agentleFS
Sign inStart free
XuHo-ITXuHo-IT/Content-Agent-Kit/skills/daily-run/SKILL.md

daily-run

Skill3 starsChanged 3 months agoMITView on GitHub

Execute today's content run for an agent built with content-agent-kit. Use when the user says "run today", "tạo nội dung hôm nay", "do the daily run", or a scheduler fires the daily prompt. Reads the project PLAYBOOK.md, does today's phase, passes every item through the review gate, publishes, schedules, and reports.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Check history.json — skip duplicates.

    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

Daily run

  1. Open PLAYBOOK.md in the project (the source of truth). Re-read it fully — do not rely on memory.
  2. Determine today's phase = (day-of-year mod N) per §1, and do exactly that phase.
  3. (If crawling) pull fresh ideas first: node scripts/queue-client.mjs pull → work from queue_raw.json.
  4. Fan out one subagent per item (§2). Each writer MUST read WRITING_CRAFT.md first (§1 universal principles + its register §2/§3 + the banned-cliché list §4) and self-check against §6 before submitting. Each produces content + images + metadata per the §4 schema. Check history.json — skip duplicates. 4b. Video items (if the PLAYBOOK calls for any) — invoke create-video (writer reads VIDEO_CRAFT.md + video-templates/CATALOG.md, writes script.json, validates with --strict, renders). Render now, not at the posting slot: a render takes 3–5 minutes, so doing it here keeps the scheduled post instant. Keep the resulting videoPath.
  5. Review gate (mandatory, §2b) — invoke the review-gate skill / an independent review subagent on every item. Pass → continue. Fail → fix (2–3 rounds) → drop + log. Reject any forbidden output on sight.
  6. Publish: content → node scripts/publish.mjs <file>.json; chapters → node scripts/append.mjs <file>.json. Treat 409 as already-done. Record ids in ledger.json / titles in history.json.
  7. Schedule social (if any): node scripts/scheduler/build-queue.mjs items.json → register/run per docs/06. Never post restricted types (see PLAYBOOK). Video items go in as type:"video" carrying videoPath + post / comment / title / hashtags / platforms — see templates/state/queue.example.json.
  8. Access tiers, author, language per §3b/§3c/§0b. Never brand as "(AI)".
  9. Clean up per-run scratch files (§7).
  10. Report → brain/<id>/report.md (§7b): made / reviewed / published / dropped.

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.

Check your setup, free