agentleFS
matteotittamatteotitta/claude-marketing-content/skills/content-ops/SKILL.md

content-ops

Skill0 starsChanged 31 days agoMITView on GitHub

Turns a content strategy into a system a team can run: recurring series, a cross-channel calendar, content briefs,

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. LazyIsEfficient/agentic-os★ 17same name
    2. varunk130/ai-marketing-claude-skills★ 1same name
    3. Th3Circle-app/agent-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use it once a strategy exists and the team is ready to produce, when output is erratic, or when pieces keep stalling in review.

    line 17
  2. Very specific:

    Don't use it to build the strategy (run /content-strategy first), to write the pieces, or to audit what already exists (/content-audit).

    line 19
  3. Very specific:

    Read these if they exist. Agency users: swap context/ for clients/<client>/context/.

    line 23
  4. Distinctive:

    Ask the user for:

    line 29
  5. Very specific:

    If there's no strategy file, stop and suggest /content-strategy.

    line 35
  6. Very specific:

    Every claim, number and customer reference has a source.

    line 52
  7. Distinctive:

    Every calendar entry traces to a series and a cluster from the strategy.

    line 61
  8. Very specific:

    Write to outputs/content/MMYY-content-ops.md: series plan, cascade map, calendar, brief template with the first briefs filled, pipeline …

    line 74

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Content ops

A strategy says what to publish. This skill decides who makes it, when, from what brief, and who checks it before it goes out. The output is a calendar, a brief template, a pipeline and a review checklist sized to the team you actually have.

When to use it

Use it once a strategy exists and the team is ready to produce, when output is erratic, or when pieces keep stalling in review.

Don't use it to build the strategy (run /content-strategy first), to write the pieces, or to audit what already exists (/content-audit).

Inputs

Read these if they exist. Agency users: swap context/ for clients/<client>/context/.

  • outputs/content/*-content-strategy.md: clusters, funnel mix, channels, volume targets. Required.
  • context/brand/: voice rules, which become review criteria.
  • context/messaging/: approved claims and proof points, which reviewers check against.

Ask the user for:

  • Team: who is involved and hours per week each.
  • Tools: where the calendar and pipeline will live (Notion, Airtable, a spreadsheet, a project tool).
  • Who has final sign-off, and anything that needs legal or compliance review.

If there's no strategy file, stop and suggest /content-strategy. If you only have clusters and channels, carry on and flag what's missing.

Steps

  1. Design the series. Give each cluster one to three recurring series with a clear arc: a problem series, a how-it-works series, a case series, an opinion series. Each instalment should build on the last. Produces: a series list with cluster, funnel stage, cadence and the first four titles.
  2. Plan the cascade. For the anchor format, map which smaller pieces come out of it, on which channel, in which order. A typical pattern: anchor piece on day 1, two LinkedIn posts that week, a newsletter mention the next. Produces: a cascade map.
  3. Build the calendar. Lay out 8-12 weeks across channels. Keep a two-week buffer of finished pieces and one open slot a week for timely topics. Produces: a calendar table with date, channel, series, title, funnel stage, owner and status.
  4. Write the brief template. Every piece starts from a brief: the ICP problem it answers, the one point the reader should take away, the funnel stage, the proof or example to use, the call to action, the format and length, the owner and the due date. Produces: a template plus filled briefs for the first two weeks.
  5. Set the pipeline. Stages: idea, briefed, drafting, review, approved, scheduled, published, reviewed for results. Each stage has an owner and a clear exit rule (for example, "review" ends when the reviewer signs off against the checklist). Produces: a stage table.
  6. Fit roles to the team. Solo: one person writes and reviews, with a waiting period before publishing and design done with templates or AI help. Small team: split writer and reviewer. Larger team: add an editor and a designer. Produces: a roles table with hours per week.
  7. Write the review checklist. What every piece is checked against before it ships (see below). Produces: a checklist the reviewer runs on every piece.
  8. Set the results review. A monthly look at what performed by series and format, with rules: a series that clearly beats the channel average gets more slots; one that trails for two months gets cut or changed. Produces: the review agenda and those rules.

The review checklist

  • Answers the ICP problem named in the brief.
  • Makes one point, stated early.
  • Every claim, number and customer reference has a source. Missing ones are marked [source needed] and the piece doesn't ship until they're filled.
  • Matches the voice rules in context/brand/ and the approved claims in context/messaging/.
  • Has one call to action that fits the funnel stage.
  • Reads like a person wrote it: contractions, plain words, no filler openers or buzzwords.
  • Compliance or legal sign-off where required.

What good looks like

  • The calendar is realistic for the stated hours, with buffer.
  • Every calendar entry traces to a series and a cluster from the strategy.
  • Briefs are short enough to fill in five minutes and specific enough that two writers would produce similar pieces.
  • Nothing ships without passing the checklist.

Mistakes to avoid

  • Calendars with no buffer. One sick week and the whole thing slips.
  • Review by gut feel. Use the checklist so feedback is consistent.
  • Too many stages for a solo operator. Collapse them.
  • Treating the calendar as fixed. The monthly review exists to change it.

Output

Write to outputs/content/MMYY-content-ops.md: series plan, cascade map, calendar, brief template with the first briefs filled, pipeline stages, roles, review checklist, results-review rules.

Next step: write the pieces with /thought-leadership for long-form and /newsletter for the newsletter.

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.