agentleFS
egdev6egdev6/discord-project-manager/skills/brand-context/SKILL.md

brand-context

Skill4 starsChanged 5 months agoMITView on GitHub

Capture and summarize project brand context for a social channel without storing secrets in git.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brand-story and brand-voice.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • akachandan1Skill

    brand-story

    Receipts-based marketing storytelling engine for LinkedIn and X personal-brand, founder, and brand accounts. Use when the user wants to plan social content, write a LinkedIn post or X thread, research what's being said on social platforms before writing, react to a trend, or build a content calendar. Triggers: "brand story", "plan my content", "write a post", "LinkedIn post", "X thread", "tweet", "content calendar", "what should I post", "social listening", "research this topic", "react to this", "post about", "founder content".

    Also in 3 projects that use this

  • Dokkabei97Skill

    brand-voice

    Defines and enforces brand voice guidelines for startups. Creates tone, style, messaging frameworks and provides consistency checks across all content. Ensures every piece of communication sounds like it comes from the same brand.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to turn rough brand notes into a small, reusable context contract for one project and, when needed, one network.

    line 9
  2. Distinctive:

    Ask for missing brand facts instead of inventing them.

    line 33
  3. Distinctive:

    Keep the summary short enough to review and revise manually.

    line 35
  4. Distinctive:

    Treat ambiguous claims as open questions, not facts.

    line 36
  5. Distinctive:

    Use only fake/demo values in repository-facing examples.

    line 37
  6. Distinctive:

    Follow ADR 0002 for all namespace references.

    line 38
  7. Distinctive:

    Do not write or overwrite durable brand memory until a human explicitly approves the summary.

    line 79
  8. Distinctive:

    Do not store tokens, credentials, private customer names, or secrets in the skill output.

    line 99
  9. Distinctive:

    Do not claim memory was updated unless the runtime actually saved it.

    line 100
  10. Distinctive:

    Do not use runtime Discord namespaces for durable brand memory.

    line 101
  11. Distinctive:

    Do not overwrite shared planning artifacts without approval.

    line 102

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “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 Context

Use this skill to turn rough brand notes into a small, reusable context contract for one project and, when needed, one network.

This is an instruction contract only. It does not prove that Discord, Engram, or any publishing flow is already wired.

Inputs

Required inputs:

  • project_slug
  • network_slug or a clear statement that the result is project-wide only
  • voice_notes
  • audience_notes
  • positioning_notes
  • approved_constraints

Optional inputs:

  • current_taglines
  • approved_examples
  • known_risks
  • open_questions

Behavior

  1. Ask for missing brand facts instead of inventing them.
  2. Separate project-wide brand context from network-local adaptation.
  3. Keep the summary short enough to review and revise manually.
  4. Treat ambiguous claims as open questions, not facts.
  5. Use only fake/demo values in repository-facing examples.
  6. Follow ADR 0002 for all namespace references.

Output shape

Return a YAML-like structure similar to this:

project: <project-slug>
network: <network-slug-or-none>
brand_context:
  voice:
    - <trait>
  audience:
    - <segment>
  positioning:
    - <statement>
  do_guidance:
    - <approved behavior>
  avoid_guidance:
    - <disallowed behavior>
  approved_constraints:
    - <constraint>
open_questions:
  - <question>

Memory behavior

Read candidates

  • discord-project-manager/project/<project-slug>/brand
  • discord-project-manager/project/<project-slug>/network/<network-slug>
  • approved repo artifacts when the brand contract was promoted previously

Write candidates

  • project-wide brand memory under discord-project-manager/project/<project-slug>/brand
  • network-local adaptation under discord-project-manager/project/<project-slug>/network/<network-slug> when the distinction matters

Approval gate

Do not write or overwrite durable brand memory until a human explicitly approves the summary.

Namespace target

Use ADR 0002 exactly:

  • discord-project-manager/project/<project-slug>/brand
  • discord-project-manager/project/<project-slug>/network/<network-slug>

Canonical ADR examples that this skill may mirror when using fake/demo values:

  • discord-project-manager/project/egdev/brand
  • discord-project-manager/project/egdev/network/linkedin

Promotion to repo artifact

Promote the result into repo artifacts when the brand contract becomes reusable, review-facing, or architecture-relevant. Engram memory is operational until promoted.

Safety rules

  • Do not store tokens, credentials, private customer names, or secrets in the skill output.
  • Do not claim memory was updated unless the runtime actually saved it.
  • Do not use runtime Discord namespaces for durable brand memory.
  • Do not overwrite shared planning artifacts without approval.

Demo example (fake)

project: egdev
network: linkedin
brand_context:
  voice:
    - direct
    - technical
    - calm
  audience:
    - engineering leads
    - product-minded developers
  positioning:
    - practical AI-assisted development without hype
  do_guidance:
    - explain trade-offs before implementation
    - keep examples reviewable
  avoid_guidance:
    - fake certainty
    - growth-hack language
  approved_constraints:
    - english artifacts only
open_questions:
  - should linkedin posts optimize for hiring reach or technical depth first?

This example is fake/demo data only and must not be treated as real brand memory.

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.