agentleFS
ntaffziintaffzii/Skill-Agents/skills/productivity/automation-design/SKILL.md

automation-design

Skill4 starsChanged 3 months agoMITView on GitHub

Design Codex automations, scheduled research jobs, recurring reports, reminders, monitors, thread follow-ups, and workspace jobs. Use when the user asks to set up, improve, schedule, template, audit, or design an automation, monitor, reminder, or recurring Markdown report.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask only when missing details would change the created automation.

    line 17
  2. Distinctive:

    Write a self-contained prompt

    line 19
  3. Distinctive:

    Keep schedule settings separate from task instructions.

    line 21
  4. Distinctive:

    Use human-readable schedule language unless a tool requires structured syntax.

    line 24
  5. Distinctive:

    When an automation tool is available and the user asked to create it, use the tool.

    line 28
  6. Distinctive:

    If schedule or destination is missing, ask before creation.

    line 29
  7. Distinctive:

    Prefer updating an existing automation over creating a duplicate.

    line 55
  8. Distinctive:

    Use current-source tools for news, prices, laws, schedules, product releases, and other changing facts.

    line 56
  9. Distinctive:

    Do not expose raw schedule syntax unless useful.

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Automation Design

Design reliable automation prompts and schedules.

Workflow

  1. Identify automation type
    • Choose reminder, thread follow-up, daily or weekly report, monitoring task, research digest, or workspace job.
  2. Capture requirements
    • Clarify task, schedule, timezone, output destination, source rules, language, failure behavior, and whether duplicates should be suppressed.
    • Ask only when missing details would change the created automation.
  3. Write a self-contained prompt
    • Include goal, scope, sources or file boundaries, output format, quality rules, and missing-information behavior.
    • Keep schedule settings separate from task instructions.
  4. Recommend schedule
    • Use human-readable schedule language unless a tool requires structured syntax.
    • State the timezone explicitly.
  5. Confirm or create
    • When an automation tool is available and the user asked to create it, use the tool.
    • If schedule or destination is missing, ask before creation.

Prompt Template

Task:
[What Codex should do]

Scope:
[Topics, files, repos, sources, or boundaries]

Quality rules:
- Use reliable sources or concrete local files.
- Include links or file paths.
- State uncertainty clearly.
- Avoid duplicate or low-value items.

Output:
[Markdown report, thread reply, file path, etc.]

Language and tone:
[Thai/English, concise/detailed]

Rules

  • Prefer updating an existing automation over creating a duplicate.
  • Use current-source tools for news, prices, laws, schedules, product releases, and other changing facts.
  • Do not expose raw schedule syntax unless useful.
  • Report what will happen, when it will happen, and where the result will appear.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.