bash
python scripts/modular/registry_build.py

Step 6: Verify Results (AI)

AI verifies:

  • Module directory exists with required files
  • MANIFEST.yaml is valid
  • Derived registries are updated

Step 7: Record in Workdocs (AI)

AI records scaffold execution in appropriate workdocs:

  • Task ID, timestamp, parameters
  • Files created
  • Any warnings or follow-ups