design-agent-customize
Skill2 starsChanged 14 days agoApache-2.0View on GitHub
Change what Design Agent knows and does. Teach it a new deliverable with a runtime skill, change its instructions, design doctrine or checks, connect MCP servers and tools, or change models and cost caps. Use when someone wants it to make something new, follow a new rule, or use another tool.
- Reads credentials
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Every kind of knowledge has one home.
- Distinctive: line 23
Start with the graphic the team asks for every week.
- Very specific: line 25
Read two skills close to it (skills/stills/, skills/thumbnails/) and skills/design-wiki/SKILL.md.
- Very specific: line 26
Create skills/<name>/SKILL.md as a real folder one level deep (MDA does not follow symlinks there).
- Distinctive: line 32
No brand facts, colours or libraries from a CDN in the skill: the brand pack supplies them.
- Very specific: line 36
Add an eval task if it matters (design-agent-evals), then redeploy (design-agent-deploy).
- Very specific: line 47
After editing, run uv run pytest -q, then compare before and after with the evals.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Customize Design Agent
Every kind of knowledge has one home. Find the owner before editing, so a fix lands once and every asset after it follows:
| The change | Its home |
| Brand facts: colours, fonts, logos, voice, graphic language | workspace/brand/ (brand-onboarding) |
| A deliverable or workflow the team asks for often | a runtime skill, skills/<name>/SKILL.md |
| Doctrine for every visual: hierarchy, type, colour, charts | skills/design-wiki/references/ |
| Identity, delivery and approval rules, how it talks | instructions.md (a budget test fails past about 8k tokens) |
| A rule a machine can count | a check in workspace/tools/ |
| A tool or data source | an MCP server in config/mcp.toml |
| Which model plays which role, effort, budgets | .env settings; Models |
Add a runtime skill
Start with the graphic the team asks for every week.
- Read two skills close to it (
skills/stills/,skills/thumbnails/) andskills/design-wiki/SKILL.md. - Create
skills/<name>/SKILL.mdas a real folder one level deep (MDA does not follow symlinks there). Frontmatter:nameis the folder;descriptionsays when to use it, in the words people use when they ask. Body: what good looks like, sizes, steps, the checks to run. Put depth inreferences/and keep the body small. Text only: binary files (fonts, images) go inskill-binaries/<name>/, because Context Hub takes only UTF-8 text; the stager puts them back beside the skill in the sandbox. - No brand facts, colours or libraries from a CDN in the skill: the brand pack supplies them.
uv run pytest -q tests/unit/test_taste_skills.py tests/unit/test_media_skills.pychecks frontmatter, size, links, and that every tool, script and check it names exists.- Try it with the request people actually send:
uv run design-agent ask "…". Look at the files. - Add an eval task if it matters (design-agent-evals), then redeploy (design-agent-deploy).
Vendored skills (HyperFrames and LangSmith, listed in skills-lock.json) are never edited: override them in a
sibling skill of ours, or send the change upstream.
Instructions, doctrine and checks
- Phrase rules as defaults with a reason, or as checks with evidence. A rule about the model is temporary; retest it when the model changes and delete what the new model outgrows.
- A rule a machine can count belongs in code, as a check, not in prose.
- After editing, run
uv run pytest -q, then compare before and after with the evals.
Tools
- MCP servers: copy
config/mcp.example.tomltoconfig/mcp.tomland declare servers. Locally, header values come from the environment (headers_env); on MDA a server that needs credentials names a workspace connection (connection), owned by the deployment or each person (owner). The example file has presets for Notion, Linear, GitHub, Figma and others (integrations). MDA serves HTTP and SSE only. Paper is configured withPAPER_*, not here (Paper). - Media keys:
OPENAI_API_KEY(images),ELEVENLABS_API_KEY(voice, music, sound effects),GROQ_API_KEY(transcription). - A new host tool is code in
src/design_agent/tools/: keys stay on the host and results drop into the sandbox as files. Follow the change discipline inAGENTS.md.
Models and cost
uv run design-agent config set DESIGN_AGENT_MODEL=provider:model, then
uv run design-agent test model. DESIGN_AGENT_JOB_BUDGET_USD makes the agent ask before passing
a budget; DESIGN_AGENT_HELPER_EFFORT_CAP caps helpers' effort. More: Customization.
In this repository53 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- brand-onboardingSkill
- deep-agents-coreSkill
- deep-agents-memorySkill
- deep-agents-orchestrationSkill
- design-agent-deploySkill
- design-agent-evalsSkill
- design-agent-onboardingSkill
- design-agent-troubleshootSkill
- design-agent-updateSkill
- langsmith-datasetSkill
- langsmith-evaluatorSkill
- managed-deep-agentsSkill
- release-checkSkill
- vendor-syncSkill
- brand-designSkill
- content-briefSkill
- data-vizSkill
- design-wikiSkill
- embedded-captionsSkill
- faceless-explainerSkill
- film-breakdownSkill
- general-videoSkill
- gif-editSkill
- hyperframes-animationSkill
- hyperframes-audioSkill
- hyperframes-cliSkill
- hyperframes-coreSkill
- hyperframes-creativeSkill
- hyperframes-keyframesSkill
- hyperframes-registrySkill
- hyperframesSkill
- image-generationSkill
- image-opsSkill
- langsmith-traceSkill
- launch-filmSkill
- media-productionSkill
- media-useSkill
- motion-directionSkill
- motion-graphicsSkill
- music-to-videoSkill
- paper-designSkill
- pr-to-videoSkill
- reference-studySkill
- remotion-to-hyperframesSkill
- slideshowSkill
- soundSkill
- stillsSkill
- storyboardSkill
- thumbnailsSkill
- visual-verifySkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

