Drive a real browser against a URL — capture full-page screenshots, inspect computed styles / ARIA / cursor / overflow per selector, and exercise interactions (open menus, hover for tooltips). Wraps ${CLAUDEPLUGINDIR}/scripts/capture-surface.mjs and ${CLAUDEPLUGINDIR}/scripts/inspect-surface.mjs. Uses headless Playwright with saved auth state by default; supports the user's running Chrome via opt-in.
EnglishMeta-knowledge for authoring canvases — the template + instructions pairs that govern artifacts produced by SDLC agents (specs, plans, reports, ...). Covers the canvas concept, the canonical knob taxonomy, conversation modes (new / tune / reverse / validate / explain), the response scaffold, and the anti-pattern catalog. Use when authoring a new canvas, tuning an existing one, reverse-modeling a canvas from an example artifact, validating a canvas, or teaching the canvas system to a new contributor.
EnglishAuthoritative reference and authoring guide for the Claude platform — both the Claude Code .claude/ config layer (skills, subagents, output styles, hooks, plugins, settings) and the Anthropic Agent SDK (Managed Agents API: agents, sessions, threads, multiagent, skills). Use when authoring a skill / subagent / output style / hook / plugin manifest, when designing a multi-agent system, or when comparing CLI vs SDK and translating between them.
EnglishSnapshot a Figma frame's metadata, tokens, design-context, and screenshot to local files under .ai-docs/figma/ / so downstream agents (design-builder, design-grader, spec authors) don't re-call the Figma MCP every iteration. Universal — not tied to design-loop; usable for spec writing, design audits, refactor planning.
EnglishWorkflow judgment for this project's SDLC loop — when to use /plan vs /design vs /develop vs /orchestrate, what each gate means, how to recover from a halt, how stacks and artifacts flow. Use when starting work on an issue, deciding the next command, interpreting a halt from any phase agent, or recovering from a failed gate.
EnglishAuto-load PR stack context for current branch. Reads stack state and reports position. Use when working on any branch that is part of a PR stack.
English
AGENT SKILLS ATLASIncludes Browser Driver, Canvas Authoring, Claude Platform, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Browser Driver
Drive a real browser against a URL — capture full-page screenshots, inspect computed styles / ARIA / cursor / overflow per selector, and exercise interactions (open menus, hover for tooltips). Wraps ${CLAUDEPLUGINDIR}/scripts/capture-surface.mjs and ${CLAUDEPLUGINDIR}/scripts/inspect-surface.mjs. Uses headless Playwright with saved auth state by default; supports the user's running Chrome via opt-in.
Canvas Authoring
Meta-knowledge for authoring canvases — the template + instructions pairs that govern artifacts produced by SDLC agents (specs, plans, reports, ...). Covers the canvas concept, the canonical knob taxonomy, conversation modes (new / tune / reverse / validate / explain), the response scaffold, and the anti-pattern catalog. Use when authoring a new canvas, tuning an existing one, reverse-modeling a canvas from an example artifact, validating a canvas, or teaching the canvas system to a new contributor.
Claude Platform
Authoritative reference and authoring guide for the Claude platform — both the Claude Code .claude/ config layer (skills, subagents, output styles, hooks, plugins, settings) and the Anthropic Agent SDK (Managed Agents API: agents, sessions, threads, multiagent, skills). Use when authoring a skill / subagent / output style / hook / plugin manifest, when designing a multi-agent system, or when comparing CLI vs SDK and translating between them.
Figma Snapshot
Snapshot a Figma frame's metadata, tokens, design-context, and screenshot to local files under .ai-docs/figma/ / so downstream agents (design-builder, design-grader, spec authors) don't re-call the Figma MCP every iteration. Universal — not tied to design-loop; usable for spec writing, design audits, refactor planning.
Sdlc Loop
Workflow judgment for this project's SDLC loop — when to use /plan vs /design vs /develop vs /orchestrate, what each gate means, how to recover from a halt, how stacks and artifacts flow. Use when starting work on an issue, deciding the next command, interpreting a halt from any phase agent, or recovering from a failed gate.
Stack Management
Auto-load PR stack context for current branch. Reads stack state and reports position. Use when working on any branch that is part of a PR stack.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Browser Driver skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- License details are not provided in these listings. Check the author’s terms before using the skills.