mcpbeat Sign in

Grad Policy Streams Agent Skill

Apply Kingdon's multiple streams framework to analyze how problems, policies, and politics converge to open policy windows. Use this skill when the user needs to explain why certain policies get adopted while others don't, identify policy windows and entrepreneurial opportunities, or analyze the agenda-setting process in public policy — even if they say 'why did this policy pass now', 'policy window', or 'how do issues get on the agenda'.

10k tokens
context cost
the whole folder, loaded on every use
4
files
instructions only
0
copies elsewhere
how many repositories repackaged it
223
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/asgard-ai-platform/skills --skill grad-policy-streams

What comes with it

33 004 bytes besides the instruction
examples/sample_scenario.md
references/comparative-msf.md
references/policy-entrepreneurs.md

The instruction itself

12 sections, as written by the author

Multiple Streams Framework

Overview

Kingdon's multiple streams framework (1984) explains policy change through the convergence of three independent streams: problems, policies, and politics. When these streams couple — often catalyzed by a policy entrepreneur — a policy window opens, creating an opportunity for policy adoption.

When to Use

Trigger conditions:

  • Explaining why a particular policy was adopted at a particular time
  • Identifying windows of opportunity for policy advocacy
  • Analyzing the role of policy entrepreneurs in agenda-setting

When NOT to use:

  • When analyzing governance structures and multi-actor arrangements (use governance theory)
  • When studying rational-comprehensive policy analysis (use cost-benefit analysis)
  • When examining self-interested behavior of public officials (use public choice theory)

Assumptions

IRON LAW: Policy Change Requires Convergence of ALL THREE Streams

A solution without a recognized problem or political will remains just
an idea. The three streams flow independently:
1. PROBLEM STREAM: How conditions become recognized as problems
   (indicators, focusing events, feedback)
2. POLICY STREAM: The "primeval soup" of solutions seeking problems
   (technical feasibility, value compatibility, anticipation of constraints)
3. POLITICS STREAM: Political mood, organized interests, government
   turnover (elections, public sentiment shifts)
POLICY WINDOWS open when streams converge — they are brief and
close quickly. Policy entrepreneurs COUPLE the streams.

Methodology

Step 1: Analyze the Problem Stream

Identify how the issue became defined as a "problem": through indicators (data/statistics), focusing events (crises, disasters), or feedback from existing programs.

Step 2: Analyze the Policy Stream

Examine the available policy solutions: their technical feasibility, budgetary workability, value compatibility with the political community, and anticipation of future constraints.

Step 3: Analyze the Politics Stream

Assess the political mood (national mood, public opinion), organized political forces (interest groups, coalitions), and government composition (administration changes, legislative turnover).

Step 4: Identify Coupling and Windows

Determine whether and how the three streams converged. Identify the policy entrepreneur(s) who coupled the streams and the type of policy window (problem window vs political window).

Output Format

# Policy Streams Analysis: {Policy/Issue}

## Problem Stream
- How issue became a "problem": {indicators/focusing events/feedback}
- Problem definition: {how the problem is framed}
- Competing definitions: {alternative problem framings}

## Policy Stream
- Available solutions: {policy proposals in the "primeval soup"}
- Technical feasibility: {can it work?}
- Value compatibility: {does it fit political values?}
- Budgetary workability: {is it affordable?}

## Politics Stream
- National mood: {public sentiment direction}
- Organized forces: {interest group positions}
- Government composition: {who is in power, recent changes}

## Policy Window
- Window type: {problem window or political window}
- Coupling mechanism: {how streams converged}
- Policy entrepreneur: {who coupled the streams, with what resources}
- Window duration: {how long it stayed open}

## Outcome
{What was adopted, why, and what was left out}

Gotchas

  • Streams are NOT fully independent: While theoretically independent, in practice the streams influence each other. Policy entrepreneurs may strategically create problem definitions to match available solutions.
  • Retrospective bias: It's easier to identify stream convergence AFTER policy adoption. Predicting windows in real-time is much harder — many apparent windows close without action.
  • Policy entrepreneurs are key but underspecified: The framework relies heavily on policy entrepreneurs but provides limited guidance on who they are, where they come from, or what resources they need.
  • Cultural transferability: The framework was developed for the U.S. federal system. In parliamentary systems, coalition governments, or authoritarian regimes, the streams operate differently.
  • Not all policy change fits: Incremental policy changes, routine decisions, and administrative reforms may not require a "window" — the framework best explains non-incremental, agenda-setting policy change.

References

  • For policy entrepreneur strategies and resources, see references/policy-entrepreneurs.md
  • For MSF applications in comparative politics, see references/comparative-msf.md

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take asgard-ai-platform/grad-policy-streams from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.