agentleFS
flavien-iaflavien-ia/hypervibe-harness/skills/add-routine/SKILL.md

add-routine

Skill50 starsChanged 20 days agoApache-2.0View on GitHub

Create a recurring AI mission for YOURSELF, on your own Claude account: a morning brief, a Friday analysis, a watch that alerts you. Zero code, zero deployment, nothing added to the app.

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

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user's request already contains the mission and the cadence ("brief me on my competitors every morning at 8"), do NOT re-ask - go …

    line 20
  2. Very specific:

    If the routine touches a Hypervibe project (e.g.

    line 45

≈ “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

Add Routine - A recurring mission for YOUR Claude

Communication

  • Detect the user's language from the conversation (the user's own messages, anywhere in the session - not just this invocation: a bare slash command like /bootstrap carries no language signal by itself). If nothing in the conversation gives a signal, fall back to the OS locale (node -e "console.log(Intl.DateTimeFormat().resolvedOptions().locale)") before defaulting to English. ALWAYS reply in that language for every user-facing message: questions, progress, confirmations, summaries, errors - including any example text quoted in this skill, which is illustrative and must be translated, never sent verbatim.
  • Plain, non-technical language. A routine is "a mission your own Claude runs for you on a schedule" - never "a scheduled cloud agent job".
  • Show progress as a short natural-language checklist.

What this skill is

A thin, user-invocable front for the routine engine (_create-routine), so that the two shapes a user can name for themselves have a clean direct entry: /add-cron (scheduled app task) and /add-routine (personal recurring AI mission). The other two, an event-triggered in-app pipeline and an autonomous product agent, are chosen by /add-automation, which remains the orchestrator.

Step 1 - Gather the mission (light discovery)

If the user's request already contains the mission and the cadence ("brief me on my competitors every morning at 8"), do NOT re-ask - go straight to Step 2.

Otherwise, one question:

What should your Claude do for you, and when? For example: "every morning, read X and send me a 5-line brief", "every Friday, analyze Y and propose improvements".

Extract GOAL (the mission, in the user's words) and CADENCE (plain language).

Step 2 - The guard (do not skip)

Apply the operator-side test from the engine before anything else: if the output feeds the APP or its end users (cleaning the database, emailing customers, syncing displayed data), STOP and reroute honestly:

What you describe is something your app needs, so it must run on the app's infrastructure, not on your personal Claude account (if your subscription stopped, your app would silently break). The right command is </add-cron | /add-automation> - want me to run it?

Step 3 - Delegate to the engine

Invoke _create-routine with GOAL and CADENCE (and any expressed preference for cloud vs this computer). The engine handles everything: mechanism detection, the two honest warnings (runs on the user's account and subscription; cloud vs local trade-offs), the self-contained mission prompt validated by the user, creation, verification, and the management handover.

Step 4 - Summary

Relay the engine's result:

✅ Your routine <id> is active: <mission in 1 sentence>, <schedule in plain words>, next run <date/time>. To manage it, just tell me: "pause my routine", "change the schedule", "show me its last run", "delete it".

If the routine touches a Hypervibe project (e.g. "analyze MY PROJECT's errors weekly"), also invoke _update-claude-md on that project with the ## Routines (opérateur) section, same format as /add-automation Branch D.

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.