# Garden Skills Open-source agent skills collection for web design, retrieval, image generation, and creative workflows. ## Agent Decision Summary - Risk level: low - Source confidence: medium - Recommended workflows: Browser automation, Coding agent workflow, Memory or RAG workflow, Reusable skill workflow - Permission surface: low explicit permission surface in metadata - Agent JSON: https://www.openagent.bot/skills/garden-skills.agent.json ## Summary Garden Skills is an open-source skills collection for AI agents. It packages reusable instructions and workflows for web design, knowledge retrieval, image generation, and related tasks. ## Guide Garden Skills is an open-source collection of reusable skills for AI agents. ### What it is It packages workflows for web design, retrieval, image generation, and related agent tasks. ### Why it matters Skills make agent behavior more repeatable by turning tacit workflow knowledge into files that can be reviewed and reused. ### How it works Start by reading the repository structure, then adapt one skill to your own agent environment and compare output consistency. ### FAQ - Is Garden Skills open source? - Yes. The repository is listed under the MIT license. - Who should evaluate Garden Skills? - Anyone building or curating reusable skills for coding, design, or creative AI agents. ## What It Does It packages workflows for web design, retrieval, image generation, and related agent tasks. ## How To Evaluate Start by reading the repository structure, then adapt one skill to your own agent environment and compare output consistency. ## Why It Matters Agent skills are becoming a practical way to turn expert workflows into reusable operating instructions. Garden Skills is useful for teams studying how skills can be organized and shared. ## Best For - Users building a personal or team agent skills library - Design and creative teams experimenting with reusable agent workflows - Developers looking for examples of skill packaging ## Not For - Teams that need a complete agent runtime - Users looking for a single-purpose automation script ## What It Actually Does - Reusable skill patterns: Garden Skills provides packaged instructions for repeatable agent work. - Why it matters: Reusable skills reduce prompting friction and help teams standardize outputs. - Creative workflow coverage: The collection includes web design, retrieval, and image generation oriented workflows. - Why it matters: Creative agent work benefits from examples, constraints, and repeatable quality bars. - Open repository: The project can be inspected, forked, and adapted. - Why it matters: Teams can learn from the skill structure instead of treating agent instructions as private magic. ## Typical Use Cases - Skill library design: Use the repository as a reference for naming, organizing, and maintaining agent skills. - Design task repeatability: Package design preferences and workflow steps so agents produce more consistent outputs. - Creative production experiments: Adapt skills for image, web, and knowledge retrieval tasks. ## How It Compares - When to choose Garden Skills: Compare it with nearby skills by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need. ## Fit Matrix - Browser automation: strong. Garden Skills has multiple signals for browser automation, including matching tags, capabilities, category, or positioning. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs. - Coding agent workflow: strong. Garden Skills has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning. Required check: Run a small repository change and inspect the diff, tests, and rollback path. - Memory or RAG workflow: strong. Garden Skills has multiple signals for memory or rag workflow, including matching tags, capabilities, category, or positioning. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data. - Reusable skill workflow: strong. Garden Skills has multiple signals for reusable skill workflow, including matching tags, capabilities, category, or positioning. Required check: Run one skill end to end and check whether it produces evidence or structured output. - Evaluation and observability: partial. Garden Skills has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI. - Connector or protocol layer: weak. Garden Skills is not primarily positioned for connector or protocol layer in the current metadata. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs. ## Evidence - verified: Garden Skills is listed as open source. Source: License metadata: MIT - verified: Garden Skills has a recorded GitHub repository: ConardLi/garden-skills. Source: Resource facts and GitHub source link. - inferred: Garden Skills supports these recorded deployment modes: cloud. Source: OpenAgent decision signal metadata. - inferred: Garden Skills is tagged with agent skill capabilities. Source: OpenAgent capability taxonomy. ## Missing Checks - Dedicated docs link is missing. - Repository freshness has not been recorded. ## Next Actions - Inspect repository: https://github.com/ConardLi/garden-skills ## Facts - Category: skills - Resource type: skill - Open source: yes - License: MIT - Last verified: 2026-06-09 - GitHub repo: ConardLi/garden-skills - GitHub stars: 7602 ## Capabilities - agent-skill ## Structured Use Case Tags - developer-workflow ## Getting Started - Open the GitHub repository: https://github.com/ConardLi/garden-skills ## Links - GitHub: https://github.com/ConardLi/garden-skills ## Structured Outputs - JSON: https://www.openagent.bot/skills/garden-skills.json - Markdown: https://www.openagent.bot/skills/garden-skills.md - Agent JSON: https://www.openagent.bot/skills/garden-skills.agent.json - Canonical: https://www.openagent.bot/skills/garden-skills