gooseworks-ai/goose-skills / skills/marketing/run-organic-social
run-organic-social
VerifiedRuns 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 23.1 KB |
| references/calendar-craft.md | markdown | 11.5 KB |
| references/graphics.md | markdown | 5.8 KB |
| references/platform-native.md | markdown | 3.6 KB |
| references/platform-strategy.md | markdown | 8.7 KB |
| references/post-checks.md | markdown | 10.6 KB |
| references/report-shape.md | markdown | 6.6 KB |
| references/run-record.md | markdown | 8.5 KB |
| references/scheduled-refill.md | markdown | 6.9 KB |
| references/slot-anatomy.md | markdown | 7.6 KB |
| references/voice-card.md | markdown | 4.4 KB |
| skill.meta.json | config | 7.9 KB |
| tests/test-by-hand.md | markdown | 9.8 KB |
references/report-shape.md
View on GitHub# The social plan report
Written and delivered through the `write-report` skill (`../../write-report/SKILL.md`). Follow its rules: summary first, plain words, a fact always has a date and link, and no ids, paths, tool or playbook names. This file says what goes in each part for a social plan. The draft (step 2) and the final (step 6) have the same shape; the draft marks what's still pending.
**Title:** "<Brand> — social plan for <platforms>, <date>". Example: "Gooseworks — X plan, 18 Oct 2026".
## In short (at most 150 words, write-report §1's order)
- **What we looked at:** the platforms, the accounts and posts read, the date, and the main limit. Example (fictional): "X and LinkedIn on 20 Oct: 40 posts from 15 accounts in your niche, and platform notes from the last 90 days. Your own X feed needed a login, so we couldn't read it."
- **2–3 numbered findings,** each with its so-what and how sure (confirmed / likely / first look). Example: "1. Replies drive reach for small accounts right now (likely; two platform notes, one study), so the plan leads with a reply routine." Then what's working in your niche, and what you'll post and how often.
- **So, do this first (because of 1 …):** the one move, who, by when. Example: "Start replying to these 12 accounts every evening before you post, from Monday."
- **Time a week:** one line, the total hours (posts plus the reply routine), checked against the hours the marketer gave, or "a guess until you tell me your hours".
- On a refill, the one "since last time" result that matters most.
- Only points as sure as the body says. A belief the research couldn't confirm goes lower, with its doubt stated.
## Decisions for you (a short dated box)
E.g. Premium (with today's price and the recommendation), the exact claim lines to approve, which account it's for if unknown, the paid top-up. Each has a recommendation.
## Since last time (every run after the first; the top of the story)
3–5 lines from the last run record: what went out, how each format did against the account's own usual numbers per platform, each format test's verdict (or why it carries on), and whether last time's recommendations were done. Then a short table per platform: format · posts · typical result · your usual · what we'll do. On a first run, one line: "This is the first plan, so these numbers become the baseline."
## Per platform (one section each)
1. **How <platform> works right now:** 3–5 dated, linked facts that shape the plan, each with what it means for you. Say how sure we are.
2. **What's getting watched in your space:** a short table of the patterns (pattern · one example with link · why it works · our version). Then the "everyone does this, so we won't" line.
3. **Your account today:** handle, followers, what has worked so far, bio and pinned post (with suggested rewrites), and voice in one line.
4. **The strategy:** the job of the account, topics, the format mix (each format with its reason), hooks, cadence and posting times (in the audience's time zone and yours). Then **total time a week**: posts plus the reply routine, in hours, checked against the hours the marketer gave (or a stated guess until they do).
5. **How you break in:** the named accounts to reply to (linked, each with a reason tied to the buyer), the daily routine with minutes, the first posts, and one borrowed-audience move. **For a reply-led plan on X, a Premium line:** what X says Premium does for reply ranking, what a sized study found for reach (each with its date and link), today's price, and a recommendation for this account.
6. **A model account** (when the marketer named one, or one account is clearly the pattern): why it works, a table of its pillars and series, its outliers against its own baseline, what to adapt and what not to copy, and five tests for you.
7. **How we'll know it's working:** the signals for your account size, and the format tests with what each one checks and when we read it, described in words.
## On a refill: what your buyers' voices talked about this week
The topics that converged, spiked, started early or caused debate among the accounts you reply to, each with a linked post and the post we made from it (or why we skipped it).
## The posts
- The next three days in full, in the order they go out.
- Each post opens with a line saying what it is: "Tuesday, 8:30 pm IST (9 am New York) — screen-recording video, modelled on @x's 'watch it fix this' clips ([example](link))".
- Then the post exactly as it goes out: text ready to paste, the video script table with on-screen text and shot notes, or the rendered slides as linked images (with the slide copy beside them).
- Then one line for what you need to do (record this screen, fill in this number) and any approval it needs ("needs your yes: it's in your voice").
- **All posts** (an appendix at the end of the report): every other post of the two weeks, in posting order, in the same readable shape: the what-it-is line, the post exactly as it goes out, and what you need to do. The workspace calendar keeps the machine copy; the marketer never needs to open it.
## What we're not doing, and why
The tempting moves we decided against, one line each, e.g. "Not going video-first: video is half of X's views overall, but per-post studies show text doing as well for accounts like yours." Or: "Not replying mostly to other AI-tool builders: they aren't your buyers."
## Posting sheet
One table in posting order: date, time (your time and the audience's), platform, format, first line, what to prepare, posted ✓.
## What we couldn't check
Plain lines, one each, with why: "Couldn't read your X posts: X doesn't let us read a profile's feed without a login. Paste your last 5 posts and I'll tune the voice."
## Sources
Every link used, with its date, grouped per platform.
## Length
The body (everything after "In short", before the "All posts" appendix and Sources) stays at or under **3,000 words**, and "In short" at or under **150**. Count both before delivering; over budget blocks delivery (write-report §3). Cut first: repeat explanations, extra examples per pattern, the model-account table to its top rows; then move posts beyond the next three days to the appendix. The appendix sits outside the budget, but the report must work without it.
## Never in this report
- Slot ids, test codes, bucket names, file paths, check blocks or the internal flag syntax, including `[NAME: …]` brackets. Say "needs your yes" instead of "PERSON YES NEEDED", and "fill in: <what>" for the one allowed fill-in.
- Template posts. A post with more than one fill-in is not a post: rebuild it from found material (SKILL.md step 4).
- Raw tables of everything collected.
- Process narration ("I searched…", "step 3…").
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |