Social cast

Skill dranshrad/groundledger/skills/social-cast

Groundledger: MIT agent skills for Claude Code, Cursor & Cowork — grounded blog SEO/AEO, PROBE site SEO, SAFE paid media, SPARK editorial, SNAP social, ORBIT discovery

Install

npx -y skills add dranshrad/groundledger --skill social-cast

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

12 days oldThe repository was created 12 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
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 author says it does

Copied from the file, not written here

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.

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

references/platforms.md

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

references/analytics.md

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

Gives 0 of the 12 instructions most social media skills give in 792 tokens

Counted across 489 of the 492 authors here whose files we hold, read 2026-08-06

build content around three to five pillarsin 24 of 489, across 12 files
read product marketing context before asking questionsin 23 of 489, across 13 files
respond to all comments on your postsin 21 of 489, across 9 files
adapt tone and structure per platformin 18 of 489, across 8 files
adapt content for each platformin 15 of 489, across 10 files
use the output flag to specify an output directoryin 14 of 489, across 4 files
Generate output logo images with white backgroundin 13 of 489, across 4 files
Fix failing generation scripts directlyin 13 of 489, across 4 files
ask user about html preview after logo generationin 12 of 489, across 3 files
run the download script with a URLin 12 of 489, across 3 files
implement exponential backoff for 429 responsesin 12 of 489, across 3 files
include a single clear call to actionin 12 of 489, across 9 files

Said here and by no other author read

use platform-native shapes
source numbers from claim ledger or user data
build or update CAST.md in context mode
rank platforms by audience fit and capacity
kill low-ROI surfaces
tag atoms by type

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.