---

name: run-organic-social description: >- Runs a brand's organic social: how each platform works now, a strategy per platform and two weeks of posts in the brand's or a person's real voice. Use when a marketer says "run organic social for my brand", "fill my social calendar", "plan two weeks of posts", "grow my X / LinkedIn / Instagram / TikTok", "ghostwrite my founder's posts", "which platforms should we be on?", "plan the social for our launch", "a TikTok or Reel script to shoot on my phone", "tear down @x's account", or "my accounts went quiet". The marketer posts by hand; nothing is posted or scheduled. Not for a standalone post or repurposing one piece — use make-content. version: 0.1.2

run-organic-social

A post list or focused research request: after shared setup, use marketing-data-access (../marketing-data-access/SKILL.md) and its focused-reads.md reference for requested post rows, dates, engagement and bounded rankings. For interpretation or voices, use the existing platform-research step, restricted to that question. Deliver the requested list/analysis; skip the full-plan opening, calendar, account-strategy intake and eight-example-per-platform gate. A top-voices list states its ranking evidence and coverage, rather than claiming an exhaustive directory.

Say once, at the start, in these words or close: "I'll look at how each platform works right now and what's getting watched in your space, then give you a plan and two weeks of posts. I can't post for you yet; you'll post by hand."

What you get

A report the marketer opens with one click (delivered through the write-report skill (../write-report/SKILL.md)):

• In short: what we looked at, the 2–3 findings with how sure, then the one move to make first, resting on them.
• Per platform:
  • how it works right now (dated, with sources);
  • what's working in this niche there, with linked examples;
  • the strategy for this account: its job, formats, topics, hooks, cadence and posting times, and the hours a week the whole plan needs;
  • how this account breaks in: named accounts to reply to, the daily routine, the first posts;
  • how we'll know it's working.
• Two weeks of posts, each modelled on a pattern that works on that platform, written the way a person posts there.
  • Video slots get a script with time, words, on-screen text and shot notes, which the marketer shoots on a phone or screen-records.
  • Text posts ready to paste.
  • Carousels, LinkedIn document posts, workflow diagrams and quote or stat cards, rendered as finished slides in the brand's style, where the host can render (references/graphics.md); otherwise the slide-by-slide copy.
  • The first three days in full at the top of the posts section; every other post in the report's "All posts" appendix, in the same readable shape. The workspace calendar is only the machine copy.
• A posting sheet (plus a CSV on request).
• What we couldn't check, in plain words.

Every post is checked for claims, voice and disclosure. Posts that speak for a named person are flagged for that person's yes.

For brand voice, read an existing company guide at brand/voices/blog-<brand-slug>.md alongside the account’s card and brand rules. Reuse transferable tone and bans; keep account-specific social patterns and never turn blog article length into a post limit. Preserve a guide’s provisional status.

Before you start

1. Setup first: do the marketing-guide skill (../marketing-guide/SKILL.md) §1–2 (connect, brand, brain read) before anything else; the job line is "I plan and write your social through it." Then, for this playbook:
   • If get_started shows a card, write one line and carry on with this ask; don't call card_wait (the card has no organic-social option). Even when it named the brand, call gooseworks:brand_read with no brand_id for its coworker_agent_id.
   • Brain path: open the map's required_reads, then chapters 11 how we sound, 14 rules, 15 how we work together (who approves a person's posts), 17 accounts and tools, 19 this week and what's coming, 20 our plan, 23 what is working; chapter 12 (look and files) only for designed slots. gooseworks:brand_knowledge_search for gaps: disclosure, off-limits topics, buyer language. Then gooseworks:brand_read lean with only sections: ["accounts","sources","organic"] (the brain doesn't hold own posts or saved sources).
   • Fallback path: gooseworks:brand_read lean with sections: ["summary","kit","learnings","accounts","sources","organic","products"], then product_ids for the products in play; gooseworks:knowledge_search for operating rules, disclosure and off-limits topics.
   • Never pass detail: "full": on a settled brand it returns 100k+ characters no host can read; the lean read carries every rule and claim.
2. "Tear down this one account"? Run the run-organic-social-platform-research skill (../run-organic-social-platform-research/SKILL.md) §3b on that account only and deliver it as a report through write-report: why it works, what to adapt, and five tests for this brand. Then offer the full plan in one line. One post, not a plan? If the ask is a single post or script, use the brand read and the voice card only. Write that one post to the platform's research card if a fresh one exists (social/research/, under 30 days). Otherwise do one quick web check of how that platform treats that format now. Run the run-organic-social-post-check skill (../run-organic-social-post-check/SKILL.md), then offer the full plan in one line.
3. Ask nothing yet, with one exception: a single blocking question is allowed up front when one fact changes everything and no public source can answer it (e.g. the person's handle, when the plan is for their own account). Do the free pass (step 1) first. Never ask a fact the free pass could find.
4. Load the last run (full plans and refills; not #2's one-offs). Run the Start steps of the run-memory skill (../run-memory/SKILL.md) with the inputs in references/run-record.md. It finds the last social calendar's run record, checks last time's recommendations and format tests against what went out and how it did, and writes the "since last time" lines that open the report. No record means a first run: say so, invent nothing, and freeze the baselines from this run's audit. A record exists and a calendar is running → this is a refill: go to step 7. "Start from scratch" (or "ignore earlier work") makes this a first run: don't read or carry the last record, earlier calendars or notes, and say so in one line ("Starting fresh: I won't use earlier plans or notes."); the brand's rules and approved claims still apply, and what the marketer says in this conversation holds.
5. Never assert a choice the marketer didn't make. "You set Instagram aside at setup" needs their own words behind it; a saved plan or flag written by an agent is not their choice. Say what the source shows and where it came from.

Steps

1. Free pass (ask nothing). Keep it proportionate: research the platforms the marketer named, or the top 1–2 recommended. Roughly 10–15 web searches and 15–20 page reads per main platform is enough; stop a line of search when it repeats what you have. Write the report once, then revise it in place. Hard gate: no draft report without a dated "how it works now" card and at least 8 linked examples of what's working in the niche, for each platform the marketer named (or the top recommended one). Other recommended platforms get a lighter read: the card plus 3 examples, deepened once the marketer picks them. If the host has no web search or browser, say so at the top of the report and in chat, and plan nothing from memory.

• Pick the platforms in scope first: the ones the marketer named. Otherwise recommend 2–3 from where the audience is and what the brand can make, and say why.

• Platform research (the run-organic-social-platform-research skill, ../run-organic-social-platform-research/SKILL.md), for each platform in scope:

  • how it works right now (web search, dated sources);
  • what's working in the niche (the free routes that work per platform, plus examples);
  • the brand's and the person's own accounts.

• Saved files, all in the coworker scope:

  • social/ (the last calendar, social/accounts.md, social/research/). A saved research card under 30 days old is reused only if it still meets this step's bar (8+ examples with numbers, at least 3 from accounts under 10k followers, a platform or sized-study source). Otherwise top it up. Files from other people's tests or drafts are not history.
  • brand/voices/
  • content/repurposed/, content/channels.md, content/pov/
  • research-market's and research-competitors' latest reports
  • the newest reports/performance/<date>.md

• Mine the raw material that's already public:

  • the person's own recent posts, read in the browser;
  • the brand's changelog, docs, blog, release notes, GitHub and product pages.

  Real shipped things, numbers and screenshots found here are what the first posts are built from.

• Own-account audit (the run-organic-social-account-audit skill, ../run-organic-social-account-audit/SKILL.md) and voice cards (the voice-card skill (../voice-card/SKILL.md), social additions in references/voice-card.md).

2. The draft report and one message.

• Write the strategy per platform (references/platform-strategy.md) and the first three days of posts (step 4). Where the account isn't known yet (whose it is, the handle), write for the most likely one and state that assumption at the top. only from found material and plain product facts, run through the run-organic-social-post-check skill (../run-organic-social-post-check/SKILL.md) (step 5). A post that needs the person shows the finished post plus one "needs from you" line, never a skeleton of brackets.
• Deliver them as a draft report through write-report.
• Then one message, at most a few lines plus a short list. It holds the link and the one move to make first. It asks only the decisions left:
  • the paid top-up for deeper niche and own-post reads: one yes to "up to N credits" (the spend-gate skill (../spend-gate/SKILL.md) branch B), with what it adds;
  • the 3–5 claim lines the posts need, for the scoped sign-off (the claims-gate skill, ../claims-gate/SKILL.md). Name each line exactly. "Check the brand kit" is not a yes to a line;
  • raw material for every named person the posts feature, one prompt per planned slot: something shipped, a mistake, a number they may share, an opinion they'd argue, a screenshot or clip they can record. Add the short voice interview when fewer than ~8 of their posts were found;
  • anything only the marketer knows: handles not found, hours a week, time zone, who approves a person's posts.
• When the marketer states a platform belief ("video works more on X now"), check it on the web before answering, then give a verdict: confirmed, contradicted or unclear, with the source. Say whether the evidence is about share of all activity (e.g. "video is half of impressions") or per-post reach for an account like theirs; only the second decides their formats. Neither agree nor refuse from memory. An unclear belief becomes a labelled test.
• Never ask before the draft exists (except the one blocking question in #3).
• Check the audience is the buyer. If the chosen platform reaches people other than the brand's buyer (e.g. X grows a B2B founder among builders while the buyer, a DTC marketing lead, is more on LinkedIn or Instagram), say so once, plainly, then follow the marketer's choice.

3. Deepen (only what the marketer said yes to).

• Run the paid reads inside the ceiling and log every charge.
• Fold the new examples into the patterns and strategy.
• Rebuild the voice card from the fuller corpus.

**4. Write