Skip to content

Best Practices

Guidelines for designing effective skills and workflows.

Each skill should handle one clear task.

<!-- Good -->
---
name: check-broken-links
description: Detect broken links on the site
---
<!-- Bad -->
---
name: check-and-fix-everything
description: Check and fix the entire site
---

Skill prompts should explicitly state the expected deliverables.

Execute the following steps:
1. Scan TypeScript files in the `src/` directory for type errors
2. Output the error list as a Markdown table
3. Apply automatic fixes where possible
## Output format
| File | Line | Error | Fixed |
|------|------|-------|-------|

Place the execution-report skill at the end of workflows to report results back to HQ.

{
"pipeline_skill_names": ["analyze", "fix", "execution-report"]
}

3–5 steps is ideal. Long pipelines make error recovery difficult.

Insert review steps before destructive operations (deployments, data changes, etc.).

{
"pipeline_steps": [
{ "assigned_role": "engineer", "requires_review": false },
{ "assigned_role": "engineer", "requires_review": true },
{ "assigned_role": "engineer", "requires_review": false }
]
}

High-frequency execution (intervals under 5 minutes) consumes resources. Consider whether such frequency is truly necessary.

  • PM — Workflow design, context management, review approval
  • Engineer — Skill implementation, pipeline execution

Recording shared knowledge in project context makes it available to all assigned minions. This eliminates the need to repeat the same explanations in every skill.