Communitygithub.com

brand-skill-builder

Builds a library of brand skills for any company from its brand book: a voice skill, format skills that make on-brand files (PDF, Word, PowerPoint, social images, HTML, motion) and an audit skill that checks assets against the brand. Turns the brand book into structured foundations (palette, typography, structural system, accessibility, voice), scaffolds each skill with a digest-verified context snapshot, a preflight, platform tests and a packager, and walks the build from intake to QA to release so one zip runs on Claude and ChatGPT. Use when someone asks to 'make brand skills for our brand', 'turn our brand guidelines into skills', 'build an on-brand deck or PDF skill', 'add a format skill to our brand library', or 'review our brand skill against best practice'. Not a brand skill itself: it makes no branded files and holds no brand's rules; it never invents brand values the sources do not give.

Was ist brand-skill-builder?

brand-skill-builder is a Claude Code agent skill that builds a library of brand skills for any company from its brand book: a voice skill, format skills that make on-brand files (PDF, Word, PowerPoint, social images, HTML, motion) and an audit skill that checks assets against the brand. Turns the brand book into structured foundations (palette, typography, structural system, accessibility, voice), scaffolds each skill with a digest-verified context snapshot, a preflight, platform tests and a packager, and walks the build from intake to QA to release so one zip runs on Claude and ChatGPT. Use when someone asks to 'make brand skills for our brand', 'turn our brand guidelines into skills', 'build an on-brand deck or PDF skill', 'add a format skill to our brand library', or 'review our brand skill against best practice'. Not a brand skill itself: it makes no branded files and holds no brand's rules; it never invents brand values the sources do not give.

Funktioniert mit✓Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/yuckier/brand-skill-builder/tree/HEAD/skills/brand-skill-builder

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

Brand Skill Builder

This skill helps you build and maintain a brand skill library: a set of small skills that let any model produce on-brand work for one company. It carries the architecture, templates, scripts and lessons from a production library; it carries no brand of its own. Every brand value comes from the user's sources.

Read references/architecture.md before starting any mode. Read the other references when the step below names them.

Folders. In every command, SKILL_DIR is the folder holding this file and LIB is the library folder the user chooses. Write both out in full in every command; do not set them as shell variables (on some platforms a variable set in one command is gone in the next).

Choose the mode

The user wantsMode
Brand skills for a brand that has none yetA. New library
One more skill in an existing libraryB. Add a skill
A review of an existing brand skill or libraryC. Review
To understand the approach before buildingExplain from references/architecture.md and stop

Ask which mode only if the request does not say.

A. New library

  1. Gather sources. Ask for the brand book and anything that rules on the brand: the design team's templates, a voice guide, a messaging document, trademark rules, a style guide, the logo files, the fonts and their licences, any icon or photo library. Ask who owns the brand (the people who will ratify decisions). Note what is missing; do not fill it in.
  2. Scaffold. python3 SKILL_DIR/scripts/scaffold.py library LIB --brand "<Brand>" --era <era>. The era is a short label for this version of the brand (for example 2027-brand). Put the sources in LIB/reference/.
  3. Write the foundations in LIB/shared-context/brand-foundations/context/ from the sources, following references/brand-foundations.md. Fill every TODO from a source or record it as a gap. Measure contrast; quote the book's wording where it carries a rule; give every file its provenance. Add logo artwork under logo/, and logo-policy.md, imagery-policy.md and chart-palette.json when the sources cover them.
  4. Review with the owner. Show the foundations as a short summary: the colour model, the type roles, the signature elements, the ship check, the gaps, and each proposed house decision with one recommendation and its reason. Wait for their decisions; record each in the House decisions table and the dev log.
  5. Build the voice skill (mode B with --kind voice). It is small and proves the snapshot, preflight and packaging path.
  6. Build the first format skill (mode B with --kind format), the format people need most. Smallest end-to-end path first, then pilot loops.
  7. Add formats one at a time, settling each format's house decisions first (references/process.md, "Order of work").
  8. Build the audit skill (mode B with --kind audit) once there are format specs to audit against.

B. Add a skill

  1. Name it <brand>-<format> (lowercase, hyphens), or <brand>-voice, <brand>-audit. Confirm one skill, one job: if the request overlaps an existing skill, say so and recommend extending that skill instead.
  2. Scaffold. python3 SKILL_DIR/scripts/scaffold.py skill LIB <name> --kind format|voice|audit --format "<PDF>". This writes the SKILL.md template, agents/openai.yaml, the preflight, the platform test, and the snapshot config LIB/tools/snapshot/<name>.json; for a format skill also LIB/shared-context/<name>/context/format-spec.md and format-map.json.
  3. Settle the format's house decisions before writing code: for every decision in structural-system.md scoped "others decide when built", recommend an answer for this format, get the owner's decision, record it.
  4. Write the format spec and map (words with BOOK, RATIFIED and PROPOSED tags; numbers with role names, never hex).
  5. Write the builder and QA scripts following references/format-skills.md: the model plans and writes a JSON spec, a script builds, a script gates the finished file; tokens read at build time; deviations recorded, never refusals. Voice and audit skills follow references/voice-and-audit.md instead.
  6. Fill SKILL.md: the description (triggers, what it will not do, under 1,024 characters), the steps, the intake with its look-to-spec table, the spec reference, the warn-never-refuse section, and one delivery line per platform.
  7. Snapshot and verify. python3 LIB/tools/snapshot/snapshot.py LIB/tools/snapshot/<name>.json, then --check, then python3 LIB/skills/<name>/scripts/verify_context.py. Add fonts, stylesheets and artwork to bundled_assets in the config so the preflight proves them.
  8. Test (references/qa-and-testing.md): the platform test, fixture builds on both themes, a tamper test per QA check, the token-swap test. Then pilot loops with a realistic prompt, rerunning the same prompt after each fix.
  9. Package when asked (references/packaging.md): python3 LIB/tools/package/package_skill.py LIB/skills/<name> <name> <fresh scratch folder>/<name>.zip --date YYYY-MM-DD. Unpack into another fresh folder and run the tests from there before placing the zip in LIB/finalized-skills/.
  10. Log it. Every step above goes in LIB/DEV-LOG.md as it happens.

C. Review

Read the skill (or library) and compare it with the pattern. Report, in this order, each with the file and line:

  1. Structure: one job, no runtime calls to other skills, agents/openai.yaml, no single-platform paths.
  2. Context: a bundled snapshot with a manifest and digests, a preflight that warns rather than stops, a brand era.
  3. Builder: tokens read at build time (or hard-coded values), a JSON spec, deviations instead of refusals.
  4. QA: a gate on the finished file mapped to the ship check, tamper tests, a restyle mode if it restyles.
  5. Workflow: intake with defaults, plan with claim and evidence, approval before build, delivery that leads with warnings.
  6. Packaging: strict frontmatter, description length and triggers, a release record.

Recommend the fixes in order of impact. Change nothing unless asked.

Rules for every mode

  • Never invent brand values. No colour, font, size, rule, claim, figure or customer comes from general knowledge. A gap is recorded and decided by the owner, or the element is left out.
  • The brand book is the rule of record; the owners' design files fill its silences; every departure is a house decision with its scope, the book's words it departs from, its status and who decided.
  • Warn, never refuse, inside the skills you build: repair and report, deliver failing files labelled, stop only for a physical impossibility. The voice skill with no voice file is that impossibility.
  • Recommend, then ask on every choice that belongs to the owner. Build only after they decide.
  • Measure, do not guess: contrast, text widths, line counts, renders.
  • Look at the output in the real renderer before calling anything done.

Delivery

  • on Claude: summarise what was created or changed with paths, and share any packaged zip from the output folder.
  • on ChatGPT: summarise what was created or changed with paths, and link any packaged zip as a download.

Then list what is still TODO, each gap waiting on the owner, and each PROPOSED decision.

Reference

FileRead it for
references/architecture.mdSkill types, the workspace, the skill folder, snapshot-first context, platform neutrality
references/brand-foundations.mdTurning a brand book into data: files, colour and type architecture, house decisions, status tags
references/format-skills.mdThe workflow inside a format skill, warn-never-refuse, the spec, the builder, the QA gate, per-format notes
references/voice-and-audit.mdThe voice skill and the audit skill
references/qa-and-testing.mdTests, renders, pilots, debugging rules that interact
references/packaging.mdStrict frontmatter, the description, release steps, upload failures
references/process.mdDecisions, the living record, order of work, working safely, Office toolchain lessons

Verwandte Skills