weekly-cycle
Skill1 starsChanged 2 days agoMITView on GitHub
Starting and running the content factory's weekly cycle — creating the week folder, checking stages and gates, what to do at each stage. Use at the start of a week, when checking \"where are we now\", and when recovering after a failure.
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ai-visualizationSkill
- approval-packSkill
- content-atomizationSkill
- dispatchSkill
- fact-checkSkill
- ffmpeg-skillSkill
- hook-storylineSkill
- idea-diceSkill
- jurySkill
- memory-compactionSkill
- perf-loopSkill
- publish-kitSkill
- seamless-insertSkill
- setupSkill
- shoot-briefSkill
- sound-designSkill
- source-skeletonSkill
- style-memorySkill
- treg-gatewaySkill
- trend-scoutSkill
- utmSkill
- video-codeSkill
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
- Very specific: line 10
Create clients/<client>/weeks/<YYYY-Www>/ with the files from templates/week/ if they do not exist yet.
- Distinctive: line 33
No facts → do not invent; put the question in the approval pack.
≈ “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.
Files
Weekly cycle
Start of the week
- The week = the ISO week:
date +%G-W%V. - Create
clients/<client>/weeks/<YYYY-Www>/with the files fromtemplates/week/if they do not exist yet. - Fill in the header of
01-plan.md: the week's quotas fromquotas.yaml, the budget limit frompermissions.yaml.
Where are we now (recovery)
The state of the week is determined by files only, not by session memory:
| File state | Meaning |
no 01-plan.md, or it has status: draft | stage 1 |
01-plan.md has status: final, no 03-scripts/ for all IDs | stages 2–3 |
scripts exist, no 04-production/<ID>/review.md with PASS | stage 4 |
all hubs PASS, no 05-adaptations/ | stage 5 |
no 06-approval.md, or it contains decision: pending | stage 6 — waiting for the human |
approved units exist without a line in 07-publications.md | stage 7 |
no 08-retro.md | stage 8 |
Continue from the first unclosed stage. Do not redo finished work.
Unit statuses (the status field in the plan)
planned → brief_sent → scripted → produced → reviewed → adapted → in_approval → approved | rejected | rework → published | kit_ready
Stop conditions
- Budget exceeded → stop, ask the human.
- 3 FAILs in a row from the reviewer → stop for that unit, ask the human with examples.
- No facts → do not invent; put the question in the approval pack.
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
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.

