ptarmiganlabs/butler/agentic-workflow-designer

Workflow Designer

Use this skill to run a structured interview with users who know their goal but not the workflow syntax yet, then generate one complete workflow .md file.

When to Use This Skill

Use this before .github/aw/create-agentic-workflow.md when requirements are unclear or incomplete.

• Use skills/agentic-workflow-designer/SKILL.md to discover and confirm requirements.
• Use .github/aw/create-agentic-workflow.md once requirements are clear and ready for implementation.
• Use .github/aw/agentic-chat.md when the user wants a specification/pseudo-code instead of a runnable workflow file.

Interview Framework

Ask one question at a time. Move to the next phase only after the current phase is clear.

Phase 1: Goal

Ask: "What do you want to automate?"

Capture:

• Workflow name (kebab-case candidate)
• Brief description
• Optional emoji

Phase 2: Trigger

Ask: "When should this run?"

Follow up only if needed:

• Which event type(s)?
• Any filters (labels, branches, commands)?
• Scheduled cadence (daily/weekly/hourly)?

Map to the on: block.

Phase 3: Scope (Read/Write)

Ask:

• "What should it read?" (issues, PRs, code, discussions, CI data)
• "What should it create or update?" (comments, issues, PRs, labels)

Map to:

• permissions: (keep read-only for agent job)
• tools:
• safe-outputs:

Phase 4: Data Strategy

Ask:

• "What data does the agent need to make decisions?"
• Follow up: "Can we pre-fetch and aggregate that data with shell commands so the agent only reads compact JSON?"

Capture:

• Whether steps: should pre-fetch GitHub data with gh + jq
• Output paths under /tmp/gh-aw/data/
• Whether batch work should use sub-agents

Map to:

• steps:
• Prompt references to pre-computed file paths

Phase 5: Guardrails

Ask: "Should it block merging, just advise, or silently log?"

Capture:

• Visibility expectations (comment, issue, no visible output)
• No-op behavior expectation

Guide toward safe output behavior and explicit noop instructions.

Phase 6: Context & Network

Ask: "Does it need external APIs, web access, package installs, or MCP servers?"

Follow up:

• "Any third-party services or MCP servers to include (for example Slack, Jira, Datadog, custom internal MCP)?"
• "Are you deploying on GitHub.com, GHEC with custom endpoints, or GHES?"
• For each integration, identify required auth from source docs and map it to GitHub Actions secrets + workflow env variables.
• Ask for exact external domains (FQDN/wildcard).

Map to:

• network.allowed
• Optional MCP/GitHub tool usage in tools:
• secrets: / env: wiring for integration tokens
• GHES/GHEC settings such as engine.api-target and aw.json ghes: true (when applicable)

Phase 7: Engine (optional)

Ask only if ambiguous: "Any AI engine preference?"

If no preference, suggest default:

• "I'd suggest Copilot since you haven't mentioned a preference. Sound good?"

Map to engine: only when not default.

Phase 8: Confirmation

Present a structured summary and ask for approval before generation.

Decision Heuristics

Trigger Mapping

Safe Output Mapping

Network Mapping

Tool Mapping

Pattern Heuristics

Integration Auth Mapping

When the user names a third-party service or MCP server:

1. Confirm whether native tool, MCP server, or safe-output job is the right integration path.
2. Look up the integration's auth requirements and required scopes before finalizing the design.
3. Provide a concrete setup checklist with:

• required GitHub Actions secrets (names to create)
• workflow env variables that consume those secrets
• minimum token scopes/permissions needed

Output format to use:

Integration auth setup:
- <service-or-mcp>: <purpose>
  - Secrets to create: <SECRET_NAME>, <SECRET_NAME>
  - Workflow env vars: <ENV_VAR>=${{ secrets.<SECRET_NAME> }}
  - Required scopes/permissions: <least-privilege scopes>

Never suggest committing plaintext tokens.

Data Strategy Mapping

Token Optimization Defaults

Apply these defaults unless the user explicitly asks otherwise:

1. Use DataOps by default for GitHub reads: pre-fetch/aggregate with gh + jq in steps:, store compact JSON in /tmp/gh-aw/data/, and point the prompt to those files (see .github/aw/token-optimization.md for details).
2. Keep tool surface minimal: default to tools.github.mode: gh-proxy, include only required toolsets, and prefer bash + gh for simple reads.
3. For batch workloads, split items into compact data and suggest sub-agent processing with model: small.
4. Keep prompts compact: concise imperative instructions, explicit file paths, single-line noop guidance, and stable instructions before dynamic content.

Progressive Disclosure Rules

1. Never dump all options at once; ask one targeted question at a time.
2. Skip questions when answers are inferable from prior user statements.
3. Offer smart defaults and request confirmation instead of over-questioning.
4. Ask at most 5 questions before presenting a summary; then ask "anything else?" if needed.
5. Detect done signals (that's it, looks good, generate it) and proceed to generation.

Confirmation Format

Use this exact structure:

📋 Proposed workflow:
- Name: <workflow-id>
- Trigger: <event + key options>
- Engine: <engine or default>
- Tools: <tool summary>
- Safe outputs: <list or none>
- Network: <allowed summary>
- Integrations/Auth: <service/mcp + required secrets/env vars>
- Deployment: <GitHub.com or GHEC/GHES details>
- Intent: <one-sentence task>

Then ask: "Ready to generate, or want to adjust anything?"

Generation Template

After confirmation, generate one workflow file using the same skeleton style as .github/aw/create-agentic-workflow.md.

---
emoji: <emoji>
description: <brief description>
on:
  <trigger config>
permissions:
  contents: read
  issues: read
  pull-requests: read
tools:
  github:
    mode: gh-proxy
    toolsets: [default]
steps:
  -name: <optional data prefetch>
    run: |
      mkdir -p /tmp/gh-aw/data
      <gh + jq commands that produce compact JSON>
safe-outputs:
  <safe-output-types-if-needed>
network:
  allowed:
    -defaults
    -<additional entries if needed>
---
 
# <Workflow Name>
 
## Task
 
<clear instructions tied to trigger context>
If `steps:` includes pre-fetch commands, read the resulting `/tmp/gh-aw/data/*.json` files instead of broad live re-fetches.
 
## Safe Outputs
 
-Use configured safe outputs for all visible write actions.
-Call `noop` with a short reason when no action is needed.

Validation Checklist

Before final output, run this internal self-check: