agentleFS
timscheueraitimscheuerai/gtm-architecture-template/.agents/skills/oxygen-linkedin-marketing/SKILL.md

oxygen-linkedin-marketing

Skill2 starsChanged 2 months agoMITView on GitHub

Run OXYGEN LinkedIn content and warm-signal motions through Posts, Publishing, Signals, Tables and bounded Sequences.

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:

    Read the author's context and the runtime contract.

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Connect content to a useful next step

Read the author's context and the runtime contract. Use linkedin-copywriter for the actual grounded draft; this skill handles native delivery and engagement workflows.

WorkNative surface
Draft artifact and owned post dataPosts
Review, schedule and broadcast deliveryPublishing
Durable viewers, followers, connections and engagementSignals
Working qualification/enrichment rowsTables
New DM and warm follow-up cadenceSequences
Existing-thread replyMessages / Unibox

Discover the chosen motion with oxygen capabilities search "LinkedIn content and warm engagement" --json, then hydrate only its commands. Public/third-party research uses the current native public-research catalog where available; connected-account actions have their own limits and scope. Do not silently substitute another provider.

For a lead-magnet post, verify the resource URL and promise. Inspect the exact author/account, copy, media and schedule before requested publication. Record the Post and Publishing IDs and read back delivery state.

For comment-to-resource or network capture, inspect the capture window, dedupe keys, pagination and freshness. Separate capture from auto-enrollment. A standing outreach grant must specify the eligible cohort, destination Sequence, limits and stop conditions. Engagement alone does not establish fit or permission for broader outreach.

Owned-post public comments belong to the Publishing community queue. Check its freshness before trusting an empty queue. Use the native reply preview and content-bound approval action; do not manufacture approval or retry an unknown external effect.

For analytics, inspect current owned-post summary/detail commands. Read coverage and freshness alongside totals; null means unavailable. Preserve source/post/event IDs through qualification and Sequence results. Monitoring belongs to hosted subscriptions or Workflows.

Return the draft/published state, resource URL, captured/qualified/held counts where available, and native object links. Avoid equating post reach with attributable pipeline.

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.