agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/week-posts/SKILL.md

week-posts

Skill2 starsChanged 2 months agoMITView on GitHub

Plan and draft a week of content using the author's configured pillars, source material, voice, cadence and optional Notion board.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read AGENTS.md, index.md, the relevant identity and audience pages, identity/proof.md, strategy/goals.md, strategy/pillars.md, …

    line 11
  2. Distinctive:

    Read the configured Notion taxonomy, topic page-body subtopics, recent published content and future cards when available.

    line 17
  3. Distinctive:

    If key material is missing, complete the supported part of the plan and identify the source needed for the rest.

    line 21
  4. Very specific:

    Use the local linkedin-copywriter skill for LinkedIn pieces.

    line 25

≈ “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

Workspace: all context paths below (identity, audience, strategy, voice, brand, raw, output, index, log, workspace preferences and context scripts) resolve from context/ in the kit root. Read both the root AGENTS.md and context/AGENTS.md. Skill-local references/ and flowchart scripts/ resolve from this skill directory.

Plan the week

Read AGENTS.md, index.md, the relevant identity and audience pages, identity/proof.md, strategy/goals.md, strategy/pillars.md, strategy/funnel.md and voice/linkedin-voice.md. Read local preferences if present.

Choose the dates and material

Use the requested dates, time zone, platform and cadence. Do not inherit a particular founder's weekdays or a fixed four-post schedule. If the user wants a dated plan and the time zone or cadence is unknown, ask for those choices together. An undated draft batch can proceed without them.

Read the configured Notion taxonomy, topic page-body subtopics, recent published content and future cards when available. Otherwise use the local strategy and supplied history. Do not claim recent topics are unused when history is inaccessible.

Select distinct source-backed angles and an appropriate pillar mix. One per pillar is a useful option, not a mandate. Avoid repeating a recent idea unless the new post has a clear new contribution. Pick one pillar, topic, subtopic and funnel job for each piece. Do not silently create a new taxonomy to fill a slot.

If key material is missing, complete the supported part of the plan and identify the source needed for the rest. Do not fabricate posts to hit a count.

Draft and save

Use the local linkedin-copywriter skill for LinkedIn pieces. Other platforms use the configured format and voice rules. Keep proof and conversion targets grounded.

A request to draft a week into the board authorizes creating draft cards in the configured board. Follow strategy/notion-schema.md; query existing dates and titles first. Use Status = Creating, one Pillar value, Platform, planned Publish date and one paste-ready text code block in each card. After an ambiguous result, query before retrying.

Without Notion, return the plan and drafts in chat. Do not start a local posts database or pretend cards were saved.

Report date, pillar, topic, funnel job and card link where created. State which content is still waiting on input. Log the run without duplicating post copy. A planned date is not a scheduled publishing action.

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.