agentleFS
LangChainKnown publisherlangchain-ai/design-agent/.agents/skills/design-agent-customize/SKILL.md

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
  1. Distinctive:

    Every kind of knowledge has one home.

    line 8
  2. Distinctive:

    Start with the graphic the team asks for every week.

    line 23
  3. Very specific:

    Read two skills close to it (skills/stills/, skills/thumbnails/) and skills/design-wiki/SKILL.md.

    line 25
  4. Very specific:

    Create skills/<name>/SKILL.md as a real folder one level deep (MDA does not follow symlinks there).

    line 26
  5. Distinctive:

    No brand facts, colours or libraries from a CDN in the skill: the brand pack supplies them.

    line 32
  6. Very specific:

    Add an eval task if it matters (design-agent-evals), then redeploy (design-agent-deploy).

    line 36
  7. Very specific:

    After editing, run uv run pytest -q, then compare before and after with the evals.

    line 47

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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 changeIts home
Brand facts: colours, fonts, logos, voice, graphic languageworkspace/brand/ (brand-onboarding)
A deliverable or workflow the team asks for oftena runtime skill, skills/<name>/SKILL.md
Doctrine for every visual: hierarchy, type, colour, chartsskills/design-wiki/references/
Identity, delivery and approval rules, how it talksinstructions.md (a budget test fails past about 8k tokens)
A rule a machine can counta check in workspace/tools/
A tool or data sourcean 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.

  1. Read two skills close to it (skills/stills/, skills/thumbnails/) and skills/design-wiki/SKILL.md.
  2. Create skills/<name>/SKILL.md as a real folder one level deep (MDA does not follow symlinks there). Frontmatter: name is the folder; description says 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 in references/ and keep the body small. Text only: binary files (fonts, images) go in skill-binaries/<name>/, because Context Hub takes only UTF-8 text; the stager puts them back beside the skill in the sandbox.
  3. No brand facts, colours or libraries from a CDN in the skill: the brand pack supplies them.
  4. uv run pytest -q tests/unit/test_taste_skills.py tests/unit/test_media_skills.py checks frontmatter, size, links, and that every tool, script and check it names exists.
  5. Try it with the request people actually send: uv run design-agent ask "…". Look at the files.
  6. 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.toml to config/mcp.toml and 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 with PAPER_*, 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 in AGENTS.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.

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.

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.