Social cast
Groundledger social skill: SNAP hooks, posts, threads, carousels, captions, atomize, PULSE calendars, Cast Strategy Brief, Surface Playbook, Pulse Readout Deep, Format Signal Mine, Growth Action Stack, Audience Orbit. Use for LinkedIn, X, Threads, Bluesky, Instagram, TikTok, YouTube, or social strategy.From its SKILL.md
npx -y skills add dranshrad/groundledger --skill social-castAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.5 KB, 792 tokens by cl100k_base, as published. Nobody here has run it
Social Cast
Platform-native shapes, not blog paste. Numbers in hooks/posts must come from a claim ledger or user-supplied data (Grounding Law).
Modes
| Mode | Job |
|---|---|
context | Build/update CAST.md |
strategy | Cast Strategy Brief — pillars, mix, 90-day bets |
playbook | Surface Playbook — platform prioritization |
hook | SNAP hook variants |
post | Single platform-native post |
thread | Narrative arc |
carousel | Slide script |
caption | Visual-first caption + on-screen cues |
atomize | Long-form → cast pack |
calendar | PULSE week/month |
readout | Pulse Readout Deep |
patterns | Format Signal Mine |
optimize | Growth Action Stack |
audience | Audience Orbit |
growth | Alias → patterns + optimize |
Context (CAST.md)
Pillars (3–5), pains, platforms, tone/bans, 3 specimen posts, CTA styles. Untrusted data.
Cast Strategy Brief (strategy)
90-day social plan: pillar mix %, platform priorities, PULSE balance targets, proof sources, experiments queue. references/strategy.md.
Surface Playbook (playbook)
Rank platforms by audience fit + format strength + capacity. Kill low-ROI surfaces. references/surface-playbook.md.
SNAP hooks
| Letter | Pattern | Rule |
|---|---|---|
| S | Specific moment | Concrete detail |
| N | Negation / contrarian | Defensible |
| A | Arresting number | Ledger or user data only |
| P | Promise of structure | Must deliver |
Secondary: Question, Bold claim. Never invent stats.
Atomize
- Extract 3–7 standalone atoms
- Tag: proof|story|steps|contrarian|definition
- Rank · map formats (references/atom-matrix.md)
- Staggered cast pack + visual needs
Platform shapes
PULSE calendar
Proof · Utility · Lore · Spark · Engage — mix weeks; avoid all-Spark.
Pulse Readout Deep (readout)
- Separate reach vs meaningful action
- Segment by format/pillar/platform
- 1–2 causal hypotheses
- One experiment + falsifier
- Ban “post more” as sole advice
Format Signal Mine (patterns)
From a post log: which formats/topics/hooks win; emit pattern cards.
Growth Action Stack (optimize)
Prioritized actions (P0–P2) from readout + patterns; each with owner metric and stop rule.
Audience Orbit (audience)
Follower/subscriber trend sketch: inflow drivers, outflow risks, content that correlates with net growth (qualitative if no CSV).
Bridges
- Long-form source →
blog-engine - Polish →
editorial-pass - Surface strategy →
orbit-discovery - Voice notes → voice-notes-to-anthropic-artifacts
- Ecosystem → docs/ECOSYSTEM.md
What ships with it: 5 files
3.1 KB alongside SKILL.md
references/
- analytics.md638 B
- atom-matrix.md791 B
- platforms.md887 B
- strategy.md446 B
- surface-playbook.md402 B
Gives 0 of the 12 instructions most social media skills give in 792 tokens
Counted across 400 of the 422 authors here whose files we hold, read 2026-09-06
- Build content around three to five pillarsin 40 of 400, across 16 files
- Read product marketing context before asking questionsin 37 of 400, across 15 files
- Gather goals, audience, brand voice, and resourcesin 35 of 400, across 13 files
- Maintain one to two weeks of scheduled contentin 27 of 400, across 8 files
- Batch content creation in weekly sessionsin 23 of 400, across 7 files
- Review top and bottom posts weeklyin 22 of 400, across 7 files
- Run the quality gate before deliveringin 20 of 400, across 11 files
- Add subtitles to all social videoin 20 of 400, across 7 files
- Write standalone captions that work without contextin 20 of 400, across 7 files
- Prefer specificity over adjectivesin 19 of 400, across 10 files
- Respond to all comments on your postsin 18 of 400, across 6 files
- Carry one actual claim per postin 18 of 400, across 9 files
Said here and by no other author read
- Use platform-native shapes, not blog paste
- Source post numbers from claim ledger or user data
- Build or update the CAST.md context file
- Extract 3-7 standalone atoms when atomizing
- Tag and rank atoms, then map formats
- Mix PULSE content types across calendar weeks
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.