Skip to content
Back to search

brand-skill-builder

SkillWorks with Claude CodeGitHub

Turn a brand book into AI skills that make on-brand files and audit them, on Claude and ChatGPT.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/yuckier--brand-skill-builder/badge.svg)](/listings/yuckier--brand-skill-builder)

HTML

<a href="/listings/yuckier--brand-skill-builder"><img src="/api/listings/yuckier--brand-skill-builder/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**Claude:** zip the `skills/brand-skill-builder` folder and upload it as a skill, or copy the folder into your skills directory (for Claude Code, `~/.claude/skills/`).

**ChatGPT and other agents:** the skill ships `agents/openai.yaml`; load the folder as a skill wherever your platform supports the Agent Skills format.

The skill works best where the model has a persistent file system (Claude Code, Codex, a local agent), because it writes a whole library of files.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 69 lines
  1. # Brand Skill Builder
  2. A skill that teaches an AI model to build **brand skills**: a small library of skills that produce on-brand work for one
  3. company, from that company's brand book.
  4. It comes from a production library of brand skills (voice, PDF, Word, PowerPoint, social images, HTML, motion and a brand
  5. audit) that runs on both Claude and ChatGPT. This repository holds the method, the templates and the tools from that
  6. library, with no brand's rules in it.
  7. ## What you get
  8. - **A workflow** (`SKILL.md`) for three jobs: start a new library from a brand book, add a skill to a library, or review an
  9. existing brand skill against the pattern.
  10. - **References** covering the architecture, how to turn a brand book into structured foundations, the anatomy of a format
  11. skill, the voice and audit skills, QA and testing, packaging, and lessons from the build.
  12. - **Templates** for the library (`AGENTS.md`, `DEV-LOG.md`), the brand foundations (palette, typography, structural system,
  13. accessibility, voice), each skill type (format, voice, audit) and a format's spec and map.
  14. - **Scripts** (Python 3.9 or newer, standard library only):
  15. - `scaffold.py`: creates a library or a new skill from the templates
  16. - `verify_context.py`: the preflight every skill runs (digests, brand era, review date, platform folders)
  17. - `snapshot.py`: refreshes a skill's bundled context and manifest from the shared source
  18. - `package_skill.py`: packages a skill into an upload zip and checks it (strict frontmatter, description length,
  19. digests, no nested zips, clean extraction)
  20. ## The approach in six lines
  21. 1. **The brand book becomes data.** Palette, typography, structural system, accessibility and voice, with provenance, and
  22. every gap recorded instead of guessed.
  23. 2. **One skill, one job.** Voice, each output format and the audit are separate skills that never call each other at runtime.
  24. 3. **Snapshot-first.** Each skill bundles the brand context it needs, with SHA-256 digests, so it runs offline and can prove
  25. which version of the brand it used.
  26. 4. **The model plans, a script builds, a script checks.** The model writes a JSON spec; a builder reads brand tokens at build
  27. time; a QA gate checks the finished file against the brand's ship check.
  28. 5. **Warn, never refuse.** Skills repair and report, deliver failing files labelled, and stop only when something is
  29. physically impossible.
  30. 6. **House decisions are written down.** Every choice the brand book did not make is recorded with its scope, its status
  31. and who decided.
  32. ## Install
  33. **Claude:** zip the `skills/brand-skill-builder` folder and upload it as a skill, or copy the folder into your skills
  34. directory (for Claude Code, `~/.claude/skills/`).
  35. **ChatGPT and other agents:** the skill ships `agents/openai.yaml`; load the folder as a skill wherever your platform
  36. supports the Agent Skills format.
  37. The skill works best where the model has a persistent file system (Claude Code, Codex, a local agent), because it writes a
  38. whole library of files.
  39. ## Quick start
  40. ```bash
  41. python3 skills/brand-skill-builder/scripts/scaffold.py library ./acme-skills --brand "Acme" --era 2027-brand
  42. python3 skills/brand-skill-builder/scripts/scaffold.py skill ./acme-skills acme-pdf --kind format --format PDF
  43. python3 acme-skills/tools/snapshot/snapshot.py acme-skills/tools/snapshot/acme-pdf.json
  44. python3 acme-skills/skills/acme-pdf/scripts/verify_context.py
  45. python3 acme-skills/skills/acme-pdf/tests/test_platforms.py
  46. ```
  47. Then ask your model: "Use brand-skill-builder to fill the Acme foundations from the brand book in `acme-skills/reference/`."
  48. ## What it does not include
  49. No brand's colours, fonts, voice or rules, and no format builders: a builder is specific to a brand's visual system, so each
  50. library writes its own, following `references/format-skills.md`.
  51. ## Licence
  52. MIT. See [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.