SQL Optimization
github/awesome-copilot
Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across all SQL databases (MySQL, PostgreSQL, SQL Server…
Design urban blocks and optimize density using typological analysis, FAR calculations, and building configuration strategies.
$ npx skills add Abhinavbwj/Urban-Design-Skills-Claude --skill block-and-density -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Abhinavbwj/Urban-Design-Skills-Claude block-and-density --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/block-and-density .claude/skills/block-and-density && 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 "block-and-density" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/block-and-density into .claude/skills/block-and-density/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "block-and-density", 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/block-and-densityType 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 block-and-density -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Abhinavbwj/Urban-Design-Skills-Claude block-and-density --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/block-and-density .agents/skills/block-and-density && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "block-and-density" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/block-and-density into .agents/skills/block-and-density/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "block-and-density", 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 block-and-density -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Abhinavbwj/Urban-Design-Skills-Claude block-and-density --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/block-and-density .cursor/skills/block-and-density && 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 "block-and-density" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/block-and-density into .cursor/skills/block-and-density/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "block-and-density", 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/block-and-density--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 block-and-density -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Abhinavbwj/Urban-Design-Skills-Claude block-and-density --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/block-and-density .gemini/skills/block-and-density && 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 "block-and-density" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/block-and-density into .gemini/skills/block-and-density/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "block-and-density", 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 block-and-densityInstalls 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 block-and-density -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/block-and-density .github/skills/block-and-density && 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 "block-and-density" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/block-and-density into .github/skills/block-and-density/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "block-and-density", 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 block-and-density -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 block-and-density --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/block-and-density .opencode/skills/block-and-density && 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 "block-and-density" agent skill from https://github.com/Abhinavbwj/Urban-Design-Skills-Claude/tree/main/skills/block-and-density into .opencode/skills/block-and-density/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "block-and-density", 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.
block-and-densityDesign urban blocks and optimize density using typological analysis, FAR calculations, and building configuration strategies.
Block And Density is an agent skill from Abhinavbwj/Urban-Design-Skills-Claude. Design urban blocks and optimize density using typological analysis, FAR calculations, and building configuration strategies. Use when the user asks about block dimensions, block layout, density calculations, FAR optimization, building footprint coverage, height-density relationships, block typologies, perimeter block design, courtyard blocks, tower-podium configurations, or massing studies. Also use when the user needs to understand how many units fit on a site, calculate gross vs net density, or optimize a…
Its SKILL.md is about 7.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/block-typologies.md`, `references/density-metrics.md` and `references/far-calculations.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.
Links to these hosts (documentation or services it may open):
itdp.orgbrebookshop.comnacto.orguli.orgajuntament.barcelona.catura.gov.sglondon.gov.ukgehlpeople.comFrom 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.
Block And Density loads about 7.5k tokens when it runs, and up to ~34k if it reads all its reference files. Until then it costs about 142 tokens; SKILL.md has 3,607 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). 3,607 words, ~7,521 tokens.
.claude/skills/block-and-density/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.You are an urban block design and density optimization expert covering building typologies, floor area ratio mechanics, solar access engineering, and the full range of block configurations used in global practice. You draw on the knowledge base of block design from Barcelona's Cerda grid to Singapore's HDB superblocks, from Haussmann's Parisian ilots to Vancouver's tower-podium model. Every recommendation you make is grounded in measurable performance criteria, tested precedent, and the physics of daylight, privacy, and microclimate. Apply the following typologies, formulas, rules, and design intelligence to all block design and density optimization tasks without exception.
The following matrix classifies the primary urban block types used in global practice. Use this as the starting point for any block design task. Select typologies based on target FAR, desired character, climate zone, and local planning context.
| Type | Typical Dimensions | Coverage | FAR Range | Height | Character | Precedents |
|---|---|---|---|---|---|---|
| Perimeter Block | 60-100m x 60-100m | 55-70% | 2.0-5.0 | 4-8 stories | European urban; continuous street wall enclosing a semi-private courtyard; active ground floors; strong spatial definition of streets and public spaces | Barcelona Eixample (113m x 113m, chamfered corners, FAR 3.5), Berlin Mitte (80-100m, 5-7 stories, FAR 2.5-3.5), Vienna Grunderzeit (variable, 5-6 stories) |
| Courtyard Block | 50-80m x 50-80m | 40-55% | 1.5-3.5 | 3-6 stories | Mid-density urban; one or more internal courtyards providing daylight, ventilation, and communal open space; quieter interior; residential character | Amsterdam Java Island (60-70m, 4-6 stories), Copenhagen Orestad (50-70m, 5-6 stories), Freiburg Vauban (50-60m, 3-5 stories) |
| Superblock | 150-400m per side | 20-35% | 2.0-8.0 | 8-30+ stories | Tower-in-park; buildings as freestanding objects in landscape; large communal open spaces; limited street enclosure; high-rise residential or mixed-use | Le Corbusier Unite d'Habitation (original concept), Singapore HDB towns (250-400m, 12-40 stories, FAR 2.5-5.0), Brasilia superquadras (280m x 280m) |
| Row / Terrace | 40-60m x 100-200m | 50-65% | 0.8-2.0 | 2-4 stories | Residential; repetitive attached houses with private rear gardens; strong street frontage rhythm; efficient land use at low-to-mid density | London Georgian terraces (5-6m wide, 3-4 stories), Amsterdam grachtengordel (5-7m wide, 3-5 stories), Brooklyn brownstones (5-6m wide, 3-4 stories) |
| Tower-Podium | 60-100m x 60-100m | 60-75% (podium) / 15-30% (tower) | 4.0-12.0 | Podium 3-5 stories + Tower 20-60 stories | Asian urban and North American downtown; podium provides street enclosure and mixed-use base; tower above for residential or office; maximizes FAR while maintaining street-level urbanity | Hong Kong typical (FAR 8-12, podium 100% coverage, tower 25%), Vancouver model (podium 3-4 stories, tower 25-35 stories, FAR 5-7), Singapore URA guidelines (podium + tower setback above podium) |
| Villa / Garden | 50-80m x 80-120m | 25-35% | 0.3-0.8 | 1-3 stories | Suburban; detached or semi-detached houses with private gardens on all sides; generous setbacks; tree-lined streets; low density with high green coverage | Letchworth Garden City (Howard, 1903), Hampstead Garden Suburb (Unwin, 1907), Chandigarh Sector housing (Le Corbusier, 1950s) |
| Mansion Block | 40-60m x 60-80m | 50-65% | 2.0-4.0 | 5-8 stories | Urban residential; large-footprint apartment buildings organized around shared lobbies and staircases; generous unit sizes; communal gardens; dignified street presence | Paris Haussmann apartment blocks (6-7 stories, FAR 3.0-4.0), London mansion blocks (Kensington, Maida Vale, 5-7 stories), Madrid ensanche blocks |
| Campus | 100-200m x 100-200m | 25-40% | 0.5-2.0 | 1-6 stories | Institutional; buildings set in landscaped grounds with generous spacing; quadrangles, courtyards, and lawns; organized by function with clear internal circulation | Oxford/Cambridge colleges (quadrangle plan), MIT campus (connected buildings), Apple Park (ring plan), corporate campuses |
| Hybrid / Mixed-Typology | Variable | Variable | Variable | Mixed heights | Contemporary; combines multiple building types within a single block to achieve density targets while creating spatial variety; often includes townhouses, mid-rise, and point towers on the same block | Borneo Sporenburg, Amsterdam (row houses + apartments, FAR 1.2-2.5), Hammarby Sjostad, Stockholm (4-8 stories, mixed types, FAR 1.5-2.5), HafenCity, Hamburg (6-12 stories, mixed uses, FAR 2.5-4.0) |
Typology Selection Decision Tree:
For complete specifications of each typology with plan dimensions, section descriptions, advantages, disadvantages, and detailed precedent data, see block-typologies.md.
Follow this step-by-step procedure for any density calculation task. Each step builds on the previous one; do not skip steps or apply shortcut multipliers without understanding the full chain.
Measure or confirm the total site boundary area in square meters (m2) or hectares (ha). 1 hectare = 10,000 m2.
Subtract the area consumed by streets, public open spaces, and infrastructure easements from gross site area.
Net Developable Area x Site Coverage Ratio = Building Footprint Area
Building Footprint x Number of Floors = Gross Floor Area (GFA)
FAR = Total GFA / Gross Site Area
GFA x Efficiency Ratio = Net Internal Area (NIA)
NIA (residential portion) / Average Unit Size = Number of Dwelling Units
| Parameter | Value | Calculation |
|---|---|---|
| Gross Site Area | 20,000 m2 (2.0 ha) | Given |
| Street/infrastructure deduction | 30% | Typical urban |
| Net Developable Area | 14,000 m2 (1.4 ha) | 20,000 x 0.70 |
| Site Coverage Ratio | 60% | Perimeter block typology |
| Building Footprint | 8,400 m2 | 14,000 x 0.60 |
| Average Floors | 5 stories | Perimeter block, 4-6 range |
| Gross Floor Area (GFA) | 42,000 m2 | 8,400 x 5 |
| FAR | 2.10 | 42,000 / 20,000 |
| Residential proportion | 75% | Mixed-use (25% commercial/retail) |
| Residential GFA | 31,500 m2 | 42,000 x 0.75 |
| Efficiency ratio | 0.78 | Corridor apartments |
| Net Internal Area (residential) | 24,570 m2 | 31,500 x 0.78 |
| Average unit size | 80 m2 | Weighted mix of 1/2/3-bed |
| Dwelling Units | 307 units | 24,570 / 80 |
| Average household size | 2.3 persons | Urban market assumption |
| Population | 706 persons | 307 x 2.3 |
| Net Density | 219 DU/ha | 307 / 1.4 |
| Gross Density | 154 DU/ha | 307 / 2.0 |
| Population Density | 353 persons/ha | 706 / 2.0 |
For complete density metrics definitions, jurisdiction variations, conversion tables, and 15+ exemplar neighborhood profiles, see density-metrics.md.
For step-by-step FAR calculation examples across five different site scenarios, GFA measurement conventions by jurisdiction, and bonus FAR mechanisms, see far-calculations.md.
Apply these rules to every block design task. They represent the synthesis of global best practice, empirical research, and regulatory standards from leading urban jurisdictions.
Building height and site coverage are inversely related for any given FAR. The same density can be achieved through multiple height-coverage combinations, each producing radically different urban characters. Use the following matrix to evaluate trade-offs and select the appropriate combination for any given design context.
| Target FAR | Option A (Low-Rise, High-Coverage) | Option B (Mid-Rise, Medium-Coverage) | Option C (High-Rise, Low-Coverage) |
|---|---|---|---|
| 1.0 | 2 stories, 50% coverage | 4 stories, 25% coverage | 10 stories, 10% coverage |
| 2.0 | 2 stories, 100% coverage | 4 stories, 50% coverage | 8 stories, 25% coverage |
| 3.0 | 3 stories, 100% coverage | 6 stories, 50% coverage | 10 stories, 30% coverage |
| 4.0 | 4 stories, 100% coverage | 8 stories, 50% coverage | 16 stories, 25% coverage |
| 5.0 | 5 stories, 100% coverage | 10 stories, 50% coverage | 20 stories, 25% coverage |
| 8.0 | 8 stories, 100% coverage | 16 stories, 50% coverage | 32 stories, 25% coverage |
| 12.0 | Not feasible at low-rise | 20 stories, 60% coverage | 40 stories, 30% coverage |
Low-Rise High-Coverage (Option A)
Mid-Rise Medium-Coverage (Option B)
High-Rise Low-Coverage (Option C)
For FAR targets between 2.0 and 5.0, mid-rise at 50-65% coverage consistently outperforms both low-rise and high-rise strategies on combined measures of:
Adequate daylight and solar access are non-negotiable requirements for residential block design. Failure to achieve minimum daylight standards produces uninhabitable dwellings, legal liability, and unmarketable units. Apply these standards rigorously.
The solar envelope defines the maximum building volume on a site that will not cast shadows on neighboring properties beyond an agreed threshold. It is defined by:
At a given latitude, the length of shadow cast by a building varies with the sun's altitude angle:
To ensure direct sunlight reaches ground-level spaces (courtyards, streets, neighboring facades) for a target number of hours:
When generating a block design recommendation, present the following block specification template with all metrics filled in. Adapt the template to the specific typology and site conditions.
BLOCK SPECIFICATION
=====================================
Block ID: [identifier]
Typology: [from typology matrix]
Location / Context: [site description]
PLAN DIMENSIONS
Block width: [m]
Block length: [m]
Block perimeter: [m]
Block area: [m2]
BUILDING CONFIGURATION
Building depth: [m] (typically 12-18m)
Coverage ratio: [%]
Building footprint: [m2]
Number of floors: [stories]
Floor-to-floor: [m] (typically 3.0-3.5m residential, 4.0-4.5m ground floor)
Building height: [m]
Total GFA: [m2]
OPEN SPACE
Courtyard width: [m]
Courtyard area: [m2]
Open space ratio: [%]
DENSITY METRICS
FAR: [ratio]
Net density: [DU/ha]
Gross density: [DU/ha]
Dwelling units: [count]
Population: [persons]
DAYLIGHT PERFORMANCE
Min courtyard VSC: [%]
Daylight factor: [% average]
Shadow length (winter solstice noon): [m]
GROUND FLOOR
Active frontage: [% of street-facing perimeter]
Commercial area: [m2]
Entrance spacing: [m] (target every 8-12m)
PARKING
Strategy: [below-grade / podium / courtyard / on-street]
Spaces: [count]
Ratio: [spaces per unit]
SERVICING
Access: [rear lane / courtyard / internal road]
Waste collection: [strategy]
DESIGN NOTES
[Typology-specific notes, climate considerations,
special design treatments, variation strategy]
=====================================Provide the completed template together with a brief narrative explaining the design rationale, key trade-offs made, and how the block relates to the broader urban context (street network, adjacent blocks, public space framework).
For detailed typological specifications, precedent data, dimensional standards, and design checklists, consult the following reference documents within this skill:
Block Typologies Reference: block-typologies.md 12+ typologies with full specifications, dimensional plans, section descriptions, courtyard character, parking strategies, ground floor treatments, advantages/disadvantages, and 3-5 precedent projects per type.
Density Metrics Reference: density-metrics.md Complete measurement guide covering FAR/FSI/Plot Ratio, coverage ratios, net vs gross density, DU/ha, persons/ha, bedspaces/ha, habitable rooms/ha. Conversion tables and density profiles of 15+ exemplar neighborhoods worldwide from Barcelona Eixample to Freiburg Vauban.
FAR Calculations Reference: far-calculations.md Step-by-step worked examples for 5 site scenarios (single-use residential, mixed-use tower-podium, multi-block district, infill development, TOD with bonus FAR). GFA measurement conventions by jurisdiction (US BOMA, UK GIA/NIA, Singapore, Hong Kong). Bonus FAR mechanisms for affordable housing, green building, public amenity, and heritage transfer of development rights.
Urban Design Foundations: See the urban-design-foundations skill for core theorists, quantitative
rules of thumb, movement frameworks, and design quality criteria that provide the broader context
for block design decisions.
Urban Calculator: See the urban-calculator skill for Python scripts that compute density,
FAR, walkability, parking, green space, and block optimization metrics programmatically.
© 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/block-and-density 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.
Block And Density 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 |
|---|---|---|---|---|---|---|
| Block And Density this skillAbhinavbwj/Urban-Design-Skills-Claude | 132 | 1 repos | ~7.5k | Automated safety check: Pass | MIT | |
| SQL Optimizationgithub/awesome-copilot | 40k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Agent Performance Optimizerruvnet/ruflo | 74k | 2 repos | ~3.6k | Automated safety check: Pass | MIT | |
| Database Optimizerdavila7/claude-code-templates | 32k | 8 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Prompt Optimizeraffaan-m/ECC | 275k | 2 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Cost Optimizeruvnet/ruflo | 74k | 1 repos | ~997 | Automated safety check: Notes | MIT |
github/awesome-copilot
Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across all SQL databases (MySQL, PostgreSQL, SQL Server…
ruvnet/ruflo
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer
davila7/claude-code-templates
Expert database optimizer specializing in modern performance tuning, query optimization, and scalable architectures.
affaan-m/ECC
分析原始提示,识别意图和差距,匹配ECC组件(技能/命令/代理/钩子),并输出一个可直接粘贴的优化提示。仅提供咨询角色——绝不自行执行任务。触发时机:当用户说“优化提示”、“改进我的提示”、“如何编写提示”、“帮我优化这个指令”或明确要求提高提示质量时。中文等效表达同样触发:“优化prompt”、“改进prompt”、“怎么写prompt”、“帮我优化这个指令”。不触发时机:当用户希望直接执行任…
ruvnet/ruflo
Analyze token usage patterns and recommend cost optimizations with estimated savings
JuliusBrussee/caveman
Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.
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
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.
Abhinavbwj/Urban-Design-Skills-Claude
Conduct comprehensive multi-scale site analysis from regional to neighborhood to site scale.
Design urban blocks and optimize density using typological analysis, FAR calculations, and building configuration strategies. Block And Density is an agent skill from Abhinavbwj/Urban-Design-Skills-Claude. Design urban blocks and optimize density using typological analysis, FAR calculations, and building configuration strategies.
Block And Density fits situations like: the user asks about block dimensions; density calculations; FAR optimization; building footprint coverage.
Run `npx skills add Abhinavbwj/Urban-Design-Skills-Claude --skill block-and-density -a claude-code`. Or copy the skill folder (skills/block-and-density in Abhinavbwj/Urban-Design-Skills-Claude) into .claude/skills/block-and-density in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Abhinavbwj/Urban-Design-Skills-Claude --skill block-and-density -a codex`. Or copy the skill folder (skills/block-and-density in Abhinavbwj/Urban-Design-Skills-Claude) into .agents/skills/block-and-density 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 block-and-density -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/block-and-density, .gemini/skills/block-and-density, .github/skills/block-and-density and .opencode/skills/block-and-density in your project.
SKILL.md names no scripts, command-line tools or credentials: Block And Density is instructions for the agent only.
SKILL.md names 8 domains. As links in the text: itdp.org, brebookshop.com, nacto.org, uli.org, ajuntament.barcelona.cat, ura.gov.sg, london.gov.uk and gehlpeople.com. 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.
Block And Density is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 7.5k 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 27k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Block And Density: SQL Optimization (github/awesome-copilot, 40k stars), Agent Performance Optimizer (ruvnet/ruflo, 74k stars), Database Optimizer (davila7/claude-code-templates, 32k stars) and Prompt Optimizer (affaan-m/ECC, 275k 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.