pipeline-brand
Skill0 starsChanged 2 months agoMITView on GitHub
Full brand-to-implementation pipeline — strategy and voice, aesthetic grounding, unified creative brief, UI + motion implementation, and an aesthetic gate before brandbook assembly. Use when a project needs its brand built or substantially reworked, not for single-deliverable requests.
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- global/CLAUDE.mdCLAUDE.md
- copywriting-frameworksSkill
- design-mdSkill
- format-carouselSkill
- format-hooksSkill
- format-linkedinSkill
- format-reelsSkill
- funnel-designSkill
- humanizationSkill
- launch-playbooksSkill
- offer-designSkill
- pipeline-campaignSkill
- pipeline-contentSkill
- pipeline-copySkill
- pipeline-landing-pageSkill
- pipeline-luxoSkill
- pipeline-refino-uiSkill
- pipeline-sistemaSkill
- scroll-worldSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Only copy or campaign strategy is needed — that is mkt-strategist's pipeline, not this one.
- Very specific: line 35
Every step writes to its own file — the chain is auditable by reading brain/ops/handoffs/ and the project pack in order, not by re-running …
- Very specific: line 36
If dsg-scout finds no adequate references, it says so rather than padding the mood report — the chain pauses, it does not degrade.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Pipeline: Brand
Chains the design squad end to end: from "who is this brand" to a shipped, gated implementation and an assembled brandbook. Invoked as /pipeline-brand, or delegated by the director when an objective spans brand strategy through implementation.
When to use
- A new project pack has no
brand.mdyet, or an existing brand needs a substantial rework (repositioning, new sub-brand, new product line). - The user asks for "the brand" or "the identity" end-to-end, not a single page or asset.
When NOT to use
- A single page/component needs design work on an ALREADY-DEFINED brand — start at
dsg-directordirectly (skip to the brief step), or atdsg-ui/dsg-motionif specs already exist. - Only copy or campaign strategy is needed — that is
mkt-strategist's pipeline, not this one. - The project is premium/luxury-tier — run this pipeline WITH the
pipeline-luxooverlay active (see that skill) rather than as a plain run.
The Chain
dsg-brand— determine mode(s) (company / personal / product / movement), produce positioning, archetype, narrative, naming, and voice DNA. Writesbrain/projects/<name>/brand.md+voice.mdinto the pack.dsg-scout— curate a mood report grounded in the brand just defined (aesthetic intent derived frombrand.md, not guessed). Writesbrain/design-library/mood-reports/<project>.md.dsg-director— readsbrand.md+ the mood report + principles, produces ONE unified creative brief. Writesbrain/ops/handoffs/brief-design-<slug>.md.dsg-ui→dsg-motion—dsg-uitranslates the brief into tokens/layout/component specs (spec-ui-<slug>.md);dsg-motionimplements motion directly in the codebase against that spec, native-first. These run back-to-back, not independently — motion needs the spec's state list.dsg-criticgate — screenshots the implementation, scores against principles + the mood report, renders APPROVE / REVISE / REJECT.- REVISE → back to step 4 with named asks. Max 2 revision loops.
- REJECT → back to step 3,
dsg-directorrebriefs. - On a 3rd failed loop, escalate to the user with the blocker stated plainly — do not keep looping.
- Brandbook assembly — once APPROVED, assemble
brain/projects/<name>/brandbook.md: essence/positioning + voice card (frombrand.md/voice.md), the approved creative brief, the visual identity (color system, type pairing, SVG marks), and the gate verdict as proof of quality. Assembled from artifacts each step already produced — no new content invented at this step.
Notes
- Every step writes to its own file — the chain is auditable by reading
brain/ops/handoffs/and the project pack in order, not by re-running agents. - If
dsg-scoutfinds no adequate references, it says so rather than padding the mood report — the chain pauses, it does not degrade. - Skipping a step (e.g., going straight from
dsg-brandtodsg-ui) is a deviation from this pipeline; report it rather than silently improvising the missing brief.
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
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.

