agentleFS
MoeenNehzatiMoeenNehzati/famulus/skills/llm-wakeup/SKILL.md

llm-wakeup

Skill4 starsChanged 4 months agoMITView on GitHub

Use when the user asks to schedule or manage an automatic assistant-session wakeup after a usage reset or timeout.

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:

    When this skill is used, begin with:

    line 47
  2. Very specific:

    Do not guess a provider, session, alias, or reset time after an interface reports ambiguity.

    line 70

≈ “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
<!-- BEGIN BLUEPRINT INTERFACES -->

Generated from blueprint.yaml. Do not edit this block by hand.

Executable Interfaces:

Send the required caller (caller skill), interface, version, and arguments; optional dry_run defaults to false. Compact uses ordered positionals plus an option mapping; ordered raw argv uses positionals: [] plus every argv token in list options. Never mix forms.

  • llm-wakeup._rtx.interface.auto-policy — Manage opt-in automatic near-limit wakeup scheduling for one provider session.
    • Caller: llm-wakeup
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": ["action", "provider", "session-id"], "stdin": null} Required options: []; positional arity: 1..3; stdin: forbidden
  • llm-wakeup._rtx.interface.explicit-schedule — Persist a guarded wakeup for an explicitly identified provider session and reset time.
    • Caller: llm-wakeup
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--delay": "duration", "--message": "message"}, "positionals": ["provider", "session-id", "reset-time"], "stdin": null} Required options: []; positional arity: 3..3; stdin: forbidden
  • llm-wakeup._rtx.interface.infer-schedule — Infer provider, canonical session, and reset time before persisting a guarded wakeup.
    • Caller: llm-wakeup
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {"--delay": "duration", "--message": "message", "--text": "timeout-or-resume-text"}, "positionals": [], "stdin": null} Required options: []; positional arity: 0..0; stdin: forbidden
  • llm-wakeup._rtx.interface.setup — Install or refresh the wakeup integration without caller arguments.
    • Caller: llm-wakeup
    • Version: 1
    • Security level: 2
    • Alternative: default Arguments JSON (replace labels with actual values). Omit optional positionals and options that are not needed. {"options": {}, "positionals": [], "stdin": null} Required options: []; positional arity: 0..0; stdin: forbidden
<!-- END BLUEPRINT INTERFACES -->

When this skill is used, begin with:

Skill: llm-wakeup

Route by intent

  • Enable, disable, or inspect automatic wakeups: invoke auto-policy. The level is the action argument. on wakes the session only when the provider refused a turn for lack of quota and the session stopped there. force wakes it at reset whenever usage neared the limit, refused or not; pass it only when the user asks to be woken either way. off removes the policy, and status reports the level in effect.
  • Schedule after a timeout when provider, session, or reset may need discovery: invoke infer-schedule.
  • Schedule when provider, session, and reset are all explicit: invoke explicit-schedule.
  • Set up, refresh, or tear down the optional wakeup commands and dedicated due-delivery registration: invoke setup. For setup, first obtain the exact selected Python fingerprint and current plugin root; do not discover Python.

Pass message and delay only when the user supplies them. Otherwise preserve the interface defaults.

Do not guess a provider, session, alias, or reset time after an interface reports ambiguity. For auto-policy, ask for the missing provider or canonical session and retry auto-policy. For infer-schedule, ask for the missing explicit value; when provider, session, and reset are all explicit, route to explicit-schedule.

For auto-policy, report the resolved provider, canonical session, and policy state, including which level is in effect. For infer-schedule and explicit-schedule, report the resolved provider, canonical session, and local scheduled time. Report failures plainly without claiming a wakeup exists.

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.