agentleFS
curvedinfcurvedinf/dev-skills/skills/activated/design-time-triggered-skill/SKILL.md

design-time-triggered-skill

Skill7 starsChanged 5 days agoMITView on GitHub

Create timed skills, periodic maintenance, interval triggers, shared timers. Design a triggered workflow with an explicit observation event and shared scratch timer state.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Verify first use, not due, due, interrupted, read-only, and concurrent-update cases.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Design a time-triggered skill

Define periodic work that runs when an agent observes a due timer, without requiring another user request. Use design-skill for general authoring conventions.

  1. Define the outcome, interval, scope, and non-user observation event. Distinguish the clock condition from when it is checked: weekly work checked at fresh-session startup runs at the next eligible startup, not autonomously on a wall-clock deadline.
  2. Assign a stable timer key, normally the skill name, in project-local agents/scratch/timers.json. Follow the shared timer contract. Preserve existing entries and completion history; never import another project's timestamps.
  3. Write the triggered skill with metadata.category: triggered: event, due condition, bounded procedure, completion evidence, and failure/deferral behavior; its description states the observation event and due condition so agents can trigger it from the description alone. State whether missed intervals collapse into one run; default to one maintenance pass, not replaying every missed period.
  4. Wire the event into instructions the host actually loads, such as AGENTS startup guidance. Name the skill and timer key, define once-per-event behavior, and preserve event state across context compaction. A description or discovery adapter is not a scheduler. Use allow_implicit_invocation: true for a Codex triggered adapter; event conditions still govern execution.
  5. Verify first use, not due, due, interrupted, read-only, and concurrent-update cases. Confirm one skill's completion preserves other timers. Check packaging and links; distinguish reviewed behavior from executed validation.

Record the event, interval, timer key, and verification limits in scratch records. Creating this workflow does not run or schedule its payload.

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.