agentleFS
Docat0209Docat0209/SoloForge/skills/brand-build/SKILL.md

brand-build

Skill1 starsChanged 7 months agoMITView on GitHub

Develops brand positioning and Build in Public strategy. Triggers ONLY when: user asks to define brand, plan Build in Public content, or establish positioning. Do NOT trigger during development or content creation for specific pieces.

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. About 0 are common, 14 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈14

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use Geoffrey Moore's positioning template:

    line 12
  2. Distinctive:

    Must be completable in ONE sentence.

    line 17
  3. Distinctive:

    Every word must be specific.

    line 18
  4. Distinctive:

    Test: can a stranger read this and immediately understand what the product does and for whom?

    line 20
  5. Distinctive:

    Search the web for how competitors position themselves — your positioning must be clearly distinct

    line 24
  6. Distinctive:

    Check that the "category" you've chosen is one the target user already understands (don't invent categories)

    line 25
  7. Distinctive:

    Verify the "key benefit" is something users actually care about (check forums, reviews, support tickets)

    line 26
  8. Distinctive:

    Write 3 sample sentences that demonstrate the voice in action:

    line 52
  9. Distinctive:

    Before publishing any content, verify:

    line 62
  10. Distinctive:

    If your feed looks like a product changelog, you're doing it wrong

    line 77
  11. Distinctive:

    Every piece of content, every community interaction, every product decision should reinforce:

    line 140
  12. Distinctive:

    After completing brand definition, store:

    line 161
  13. Distinctive:

    Every 3 months, review and update:

    line 172
  14. Very specific:

    Update auto memory (memory/brand.md) with any changes and the reasoning behind them.

    line 178
  15. Distinctive:

    Start Build in Public → "Run content-create"

    line 186

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brand Building SOP

Section 1: Positioning Statement

Define Positioning

Use Geoffrey Moore's positioning template:

"For [target user] who [need/pain point], [product name] is a [category] that [key benefit]. Unlike [primary alternative], we [key differentiator]."

Rules:

  • Must be completable in ONE sentence. If you need two sentences, the positioning is unclear — simplify.
  • Every word must be specific. "Developers" is too broad — "solo developers shipping SaaS products" is better.
  • The differentiator must be verifiable, not just a claim. "Faster" means nothing. "Deploys in 30 seconds vs 10 minutes" is verifiable.
  • Test: can a stranger read this and immediately understand what the product does and for whom? If not, rewrite.

Validate Positioning

  1. Search the web for how competitors position themselves — your positioning must be clearly distinct
  2. Check that the "category" you've chosen is one the target user already understands (don't invent categories)
  3. Verify the "key benefit" is something users actually care about (check forums, reviews, support tickets)

Store the final positioning statement in auto memory (memory/brand.md).

Section 2: Brand Voice

Define Voice Attributes

Choose exactly 3 adjectives that describe how the brand communicates:

Example sets:

  • Developer tool: "direct, technical, honest"
  • Consumer app: "friendly, clear, encouraging"
  • B2B SaaS: "professional, precise, confident"

Define Anti-Voice

Choose exactly 3 things the voice is NOT:

Example sets:

  • "Not corporate, not salesy, not vague"
  • "Not condescending, not hype-driven, not formal"
  • "Not passive, not apologetic, not generic"

Write Reference Sentences

Write 3 sample sentences that demonstrate the voice in action:

  1. Explaining a feature: [sentence in-voice]
  2. Handling an error/problem: [sentence in-voice]
  3. Celebrating a win: [sentence in-voice]

These reference sentences are the calibration tool. When writing ANY content, compare against these samples. If it doesn't sound like it was written by the same entity, adjust.

Voice Consistency Check

Before publishing any content, verify:

  • Matches the 3 voice adjectives
  • Avoids all 3 anti-voice qualities
  • Could be swapped with the reference sentences and feel consistent

Store voice definition in auto memory (memory/brand.md).

Section 3: Build in Public Strategy

Reference: Nathan Barry (ConvertKit), Pieter Levels (Nomad List, Photo AI) — both built multi-million dollar businesses by sharing the journey publicly.

The 95/5 Rule

  • 95% of Build in Public content is pure value: learnings, data, decisions, mistakes
  • 5% is product-related: launches, features, milestones
  • If your feed looks like a product changelog, you're doing it wrong

What to Share

High value (share freely):

  • Decision tradeoffs: "We chose X over Y because [reasoning]"
  • Real metrics: revenue numbers, user counts, conversion rates, churn
  • Mistakes and post-mortems: what went wrong and what you learned
  • Behind-the-scenes process: how you build, test, deploy, prioritize
  • Tool and stack choices: what you use and why (people love this)

Medium value (share selectively):

  • Feature development progress
  • Design decisions and iterations
  • Customer feedback themes (anonymized)
  • Hiring/team building experiences

Never share:

  • Exact proprietary algorithms or implementation details that constitute competitive advantage
  • Unreleased roadmap with timelines (creates expectations you may not meet)
  • Customer PII or private conversations
  • Internal disagreements or negative team dynamics
  • Anything covered by NDA or legal agreements

Content Cadence

FrequencyTypePlatform
3-5x/weekShort updates (metrics, decisions, learnings)Primary platform (Twitter/X or LinkedIn)
1x/weekDeeper piece (essay, tutorial, retrospective)Blog + cross-post via content-distribute
1x/monthMilestone post (MRR update, user count, major feature)All platforms
As neededPost-mortem or major learningBlog + Hacker News (if substantial)

Choose Primary Platform

Pick ONE platform as your home base:

If your audience is...Primary platform
Developers / techTwitter/X
B2B / enterpriseLinkedIn
Bootstrapped foundersIndie Hackers + Twitter/X
General startupTwitter/X

Be consistent on the primary platform. Other platforms are secondary distribution.

Section 4: Tribe Identity

Reference: Seth Godin, "Tribes" — people want to belong to groups that share their values.

Define the Tribe

Complete this statement:

"We are [type of people] who believe [shared value/worldview]."

Examples:

  • "We are solo developers who believe you don't need a team to build a profitable product."
  • "We are data engineers who believe data pipelines should be boring and reliable."
  • "We are bootstrapped founders who believe sustainable growth beats VC-funded blitzscaling."

Apply the Tribe Filter

Every piece of content, every community interaction, every product decision should reinforce:

"People like us do things like this."

  • Does this content make our tribe feel seen and understood? If not, it's off-brand.
  • Does this feature serve what our tribe values? If not, question whether to build it.
  • Does this community interaction represent our tribe well? If not, don't post it.

Tribe vs. Audience

  • Audience = people who consume your content (passive)
  • Tribe = people who identify with your values and advocate for you (active)

The goal is to convert audience into tribe. This happens through:

  1. Consistent reinforcement of shared values
  2. Creating opportunities for tribe members to connect with each other
  3. Celebrating tribe members' wins (not just your own)
  4. Taking public stances that your tribe agrees with (and that outsiders might not)

Section 5: Store in Auto Memory

After completing brand definition, store:

  • Positioning statement — the complete one-sentence statement
  • Voice definition — 3 adjectives, 3 anti-adjectives, 3 reference sentences
  • Tribe identity — the "We are... who believe..." statement
  • Primary platform — where Build in Public content goes first
  • Content cadence — the agreed publishing schedule
  • Date defined — for tracking when brand was last reviewed

Quarterly Review

Every 3 months, review and update:

  1. Is the positioning still accurate? Has the product or market shifted?
  2. Is the voice consistent across all recent content? Pull 5 recent pieces and check.
  3. Is the tribe identity resonating? Check engagement rates on tribe-aligned vs generic content.
  4. Are the Build in Public metrics improving? (followers, engagement, referral traffic from social)

Update auto memory (memory/brand.md) with any changes and the reasoning behind them.

Next Steps

Report to user: "Brand positioning defined: [one-sentence positioning]. Voice: [3 adjectives]"

Suggested next steps (user decides):

  • Brand defined, new project → "Run project-init"
  • Need landing page → "Run copy-craft"
  • Start Build in Public → "Run content-create"

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.