Design agent skills
Skill hiteshbandhu/skills-i-use/skills/ai-engineer-talks/design-agent-skills
Runs workflows for authoring agent skills — SKILL.md structure, MCP pairing, Langfuse lessons, progressive disclosure, validation. Use when the user writes skills, combines MCP+skills, or says "agent skills", "SKILL.md", "context gap".From its SKILL.md
npx -y skills add hiteshbandhu/skills-i-use --skill design-agent-skillsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 3 commands, including `cp -r skills/design-agent-skills ~/.claude/skills/` and 2 more.
SKILL.md
2.0 KB, 443 tokens by cl100k_base, as published. Nobody here has run it
Design agent skills
Action playbook from three AI Engineer / World's Fair talks. Do not summarize talks — pick a workflow and execute it.
Supporting files (read when needed):
- workflows.md — workflows A–C (steps, deliverables, stop conditions)
- source-index.md — src-NNN → talk learnings in ingest-into-skills
Optional: {SKILL_OUTPUT_DIR}/design-agent-skills/
Step 0 — Pick workflow
Use the decision tree below. Open the matching section in workflows.md.
What is the user trying to do?
├─ Author first skill (structure + triggers) → A
├─ Pair skills with MCP for live data → B
└─ Skill-up coding agents on complex devtools → C
Stop summarizing once a workflow is identified — run its checklist.
Install
cp -r skills/design-agent-skills ~/.claude/skills/
cp -r skills/design-agent-skills ~/.cursor/skills/
cp -r skills/design-agent-skills ~/.codex/skills/
From skills-i-use or ingest-into-skills (playlists/skills-ai-engineer/).
Cross-cutting rules
| Rule | Source |
|---|---|
| SKILL.md slim; workflows in sibling files | [src-002 @ 7:06] |
| Third-person description + triggers | [src-002 @ 35:14] |
| Procedures in skills; state via MCP | [src-001 @ 3:17] |
Disputed steps: see source-index.md. Name workflow A–C; save artifacts to ./skill-outputs/design-agent-skills/ when requested; do not auto-commit.
Invocation examples
@design-agent-skills write a skill for our API
combine MCP with skills for Supabase
What ships with it: 3 files
2.4 KB alongside SKILL.md
- README.md845 B
- source-index.md917 B
- workflows.md705 B
Gives 0 of the 12 instructions most context ai engineering skills give in 443 tokens
Counted across 1,328 of the 2,349 authors here whose files we hold, read 2026-09-06
- Dispatch a fresh subagent for each taskin 76 of 1328, across 59 files
- Perform spec compliance review before code quality reviewin 44 of 1328, across 34 files
- Dispatch a final code reviewer after all tasksin 38 of 1328, across 26 files
- Answer subagent questions before allowing implementationin 36 of 1328, across 26 files
- Use the least powerful model capable of the taskin 33 of 1328, across 26 files
- Create a TodoWrite list for all tasksin 32 of 1328, across 22 files
- Perform a task review after each implementationin 31 of 1328, across 24 files
- Extract all tasks and context from the planin 29 of 1328, across 20 files
- Provide full task text to subagentsin 28 of 1328, across 20 files
- Use git worktrees for isolated workspacesin 25 of 1328, across 20 files
- Specify the model explicitly when dispatching a subagentin 23 of 1328, across 18 files
- Execute all tasks from the plan without stoppingin 21 of 1328, across 16 files
Said here and by no other author read
- Pick a workflow from the decision tree
- execute the workflow checklist
- save artifacts to the output directory
- Keep SKILL.md files slim
- Place workflows in sibling files
- Use third-person descriptions and triggers
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.