Automation Designer
SkillMediaDesign safe recurring Codex automations with clear prompts, outputs, schedules, and gating rules.
Use Automation Designer in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Automation Designer and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Automation Designer skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
What this skill tells your AI
The instructions your AI receives, as published by hoavdc/codexkit in skills/codexkit-automation-designer/SKILL.md and read by Ahel’s review.
Use this skill when a task should happen repeatedly and you need more than just a schedule.
Automation quality bar
- the task must be self-contained
- output destination must be clear
- skip conditions should be explicit
- noisy automations should be rejected
Workflow
- Define the recurring problem.
- Write a prompt that describes only the task.
- Specify output shape and success criteria.
- Add guards: only if changed, only on weekdays, skip if empty.
- Choose a schedule that matches human response capacity.
Use references/automation-template.md as the default structure.
Quality Criteria
- Trigger conditions and input requirements are unambiguous
- Each automated step produces a verifiable output
- Error handling and fallback paths are defined
- Manual override points are documented
Verification (4C)
| Check | Question |
|---|---|
| Correctness | Does the workflow produce the expected output for the defined inputs? |
| Completeness | Are all trigger conditions, edge cases, and error paths handled? |
| Context-fit | Is the automation appropriate for the frequency and criticality of this task? |
| Consequence | If this ran unattended and failed silently, what would the downstream impact be? |
Edge Cases
- Input format varies unexpectedly — Add a normalization step at entry. Alert the operator on format mismatches.
- Downstream system is unavailable — Queue the output and retry with exponential backoff. Alert after N failures.
- Partial execution completes — Ensure idempotency — re-running from the start produces the same result without duplication.
Changelog
- v1.0.0 — Initial release
Signals
- GitHub stars
- 25
- Forks
- 13
- Last commit
- Oct 2026
Advanced
- Item type
- skill
- Key
codexkit-automation-designer- Source
- github.com/hoavdc/codexkit