Skip to content

HK-hub/AgentSkills / agent-native-design

agent-native-design

Verified

Use when designing, reviewing, or refactoring a CLI that must serve AI agents alongside humans, or when converting an API or SDK into an agent-usable CLI interface.

FileKindSize
SKILL.mdskill md12.6 KB
agents/openai.yamlconfig1.1 KB
references/checklists.mdmarkdown3.6 KB
references/citations.mdmarkdown3.7 KB
references/design-patterns.mdmarkdown12.4 KB
references/examples.mdmarkdown8.1 KB
references/hybrid-mcp-cli.mdmarkdown3.9 KB
references/rubric.mdmarkdown3.5 KB
references/testing.mdmarkdown11.9 KB
scripts/validate-metadata.shscript2.7 KB

agents/openai.yaml

View on GitHub
interface:
  display_name: "Agent Native Design"
  short_description: "Design, review, and refactor CLIs to serve humans, AI agents, and orchestration systems simultaneously — structured output, schema introspection, dry-run, safety tiers, and delegated authentication"
  brand_color: "#1A3A5C"

policy:
  allow_implicit_invocation: true

capabilities:
  - Evaluate whether a CLI is agent-native across 7 design principles
  - Design stdout JSON contracts with stable error envelopes
  - Define exit code semantics per failure class (success, runtime, auth, validation)
  - Design layered --help, schema introspection, and dry-run previews
  - Define safety tiers: open (read), warned (write), hidden (destructive)
  - Design delegated authentication — human owns auth lifecycle, agent receives token
  - Apply directional trust model — env vars trusted, CLI args untrusted
  - Convert a REST API or SDK into an agent-native CLI command tree
  - Score a CLI on the 14-criterion rubric and summarize the seven design principles
  - Produce a prioritized P0/P1/P2 refactor plan with concrete examples

prerequisites: []
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall