Playground
Arize-ai/phoenix
Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset.
Design parks, plazas, waterfronts, pocket parks, civic spaces, playgrounds, and urban gardens using Jan Gehl quality criteria, PPS placemaking methodology, and global best practices.
$ npx skills add Abhinavbwj/Urban-Design-Skills-Claude --skill public-space-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Abhinavbwj/Urban-Design-Skills-Claude public-space-design --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/Abhinavbwj/Urban-Design-Skills-Claude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/public-space-design .claude/skills/public-space-design && 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 "public-space-design" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/public-space-design into .claude/skills/public-space-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "public-space-design", 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/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/public-space-designType 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 Abhinavbwj/Urban-Design-Skills-Claude --skill public-space-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Abhinavbwj/Urban-Design-Skills-Claude public-space-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abhinavbwj/Urban-Design-Skills-Claude.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/public-space-design .agents/skills/public-space-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "public-space-design" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/public-space-design into .agents/skills/public-space-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "public-space-design", 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 Abhinavbwj/Urban-Design-Skills-Claude --skill public-space-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Abhinavbwj/Urban-Design-Skills-Claude public-space-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abhinavbwj/Urban-Design-Skills-Claude.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/public-space-design .cursor/skills/public-space-design && 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 "public-space-design" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/public-space-design into .cursor/skills/public-space-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "public-space-design", 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/Abhinavbwj/Urban-Design-Skills-Claude.git --path skills/public-space-design--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 Abhinavbwj/Urban-Design-Skills-Claude --skill public-space-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Abhinavbwj/Urban-Design-Skills-Claude public-space-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abhinavbwj/Urban-Design-Skills-Claude.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/public-space-design .gemini/skills/public-space-design && 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 "public-space-design" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/public-space-design into .gemini/skills/public-space-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "public-space-design", 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 Abhinavbwj/Urban-Design-Skills-Claude public-space-designInstalls 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 Abhinavbwj/Urban-Design-Skills-Claude --skill public-space-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Abhinavbwj/Urban-Design-Skills-Claude.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/public-space-design .github/skills/public-space-design && 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 "public-space-design" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/public-space-design into .github/skills/public-space-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "public-space-design", 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 Abhinavbwj/Urban-Design-Skills-Claude --skill public-space-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Abhinavbwj/Urban-Design-Skills-Claude public-space-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Abhinavbwj/Urban-Design-Skills-Claude.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/public-space-design .opencode/skills/public-space-design && 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 "public-space-design" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/public-space-design into .opencode/skills/public-space-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "public-space-design", 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.
public-space-designDesign parks, plazas, waterfronts, pocket parks, civic spaces, playgrounds, and urban gardens using Jan Gehl quality criteria, PPS placemaking methodology, and global best practices.
Public Space Design is an agent skill from Abhinavbwj/Urban-Design-Skills-Claude. Design parks, plazas, waterfronts, pocket parks, civic spaces, playgrounds, and urban gardens using Jan Gehl quality criteria, PPS placemaking methodology, and global best practices. Use when the user asks to design a park, create a plaza, plan a waterfront, design a civic space, lay out a playground, plan a community garden, create an outdoor gathering space, design a public realm strategy, or improve an existing public space. Also use when discussing public space programming, activation strategies, or landscape…
Its SKILL.md is about 7.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/gehl-criteria.md`, `references/programming-guide.md` and `references/space-typologies.md`).
The repository describes itself as: Urban Design Skills Claude. The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 666327b. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Public Space Design loads about 7.6k tokens when it runs, and up to ~30k if it reads all its reference files. Until then it costs about 141 tokens; SKILL.md has 4,063 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.
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.
The full file from Abhinavbwj/Urban-Design-Skills-Claude at commit 666327b, republished under its MIT licence (© Abhinavbwj). 4,063 words, ~7,600 tokens.
.claude/skills/public-space-design/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.You are an expert public space designer with deep knowledge of Jan Gehl's urban quality criteria, the Project for Public Spaces (PPS) placemaking methodology, and global best practices in landscape architecture and urban realm design. You design spaces that are safe, comfortable, vibrant, and loved by the communities they serve.
Before designing, classify the space to establish dimensional and programmatic parameters. Use the following decision tree:
Step 1 - Determine scale:
Step 2 - Determine dominant character:
Step 3 - Match to typology:
| Typology | Area Range | Key Dimension | Aspect Ratio | Landscape Character |
|---|---|---|---|---|
| Civic Plaza | > 0.5 ha | 30 - 100 m | 1:1 to 1:2 | Hard dominant, formal |
| Neighborhood Park | 0.5 - 5 ha | 70 - 250 m | Varied | Mixed, diverse programming |
| Pocket Park | < 0.5 ha | 10 - 30 m | 1:1 to 1:3 | Intimate, simple program |
| Linear Park / Greenway | Corridor | 10 - 30 m wide | > 3:1 | Continuous, movement-oriented |
| Waterfront Promenade | Corridor | 8 - 20 m wide | Linear | Hard edge, views to water |
| Playground | 0.05 - 0.5 ha | 20 - 70 m | Varied | Defined boundary, surfacing |
| Community Garden | 0.1 - 0.5 ha | 30 - 70 m | Varied | Cultivated, utilitarian |
| Streetscape / Green Street | Within ROW | 2 - 6 m zones | Linear | Bioswales, trees, seating |
Step 4 - Confirm the following before proceeding:
Follow this 6-step workflow for every public space project:
Apply all 12 criteria from Jan Gehl's framework. Each criterion must be explicitly addressed in the design. Score every criterion from 1 (poor) to 5 (excellent).
Criterion 1 - Protection Against Traffic and Accidents The space must feel physically and psychologically safe from vehicles.
Criterion 2 - Protection Against Crime and Violence (Safety and Security) People must feel safe at all times of day and night.
Criterion 3 - Protection Against Unpleasant Sensory Experiences The space must be comfortable against wind, rain, noise, pollution, dust, glare, and extreme temperatures.
Criterion 4 - Opportunities to Walk Movement through and within the space must be easy, logical, and enjoyable.
Criterion 5 - Opportunities to Stand and Linger People need comfortable places to pause, wait, and people-watch.
Criterion 6 - Opportunities to Sit Seating is the single most critical element of a successful public space.
Criterion 7 - Opportunities to See Visibility is essential for feeling safe, engaged, and oriented.
Criterion 8 - Opportunities to Talk and Listen The acoustic environment must support conversation.
Criterion 9 - Opportunities for Play, Exercise, and Activity The space must invite physical engagement for all ages.
Criterion 10 - Scale (Human Scale and Proportion) The space must feel comfortable and appropriately scaled to the human body.
Criterion 11 - Opportunities to Enjoy Climate Design the space to maximize climate comfort throughout the year.
Criterion 12 - Positive Sensory Experiences (Aesthetic Quality and Delight) The space must be beautiful, interesting, and sensorially rich.
Use these dimensions as design inputs. Deviations are acceptable with justification but should be flagged.
Apply Project for Public Spaces methodology in parallel with the Gehl criteria.
Every successful public space needs at least 10 things to do. If you cannot list 10 activities or reasons a person would visit, the design is under-programmed.
Position elements to stimulate interaction between strangers.
People gravitate to edges, not centers. Activity concentrates where the space meets its boundary.
People will not stay in a space that lacks basic comfort provisions.
Great spaces are actively managed, not just designed and abandoned.
Flag and avoid these in every design review:
When presenting a public space design, structure the output as follows:
Site Summary
Design Concept
Program
| Zone / Room | Area (m2) | Primary Activity | Users | Hours of Use |
|---|---|---|---|---|
| [Zone 1] | [area] | [activity] | [user group] | [time range] |
| [Zone 2] | [area] | [activity] | [user group] | [time range] |
| ... | ... | ... | ... | ... |
Dimensional Compliance
| Standard | Required | Provided | Status |
|---|---|---|---|
| Seating quantity | [from Sec 4] | [designed] | [Pass/Fail] |
| Path width | 1.8m min | [designed] | [Pass/Fail] |
| Canopy cover | [target %] | [designed %] | [Pass/Fail] |
| Gradient | 5% max | [designed] | [Pass/Fail] |
| Lighting | [lux range] | [designed] | [Pass/Fail] |
Gehl 12 Criteria Scorecard
| # | Criterion | Score (1-5) | Design Response |
|---|---|---|---|
| 1 | Traffic safety | [score] | [how addressed] |
| 2 | Crime safety | [score] | [how addressed] |
| 3 | Sensory protection | [score] | [how addressed] |
| 4 | Walking | [score] | [how addressed] |
| 5 | Standing/lingering | [score] | [how addressed] |
| 6 | Sitting | [score] | [how addressed] |
| 7 | Seeing | [score] | [how addressed] |
| 8 | Talking/listening | [score] | [how addressed] |
| 9 | Play/exercise | [score] | [how addressed] |
| 10 | Human scale | [score] | [how addressed] |
| 11 | Climate enjoyment | [score] | [how addressed] |
| 12 | Aesthetic quality | [score] | [how addressed] |
| Average | [avg] | Minimum target: 4.0 |
Placemaking Check
Materials and Planting
Maintenance and Management
Use the following references for detailed guidance:
references/space-typologies.md for 10+ typologies with dimensional ranges, materials, planting, and precedent examples.references/gehl-criteria.md for the full scoring methodology, observation tools, and data collection templates.references/programming-guide.md for activity programming, seasonal strategies, event infrastructure, and maintenance benchmarks.Key External References:
© Abhinavbwj, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references) in skills/public-space-design of Abhinavbwj/Urban-Design-Skills-Claude.
Open the folder on GitHubat commit 666327b
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in Abhinavbwj/Urban-Design-Skills-Claude, which our catalogue first saw on October 7, 2026.
Public Space Design 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 |
|---|---|---|---|---|---|---|
| Public Space Design this skillAbhinavbwj/Urban-Design-Skills-Claude | 132 | 1 repos | ~7.6k | Automated safety check: Pass | MIT | |
| PlaygroundArize-ai/phoenix | 12k | — | ~3.9k | Automated safety check: Pass | Custom licence | |
| Vuetify Playgroundvuetifyjs/vuetify | 41k | — | ~730 | Automated safety check: Pass | Custom licence | |
| Maintain Spaceasgeirtj/system_prompts_leaks | 69k | — | ~1.6k | Automated safety check: Pass | CC0-1.0 | |
| Organize Spaceasgeirtj/system_prompts_leaks | 69k | — | ~1.6k | Automated safety check: Pass | CC0-1.0 | |
| Huggingface Spacessickn33/agentic-awesome-skills | 47k | 1 repos | ~3.9k | Automated safety check: Pass | Apache-2.0 |
Arize-ai/phoenix
Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset.
vuetifyjs/vuetify
Maintains the Vuetify repo's local Playground.vue so contributors get a realistic reproduction and a short demo they can paste into a pull request description.
asgeirtj/system_prompts_leaks
Reconcile new evidence into existing ChatGPT Pages or a Space when the user requests upkeep.
asgeirtj/system_prompts_leaks
Organize existing ChatGPT Pages and Space structure when the user requests changes to that structure.
sickn33/agentic-awesome-skills
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community…
github/awesome-copilot
Use Copilot Spaces to provide project-specific context to conversations.
Abhinavbwj/Urban-Design-Skills-Claude
Estimate construction costs, infrastructure costs, soft costs, and total development costs for urban design projects.
Abhinavbwj/Urban-Design-Skills-Claude
Python computational tools for urban design metric calculations including density, FAR, walkability scoring, parking requirements, green space analysis, and block optimization.
Abhinavbwj/Urban-Design-Skills-Claude
Design urban blocks and optimize density using typological analysis, FAR calculations, and building configuration strategies.
Abhinavbwj/Urban-Design-Skills-Claude
Evaluate urban designs against comprehensive criteria drawn from all major global standards, certification systems, and theoretical frameworks.
Abhinavbwj/Urban-Design-Skills-Claude
Comprehensive mobility and transport planning for urban design including trip generation, mode split targets, street network connectivity, transit planning, cycling network design, pedestrian…
Abhinavbwj/Urban-Design-Skills-Claude
Research and analyze urban design precedents systematically.
Design parks, plazas, waterfronts, pocket parks, civic spaces, playgrounds, and urban gardens using Jan Gehl quality criteria, PPS placemaking methodology, and global best practices. Public Space Design is an agent skill from Abhinavbwj/Urban-Design-Skills-Claude. Design parks, plazas, waterfronts, pocket parks, civic spaces, playgrounds, and urban gardens using Jan Gehl quality criteria, PPS placemaking methodology, and global best practices.
Public Space Design fits situations like: the user asks to design a park; plan a waterfront; design a civic space; lay out a playground.
Run `npx skills add Abhinavbwj/Urban-Design-Skills-Claude --skill public-space-design -a claude-code`. Or copy the skill folder (skills/public-space-design in Abhinavbwj/Urban-Design-Skills-Claude) into .claude/skills/public-space-design in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Abhinavbwj/Urban-Design-Skills-Claude --skill public-space-design -a codex`. Or copy the skill folder (skills/public-space-design in Abhinavbwj/Urban-Design-Skills-Claude) into .agents/skills/public-space-design in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Abhinavbwj/Urban-Design-Skills-Claude --skill public-space-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/public-space-design, .gemini/skills/public-space-design, .github/skills/public-space-design and .opencode/skills/public-space-design in your project.
SKILL.md names no scripts, command-line tools or credentials: Public Space Design is instructions for the agent only.
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.
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.
Public Space Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 7.6k tokens (SKILL.md is roughly 30k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 22k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Public Space Design: Playground (Arize-ai/phoenix, 12k stars), Vuetify Playground (vuetifyjs/vuetify, 41k stars), Maintain Space (asgeirtj/system_prompts_leaks, 69k stars) and Organize Space (asgeirtj/system_prompts_leaks, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Abhinavbwj (a GitHub user) maintains it in Abhinavbwj/Urban-Design-Skills-Claude, which has 132 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on March 12, 2026.
Source: Abhinavbwj/Urban-Design-Skills-Claude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.