AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Onboarding Brand Brief

skill-moses607-socialforge-onboarding-brand-brief · by moses607

First-run setup that captures a creator's foundation — niche, positioning, offer, platforms, and voice — into a reusable BRAND BRIEF block the other SocialForge skills read from. Includes a voice-training step that extracts tone, lexicon, and rhythm from the creator's own posts (or admired creators) so generated content sounds like a person, not a model. Use when the user first opens SocialForge,…

No reviews yet
0 installs
13 views
0.0% view→install

Install

$ agentstack add skill-moses607-socialforge-onboarding-brand-brief

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-moses607-socialforge-onboarding-brand-brief)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Onboarding Brand Brief? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Onboarding Brand Brief

Everything downstream — hooks, personas, calendars, captions — degrades to generic mush without a foundation the model can anchor on. A brand brief is not branding fluff; it is a compression of five decisions (who you serve, why you, what you sell, where, and how you sound) into a block short enough to prepend to every generation. Extract it once, reuse it forever. The single highest-leverage step is voice training: a model that has read five of the creator's real posts stops writing "in today's fast-paced world" and starts writing like them.

Method: interrogate the five pillars

Ask these in order. One question at a time. Push back on vague answers — "fitness" is not a niche, "busy moms who want to lift heavy without a gym" is.

  1. Niche + sub-niche. Force specificity. Broad niche = the room; sub-niche = the corner they own. Reject anything you could put on a billboard for a competitor.
  2. Positioning / unique angle. Finish this sentence with them: "Unlike everyone else in [niche], I ___." If they can't, probe their contrarian take, origin story, or unfair advantage.
  3. Offer + primary goal. What is the money or growth event? Followers, email leads, product sales, bookings? Name ONE primary goal and the metric that proves it. Secondary goals get logged but never drive the strategy.
  4. Platforms. Where do they post now and where do they want to. Rank them. Downstream skills adapt format per platform.
  5. Voice attributes. Pull 3 adjectives, but make them earn it — "professional" is banned. Push for tension pairs like "blunt but warm" or "nerdy but irreverent".

Method: voice training from real posts

  1. Ask for 3-5 of their best-performing or favorite posts — their own, or admired creators they want to sound like (flag which).
  2. Extract three layers explicitly: tone (emotional default — deadpan, hyped, tender), lexicon (recurring words, slang, jargon, signature phrases, emoji habits), rhythm (sentence length, one-liners vs paragraphs, use of line breaks, punctuation quirks).
  3. Derive a do-words / don't-words list: words that sound like them, and words that would break the illusion (corporate filler, hashtag-speak, AI tells like "delve", "elevate", "unlock").
  4. Write one 2-sentence sample in their voice and ask "does this sound like you?" Iterate until yes. Do not finalize the brief on an unconfirmed voice.

Output template

=== BRAND BRIEF ===
Niche:  > 
ICP one-liner: 
Positioning: Unlike others in , I .
Voice attributes: , , 
Do-words: 
Don't-words: 
Rhythm: 
Platforms (ranked): , , 
Primary goal:  | Metric: 
Secondary goals: 
=== END BRIEF ===

Platform variants

  • Short-form video (TikTok/Reels/Shorts): voice attributes should include a spoken-cadence note — how they'd say it out loud, not write it.
  • LinkedIn/X: capture a "credibility marker" (role, result, receipts) since positioning leans on authority.
  • Instagram/Pinterest: log an aesthetic note (visual mood) alongside voice; the brief feeds caption tone, not just copy.

Rules

  • One question at a time. A wall of 10 questions gets skimmed and answered lazily — the brief is only as good as the answers.
  • Reject vague niches and banned adjectives ("professional", "authentic", "high-quality") on sight — make them replace the word with a specific one.
  • Never finalize until the voice sample passes the "sounds like me" test; an unconfirmed voice poisons every downstream generation.
  • The brief is a living artifact — end by telling the user to re-run this when their offer or platform mix changes.
  • Force exactly one primary goal. Two primary goals means no strategy, just wishes.
  • Prefer the creator's real posts over admired-creator samples; imitation is a fallback, not the default.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.