Is the City Analysis Workflow skill free?

Yes. The skill itself is free from sgarcese/Civic-Analytics-Agent-Workflow-Claude-Skill. SkillProof publishes the install command and an independent test verdict at no cost.

How do I install City Analysis Workflow?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use City Analysis Workflow with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

City Analysis Workflow

Boston civic data analysis via a 5-phase framework and city open-data MCPs

by sgarcese · sgarcese/Civic-Analytics-Agent-Workflow-Claude-Skill

Tested · Didn't pass

Read why it failed Download source ↗

Test report

Verdict: Tested · Didn't pass
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 4640537

A five-phase Boston civic-analysis orchestrator whose headline value, querying live Boston/SF/Seattle/DC open data, depends on four external MCP servers that are not bundled and were not available, so the core analytical capability could not be measured against a baseline. The methodology files (problem framing, memo audience/format tables, a data-story arc) are well structured but amount to generic consulting guidance without the data layer. The install runs verbatim, but the SKILL references TEMPLATES.md while the actual file is named TEMPLATES.mdv, and it points to /mnt/skills/public paths that only exist inside Anthropic's own environment. It works as a prompt framework, but the data-driven analysis it promises requires substantial MCP setup first.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 4/5
Output vs. baseline 4/10
Docs & honesty 3/5

What City Analysis Workflow does

A master orchestrator skill for City of Boston policy analysis that routes across five phases (frame, analyze, communicate, benchmark, perform) using methodologies from Bloomberg, J-PAL, and GovLab. Its core capability is querying live Boston, San Francisco, Seattle, and DC open data through external MCP servers; triggers on civic and government requests like 311 analysis, equity questions, policy memos, and cross-city comparisons.

How to install City Analysis Workflow

git clone https://github.com/sgarcese/Civic-Analytics-Agent-Workflow-Claude-Skill.git
mkdir -p ~/.claude/skills/city-analysis-workflow
cd Civic-Analytics-Agent-Workflow-Claude-Skill && cp -r ./* ~/.claude/skills/city-analysis-workflow/

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger City Analysis Workflow

/city-analysis-workflow Boston civic data analysis via a 5-phase framework and city open-data MCPs

It also activates on plain-language prompts like these:

analyze Boston 311 response times broken down by neighborhood
write a policy memo comparing Boston and Seattle on housing
what does the open data show about equity in city services

Frequently asked questions

Is the City Analysis Workflow skill free?: Yes. The skill itself is free from sgarcese/Civic-Analytics-Agent-Workflow-Claude-Skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does City Analysis Workflow work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Tested · Didn't pass. A five-phase Boston civic-analysis orchestrator whose headline value, querying live Boston/SF/Seattle/DC open data, depends on four external MCP servers that are not bundled and were not available, so the core analytical capability could not be measured against a baseline. The methodology files (problem framing, memo audience/format tables, a data-story arc) are well structured but amount to generic consulting guidance without the data layer. The install runs verbatim, but the SKILL references TEMPLATES.md while the actual file is named TEMPLATES.mdv, and it points to /mnt/skills/public paths that only exist inside Anthropic's own environment. It works as a prompt framework, but the data-driven analysis it promises requires substantial MCP setup first.
How do I install City Analysis Workflow?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use City Analysis Workflow with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.