Adonis0123/adonis-skills / skills/ardot-mcp
ardot-mcp
VerifiedThis skill should be used when the user invokes /ardot-mcp or asks to package Ardot MCP through UXC, set up ardot-mcp-cli, complete Ardot OAuth for UXC, run sanitized Ardot readiness, open or inspect Ardot design files via a fixed CLI facade, or keep Grok/Claude native Ardot MCP as a compatibility path. Own Ardot endpoint identity, OAuth boundary, safe output, and task acceptance. Use uxc-facade for the generic packaging method. Do not use for one-off Ardot calls already solved by the native host MCP tools.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.6 KB |
| agents/openai.yaml | config | 103 B |
| evals/evals.json | config | 2.9 KB |
| evals/trigger-eval.json | config | 1.4 KB |
| references/oauth-and-binding.md | markdown | 1.9 KB |
| references/uxc-facade.md | markdown | 2.0 KB |
| scripts/install-uxc.zshexecutable | script | 4.4 KB |
| scripts/lib/defaults.zsh | script | 802 B |
| scripts/lib/uxc-link-contract.zsh | script | 838 B |
| scripts/lib/uxc-owned-binary.zsh | script | 3.5 KB |
| scripts/lib/uxc-release.zsh | script | 1.3 KB |
| scripts/oauth-complete.zshexecutable | script | 1.4 KB |
| scripts/oauth-start.zshexecutable | script | 937 B |
| scripts/setup-auth-binding.zshexecutable | script | 1.9 KB |
| scripts/setup-uxc-link.zshexecutable | script | 2.3 KB |
| scripts/uxc-readiness.zshexecutable | script | 2.8 KB |
evals/evals.json
View on GitHub{
"skill_name": "ardot-mcp",
"evals": [
{
"id": 1,
"name": "readiness-only-entry",
"prompt": "/ardot-mcp",
"expected_output": "Runs sanitized UXC readiness through the owned ardot-mcp facade and returns ARDOT_MCP_READY without mutating designs or printing OAuth tokens.",
"files": [],
"expectations": [
"Treats bare /ardot-mcp as readiness-only",
"Uses zsh scripts/uxc-readiness.zsh rather than an unowned PATH uxc",
"Does not claim task acceptance from readiness alone"
]
},
{
"id": 2,
"name": "oauth-handoff",
"prompt": "Ardot 的 UXC facade 报 oauth_required。请按 ardot-mcp skill 完成 OAuth 并重新 readiness。",
"expected_output": "Uses oauth-start/oauth-complete helpers, sets the ardot-mcp binding, retries sanitized readiness once, and never pastes tokens into chat.",
"files": [],
"expectations": [
"Follows the skill OAuth handoff instead of inventing curl token hacks",
"Keeps native Grok OAuth separate from UXC credentials",
"Retries readiness after binding is ready"
]
},
{
"id": 3,
"name": "design-task-acceptance",
"prompt": "用 ardot-mcp-cli 打开 https://ardot.tencent.com/file/726157280612685 并总结页面顶层 Frame。",
"expected_output": "Proves readiness or reuses private-result, then runs open_design/fetch_editor_state or batch_read through ardot-mcp-cli and reports task acceptance separately from transport.",
"files": [],
"expectations": [
"Uses the managed CLI path by default",
"Separates TRANSPORT_READY from TASK_ACCEPTANCE",
"Avoids dumping unrelated design payloads"
]
},
{
"id": 4,
"name": "native-compat-opt-in",
"prompt": "当前 Grok 已经连了 ardot-remote,不要装 UXC,直接用原生 MCP 看一下文件。",
"expected_output": "Respects the explicit native compatibility request, does not install or overwrite the UXC binary/link, and marks NATIVE_COMPAT when using host tools.",
"files": [],
"expectations": [
"Does not force UXC install when native is requested",
"Marks native compatibility explicitly",
"Does not claim the shared facade is ready without running it"
]
},
{
"id": 5,
"name": "binary-owner-conflict",
"prompt": "chrome-dev-mcp 想装 UXC 0.17,ardot-mcp 想装 0.22,能不能各装一份?",
"expected_output": "Explains the shared $HOME/.uxc daemon boundary, keeps ardot-mcp as the named binary owner for its pin, and refuses silent dual-version installs on one user.",
"files": [],
"expectations": [
"Names the shared daemon boundary",
"Does not allow two owners to overwrite one shared daemon version silently",
"Points to uxc-facade for the generic ownership method"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |