social-context
Skill8 starsChanged 4 months agoMITView on GitHub
Interview the user in ten questions or fewer and produce a social-context.md file that captures who they are, who they are talking to, what they post about, and what they refuse to post. Covers LinkedIn, X (Twitter), Instagram, Threads, TikTok, and YouTube — the interview decides which of those platforms actually matter. Use when the user says "set up my social context", "onboard me", "set up my socials", or "create my social profile". Every other skill in this collection reads social-context.md for brand voice and setup, so this is the skill to run first. Re-running it updates the existing file section by section and never overwrites the user's manual edits without asking.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- EvolutionAPI/evo-nexustheir own version, first seen Oct 8, 2026
- evolution-foundation/evo-nexustheir own version, first seen Apr 20, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- EvolutionAPI/evo-nexus★ 545same name
- evolution-foundation/evo-nexus★ 535same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- idkSkill
- social-adSkill
- social-auditSkill
- social-calendarSkill
- social-carouselSkill
- social-checkSkill
- social-crosspostSkill
- social-hookSkill
- social-postSkill
- social-replySkill
- social-repurposeSkill
- social-threadSkill
- social-voiceSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 10 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 28
Check for an existing social-context.md at the project root, then .agents/social-context.md.
- Distinctive: line 29
If one exists, this run is an update: read it fully before asking anything, skip questions it already answers well, and confirm only what …
- Distinctive: line 41
Audience: Ask who they most need to reach, offering choices:
- Distinctive: line 47
Follow with one sharpening question: "Describe one real person in that audience — job title, what they scroll past, what stops them." …
- Distinctive: line 49
Platforms: Ask which platforms they're active on — LinkedIn, X, Instagram, Threads, TikTok, YouTube etc.
- Distinctive: line 53
Pillars: Ask for 3–5 recurring themes they can post about for a year without running dry.
- Distinctive: line 64
Cadence reality check: Ask how many posts per week they will _actually_ ship, not aspire to.
- Distinctive: line 67
Goals: Ask what a win looks like in 90 days, offering: reach/awareness, inbound leads, hiring pipeline, community, or personal brand.
- Distinctive: line 70
Red lines: Ask what they will never post: competitors they won't name, topics that are off-limits (politics, salaries, client names), …
- Very specific: line 76
Fresh run: write the whole file. Update run: regenerate section by section, diff each against the existing file, and where the existing …
- Distinctive: line 81
Before showing the file, check every section against the Quality bar.
- Distinctive: line 102
Every entry must be specific enough that a stranger could draft a post from the file alone.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Interview the user, then write a social-context.md at the project root that every other
social skill can read.
Context
Check for an existing social-context.md at the project root, then .agents/social-context.md.
If one exists, this run is an update: read it fully before asking anything, skip questions
it already answers well, and confirm only what looks stale. If neither exists, this is a fresh
interview — say so and start immediately.
Workflow
- Set expectations in one line: "Up to 10 quick questions, multiple choice where I can — say 'skip' to any." Then ask the first question in the same message. Do not wait for permission to begin.
- Who are you and what do you sell? One open question, captured as the
## Positioningsection. If the answer is vague ("a startup"), push once for the one-sentence version a stranger would understand: product, category, and who pays. - Audience. Ask who they most need to reach, offering choices:
- (a) buyers/customers
- (b) peers in their field
- (c) potential hires
- (d) investors
- (e) a niche community Follow with one sharpening question: "Describe one real person in that audience — job title, what they scroll past, what stops them." Capture that person, not a demographic.
- Platforms. Ask which platforms they're active on — LinkedIn, X, Instagram, Threads, TikTok, YouTube etc. — and, for each chosen one, why (where the audience is vs. where they're comfortable). If they pick more than three, warn once that two done consistently beats five done sporadically, and ask them to rank. Record a primary and a secondary.
- Pillars. Ask for 3–5 recurring themes they can post about for a year without running dry. If they stall, propose pillars derived from their answers so far — build-in-public progress, opinions on their industry, teaching their craft, customer stories, behind-the-scenes — and let them pick and edit. Each pillar gets a name and a one-line description.
- Tone sliders. Present three sliders as multiple choice (1–5), all in one message:
- funny ↔ serious
- spicy ↔ safe
- personal ↔ brand Then ask for one account they admire and one they'd hate to sound like — those two anchors are worth more than the sliders.
- Cadence reality check. Ask how many posts per week they will actually ship, not aspire to. If they say daily, ask what they shipped last month. Record the honest number per platform.
- Goals. Ask what a win looks like in 90 days, offering: reach/awareness, inbound leads, hiring pipeline, community, or personal brand. Force a single primary goal; secondary goals are allowed but labeled.
- Red lines. Ask what they will never post: competitors they won't name, topics that are off-limits (politics, salaries, client names), formats they hate (dance trends, engagement bait), words they'd never use. Get at least three concrete items.
- Write the file. Assemble
social-context.mdusing the sections in the Quality bar table below, in that order, with those exact headings — other skills locate sections by these headings, so never rename or reorder them. - Fresh run: write the whole file. Update run: regenerate section by section, diff
each against the existing file, and where the existing text contains detail you didn't
collect this session (manual edits, rules added by the
social-voiceskill), show the old and new versions side by side and ask which to keep. Never silently drop a line the user wrote by hand. - Before showing the file, check every section against the Quality bar; fix any that fail its "Must contain" bar, and turn any section you can only fill with an invented answer into a placeholder instead. Then show the file and ask for one correction pass on the highest-stakes sections: "Read the Never and Voice sections — anything wrong?" Apply fixes and finish.
Quality bar
| Section | Must contain |
| Positioning | One-sentence statement: product, category, and who pays — a stranger could draft from it |
| Audience | One named persona sketch (role, pain, what stops their scroll) — not just a demographic |
| Platforms | Primary and secondary marked, with a one-line "why" for each |
| Pillars | 3–5 named pillars, each with a one-line description |
| Voice | The three slider values plus the admire/avoid anchor accounts |
| Cadence | A realistic posts-per-week number per platform |
| Goals | Exactly one primary goal; secondaries labeled as secondary |
| Never | At least 3 concrete, checkable red lines |
Additional rules:
- Every entry must be specific enough that a stranger could draft a post from the file alone. "Professional but approachable" fails; "explains like a senior engineer at lunch, no corporate verbs, swearing allowed but rare" passes.
- Skipped questions produce a
_Not captured yet — rerun this interview to fill in._placeholder under the relevant heading, never an invented answer. - The file is plain markdown: no YAML frontmatter, no HTML, headings exactly as listed.
Deliverable
social-context.md written to the project root (or updated in place, edits preserved),
followed by a short summary in chat: the one-line positioning, primary platform, primary
goal, the pillar list, and any sections left as placeholders with a note that re-running
this skill fills them in.
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
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.

