Markdown Rendering
sickn33/agentic-awesome-skills
Open Markdown reliably in cmux panes and recover from blank rendered surfaces.
A skill your agent uses when an agent renders rich UI back to a client surface (cards, dashboards, forms, modals) using the A2UI v0.8.0 declarative protocol.
Apache-2.0Auto-check passed
Install A2ui Rendering
$ npx skills add GoogleCloudPlatform/race-condition --skill a2ui-rendering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install GoogleCloudPlatform/race-condition a2ui-rendering --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/race-condition.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/skills/a2ui-rendering .claude/skills/a2ui-rendering && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "a2ui-rendering" agent skill from https://github.com/GoogleCloudPlatform/race-condition/tree/main/agents/skills/a2ui-rendering into .claude/skills/a2ui-rendering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a2ui-rendering", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/GoogleCloudPlatform/race-condition/tree/main/agents/skills/a2ui-renderingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add GoogleCloudPlatform/race-condition --skill a2ui-rendering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install GoogleCloudPlatform/race-condition a2ui-rendering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/race-condition.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agents/skills/a2ui-rendering .agents/skills/a2ui-rendering && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "a2ui-rendering" agent skill from https://github.com/GoogleCloudPlatform/race-condition/tree/main/agents/skills/a2ui-rendering into .agents/skills/a2ui-rendering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a2ui-rendering", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GoogleCloudPlatform/race-condition --skill a2ui-rendering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install GoogleCloudPlatform/race-condition a2ui-rendering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/race-condition.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agents/skills/a2ui-rendering .cursor/skills/a2ui-rendering && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "a2ui-rendering" agent skill from https://github.com/GoogleCloudPlatform/race-condition/tree/main/agents/skills/a2ui-rendering into .cursor/skills/a2ui-rendering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a2ui-rendering", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/GoogleCloudPlatform/race-condition.git --path agents/skills/a2ui-rendering--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add GoogleCloudPlatform/race-condition --skill a2ui-rendering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install GoogleCloudPlatform/race-condition a2ui-rendering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/race-condition.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agents/skills/a2ui-rendering .gemini/skills/a2ui-rendering && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "a2ui-rendering" agent skill from https://github.com/GoogleCloudPlatform/race-condition/tree/main/agents/skills/a2ui-rendering into .gemini/skills/a2ui-rendering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a2ui-rendering", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install GoogleCloudPlatform/race-condition a2ui-renderingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add GoogleCloudPlatform/race-condition --skill a2ui-rendering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/race-condition.git skills-src && mkdir -p .github/skills && cp -r skills-src/agents/skills/a2ui-rendering .github/skills/a2ui-rendering && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "a2ui-rendering" agent skill from https://github.com/GoogleCloudPlatform/race-condition/tree/main/agents/skills/a2ui-rendering into .github/skills/a2ui-rendering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a2ui-rendering", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GoogleCloudPlatform/race-condition --skill a2ui-rendering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install GoogleCloudPlatform/race-condition a2ui-rendering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GoogleCloudPlatform/race-condition.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agents/skills/a2ui-rendering .opencode/skills/a2ui-rendering && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "a2ui-rendering" agent skill from https://github.com/GoogleCloudPlatform/race-condition/tree/main/agents/skills/a2ui-rendering into .opencode/skills/a2ui-rendering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a2ui-rendering", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
a2ui-rendering- GitHub stars
- 234
- Token cost
- ~1k tokens
- SKILL.md length
- 318 words
- Files
- 4
- Skills in repo
- 16
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when an agent renders rich UI back to a client surface (cards, dashboards, forms, modals) using the A2UI v0.8.0 declarative protocol.
- An agent renders rich UI back to a client surface (cards
- SKILL.md covers When to Compose A2UI, Workflow, Message Structure and Typed Value Wrappers, plus 4 more sections
- Runs Python scripts from its folder
- Modals) using the A2UI v0.8.0 declarative protocol
What it does
A2ui Rendering is an agent skill from GoogleCloudPlatform/race-condition. Use when an agent renders rich UI back to a client surface (cards, dashboards, forms, modals) using the A2UI v0.8.0 declarative protocol. Required whenever the response should display structured components rather than plain text, or whenever the validateandemita2ui tool is in scope.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `components.md`, `examples.md` and `tools.py`).
The repository describes itself as: The open source multi-agent simulation from the Developer Keynote at Google Cloud Next '26. A deployable reference architecture for autonomous AI agents using Gemini and ADK. The licence is Apache-2.0.
When your agent uses it
- An agent renders rich UI back to a client surface (cards
- Modals) using the A2UI v0.8.0 declarative protocol
Example prompts
- “/a2ui-rendering”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 26efc1b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
A2ui Rendering loads about 1k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 318 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from GoogleCloudPlatform/race-condition at commit 26efc1b, republished under its Apache-2.0 licence (© GoogleCloudPlatform). 318 words, ~1,030 tokens.
Download SKILL.mdSave it as
.claude/skills/a2ui-rendering/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- a2ui-rendering
- description
- Use when an agent renders rich UI back to a client surface (cards, dashboards, forms, modals) using the A2UI v0.8.0 declarative protocol. Required whenever the response should display structured components rather than plain text, or whenever the validate_and_emit_a2ui tool is in scope.
- license
- Apache-2.0
A2UI Rendering
A2UI is a declarative JSON protocol for delivering rich UI from agents to client surfaces. UI is composed as a flat list of components where layout containers reference children by ID. The protocol enforces typed value wrappers and a fixed catalog of 18 primitives.
When to Compose A2UI
Compose A2UI only in response to a user message that needs rich visual output. Do not generate A2UI on session creation or proactively. Plain text remains the default for narrative responses.
Workflow
A2UI Render Progress:
- [ ] Decide what information to present
- [ ] Choose primitives (Text, Card, Column/Row, etc.)
- [ ] Compose the surfaceUpdate JSON with unique component IDs
- [ ] Call validate_and_emit_a2ui with the surfaceUpdate JSON
- [ ] If validation fails, fix the violations and re-validate
- [ ] Compose the beginRendering JSON pointing to the root component
- [ ] Call validate_and_emit_a2ui with the beginRendering JSON
- [ ] Wrap both validated payloads in ```a2ui markdown fencesvalidate_and_emit_a2ui MUST be called twice per surface: once
for surfaceUpdate and once for beginRendering. Without
beginRendering, the frontend will not render the surface.
<!-- [START a2ui_skill_message_structure] -->Message Structure
surfaceUpdate (defines components)
{
"surfaceUpdate": {
"surfaceId": "my-surface",
"components": [
{"id": "unique-id", "component": {"TypeName": { ...props }}}
]
}
}surfaceId: unique identifier for this UI surface.components: flat array of component definitions (NOT nested trees).- Each component has
id(unique string) andcomponent(object with exactly one key = the type name).
beginRendering (tells the frontend which component is root)
{
"beginRendering": {
"surfaceId": "my-surface",
"root": "root-component-id"
}
}surfaceId: must match the surfaceUpdate's surfaceId.root: theidof the outermost component (usually a Card).
<!-- [END a2ui_skill_message_structure] --><!-- [START a2ui_skill_wrappers] -->Typed Value Wrappers
CRITICAL: Never use raw JSON primitives. All values MUST be wrapped.
| Type | Wrapper | Example |
|---|---|---|
| String | {"literalString": "value"} | "text": {"literalString": "Hello"} |
| Number | {"literalNumber": 42.0} | "value": {"literalNumber": 3.14} |
| Boolean | {"literalBoolean": true} | "autoplay": {"literalBoolean": true} |
| Binding | {"path": "some.data.path"} | "text": {"path": "user.name"} |
Raw "value", raw 42, or raw true as property values will be
rejected by validate_and_emit_a2ui.
<!-- [END a2ui_skill_wrappers] -->Container Children
Layout containers reference children by ID:
- Multiple children:
"children": {"explicitList": ["child-id-1", "child-id-2"]}(NEVER raw arrays) - Single child:
"child": "child-id"(used by Card, Button)
Component ID Rules
- IDs MUST be unique within a
surfaceUpdate. - Use descriptive names:
"title-heading","main-card","details-column". - All ID references (
child,children.explicitList,entryPointChild,contentChild,tabItems[].child) MUST resolve to IDs in the samecomponentsarray.
Component Catalog
For the full catalog of 18 primitives, with required and optional props plus per-type notes, see components.md.
Examples
For three complete surfaceUpdate + beginRendering payloads
(simple info card, data list card, dashboard with action button), see
examples.md.
© GoogleCloudPlatform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files in agents/skills/a2ui-rendering of GoogleCloudPlatform/race-condition.
- SKILL.md
- components.md
- examples.md
- tools.py
Open the folder on GitHubat commit 26efc1b
Compare with similar skills
A2ui Rendering next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| A2ui Rendering this skillGoogleCloudPlatform/race-condition | 234 | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Markdown Renderingsickn33/agentic-awesome-skills | 47k | 1 repos | ~751 | Automated safety check: Pass | MIT | |
| Render Blockingthedaviddias/Front-End-Checklist | 74k | — | ~430 | Automated safety check: Pass | MIT | |
| RenderLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.8k | Automated safety check: Pass | MIT | |
| Workspace Surface Auditaffaan-m/ECC | 274k | 3 repos | ~1.3k | Automated safety check: Notes | MIT | |
| A2uiPrism-Shadow/penguin-harness | 2.5k | — | ~3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Render Blocking
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Eliminate render-blocking resources.
Render
LeoYeAI/openclaw-master-skills
Deploy and operate apps on Render (Blueprint + one-click Dashboard deeplink, same flow as Codex render-deploy).
Workspace Surface Audit
affaan-m/ECC
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows.
A2ui
Prism-Shadow/penguin-harness
Make a reply easier to read and act on with rich blocks inside ordinary Markdown — a choice the user picks from, a form that collects several answers, a procedure as steps with warnings in place, a…
Multi Surface Render
yonatangross/orchestkit
Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes.
More from GoogleCloudPlatform/race-condition
All 16 skills in this repoGis Spatial Engineering
GoogleCloudPlatform/race-condition
A skill your agent uses when the marathon plan needs a 26.2-mile physical route generated from road-network GeoJSON, or when the request mentions traffic impact, route variety via seed, finishing…
Contributing
GoogleCloudPlatform/race-condition
Guides the developer workflow for contributing to Race Condition.
Deploying
GoogleCloudPlatform/race-condition
Guides deployment of Race Condition to a GCP project. An agent skill from GoogleCloudPlatform/race-condition.
Exploring The Codebase
GoogleCloudPlatform/race-condition
Explains the Race Condition architecture, the design decisions behind it, and where to read code first.
Getting Started
GoogleCloudPlatform/race-condition
Guides setup of the Race Condition project from clone to running simulation.
Preparing The Race
GoogleCloudPlatform/race-condition
A skill your agent uses when the simulator receives a validated plan from the planner and must initialize the race: parsing the plan, spawning runner agents, starting the telemetry collector, and…
Questions about A2ui Rendering
What does A2ui Rendering do?
A skill your agent uses when an agent renders rich UI back to a client surface (cards, dashboards, forms, modals) using the A2UI v0.8.0 declarative protocol. A2ui Rendering is an agent skill from GoogleCloudPlatform/race-condition.0 declarative protocol.
When should I use A2ui Rendering?
A2ui Rendering fits situations like: an agent renders rich UI back to a client surface (cards; modals) using the A2UI v0.8.0 declarative protocol.
How do I install A2ui Rendering in Claude Code?
Run `npx skills add GoogleCloudPlatform/race-condition --skill a2ui-rendering -a claude-code`. Or copy the skill folder (agents/skills/a2ui-rendering in GoogleCloudPlatform/race-condition) into .claude/skills/a2ui-rendering in your project. Claude Code loads it when a task matches its description.
How do I install A2ui Rendering in Codex?
Run `npx skills add GoogleCloudPlatform/race-condition --skill a2ui-rendering -a codex`. Or copy the skill folder (agents/skills/a2ui-rendering in GoogleCloudPlatform/race-condition) into .agents/skills/a2ui-rendering in your project. Codex loads it when a task matches its description.
Can I use A2ui Rendering in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GoogleCloudPlatform/race-condition --skill a2ui-rendering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/a2ui-rendering, .gemini/skills/a2ui-rendering, .github/skills/a2ui-rendering and .opencode/skills/a2ui-rendering in your project.
What does A2ui Rendering need to run?
Going by SKILL.md and its folder, A2ui Rendering needs Python for the scripts in its folder. Our summary lists: Python 3.
Does A2ui Rendering access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is A2ui Rendering safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does A2ui Rendering use?
A2ui Rendering is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does A2ui Rendering use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to A2ui Rendering?
Skills that share tags, products or a category with A2ui Rendering: Markdown Rendering (sickn33/agentic-awesome-skills, 47k stars), Render Blocking (thedaviddias/Front-End-Checklist, 74k stars), Render (LeoYeAI/openclaw-master-skills, 2.2k stars) and Workspace Surface Audit (affaan-m/ECC, 274k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains A2ui Rendering?
GoogleCloudPlatform (a GitHub organization) maintains it in GoogleCloudPlatform/race-condition, which has 234 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 5, 2026.
Source: GoogleCloudPlatform/race-condition on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.