claudecodex

civic-skills-localize-skill

Fits a generalized skill to one organization writes its local values back in and produces an ordinary, self-contained skill that runs without a context file. Works out what it can from the organization's own data and public sources, and asks a person only what no source can answer, at the precision the value actually needs. Confirms every machine-consumed value before shipping, because a plausible wrong value is worse than a blank one.

2 on GitHubby AI Lab for Cities at Harvardupdated 22 days agoAI Tools
/

Plugin civic-skills-localize-skill from marketplace civic-skill-exchange in AI-Lab-for-Cities-at-Harvard/civic-skill-exchange. Commands read from the repo's manifest — 22 days ago.

What it installs

Skills (1)

  • localize-skill

    Fits a generalized skill to one organization writes its local values back in and produces an ordinary, self-contained skill that runs without a context file. Works out what it can from the organization's own data and public sources, and asks a person only what no source can answer, at the precision

View source on GitHub

More from AI-Lab-for-Cities-at-Harvard/civic-skill-exchange

All 7 plugins →

Housing dashboards, refreshes and briefs for any U.S. city or county (a state works too, with fewer comparisons) from Census ACS, BLS and HUD open data: demand and tenure, construction costs and labor, and federally assisted housing, compared with the surrounding region, state and nation.

3 skills · 5 MCP servers

2

Separates a skill written for one organization into two things a portable generalized skill, and a context file holding every value that was specific to that place. Records how far the skill was generalized to travel, since that is what decides which values are local at all. Reports what it was unsure about rather than guessing. Produces drafts for the author to check; decides nothing and publishes nothing.

1 skill

2

Rewrites a government notice template into plain language at a target reading level, preserving every legally required element. Works on templates, not on filled notices containing a specific person's information. Produces a draft for human review; it does not approve or send anything.

1 skill

2

This is the original civic analytics workflow. Orchestrator for local government policy analysis and civic innovation. ALWAYS use for any request involving open government data, city, county or town services, neighborhood or ward equity, public policy, government performance, 311 and service request analysis, housing, safety or transportation — even if the user hasn't asked for a 'full analysis'. Routes between five sub-skills: problem framing (Bloomberg-inspired), policy analysis (J-PAL-inspired), communication (GovLab/InnovateUS-inspired), peer benchmarking, and performance management (Results for America / PerformanceStat). Triggers include: 'full analysis', 'policy brief', 'data-driven recommendation', 'service improvement project', 'investigate [issue]', 'compare us to peer cities', 'peer counties', 'similar towns', 'what does the data show', 'help me write a memo about', or any request combining problem definition, data analysis and communication for government or civic purposes.

1 skill

2

Plan de arborización urbana en tres fases a partir del portal de datos abiertos de una ciudad y su conector OpenContext, priorizando lo que el conector entrega directamente. Produce un inventario de los datos del portal útiles para una gestión basada en la naturaleza, con sus vacíos; un ranking de oportunidad de siembra por distrito, comuna o barrio que combina déficit de árboles, cobertura de copa y vulnerabilidad; y una propuesta de especies por barrio basada en el censo arbóreo de la propia ciudad. Úsalo cuando un equipo de medio ambiente o planeación pregunte qué datos abiertos sirven para enverdecer la ciudad, dónde sembrar primero, qué barrios tienen poca sombra y muchas personas mayores, o qué especies sembrar en un barrio, aunque no mencione el conector.

1 skill

2

Supports problem identification, the first phase of performance management. Runs a broad scan for potential issues a state or city agency might focus on, drawing on the jurisdiction's performance data through an OpenContext MCP connector, local media coverage, public testimony, and social media where a tool can reach it. Covers state labor and workforce, state health and human services, city 311, emergency dispatch (CAD), and city operations. Produces a ranked list of candidate problems for agency leaders and performance officers, each tagged by evidence source, shape (acute/chronic), horizon, degree of control, and dominant cost, with a verified/partial/unverified confidence flag, plus a second list of adjacent problems where the agency has leverage but no formal remit. Use when someone asks what a state or city agency should prioritize, where to target process improvement, what data or local coverage shows about emerging problems, or for a priority scan or focus areas.

1 skill

2

Similar plugins

Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.

2 skills · 2 commands · 2 agents · 1 MCP server

f/prompts.chat 177,027

Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.

1 skill

headroomlabs-ai/headroom 79,508

mempalace

claudecodex

AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.

3 skills · 6 commands · 1 MCP server · hooks

MemPalace/mempalace 60,536

Harness Adobe's creative AI-powered tools to edit images, automate design workflows, and bring creative visions to life — from background removal to vectorization and professional retouching.

26 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

ifixai

claudecodex

Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).

1 skill · hooks

ifixai-ai/iFixAi 45,158

ZoomInfo

claudecodex

Search companies and contacts, enrich leads, find lookalikes, and get AI-ranked contact recommendations. Pre-built skills chain multiple ZoomInfo tools into complete B2B sales workflows.

35 skills · 1 MCP server

anthropics/knowledge-work-plugins 35,601

Maintain civic-skills-localize-skill?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins7 plugins