political-science-analysis
Skill30 starsChanged 9 months agoApache-2.0View on GitHub
Apply comparative politics, political behavior, and policy analysis frameworks to European Parliament data
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈10
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Account for Institutional Context: Consider EP's unique features: multilingual deliberation, rotating presidency influence, co-decision …
- Distinctive: line 28
Control for Confounders: When analyzing voting behavior, control for national party discipline, political group whip strength, salience of …
- Distinctive: line 33
Attribution: Always cite European Parliament Open Data Portal as the authoritative data source
- Distinctive: line 68
Ecological Fallacy: Do NOT infer individual MEP positions from political group averages — always check individual roll-call votes
- Distinctive: line 69
Selection Bias on Roll-Calls: Do NOT treat roll-call votes as representative of all EP votes — they are a biased sample (requested …
- Distinctive: line 70
Ignoring Absences: Do NOT exclude abstentions and absences from analysis — they carry political meaning in EP (strategic abstention is …
- Distinctive: line 71
National Party Conflation: Do NOT assume all MEPs from a country share positions — national party affiliation within political groups is …
- Distinctive: line 72
Static Analysis: Do NOT analyze EP voting without accounting for temporal dynamics — political group composition changes within and across …
- Distinctive: line 73
Monocausal Explanations: Do NOT attribute voting patterns to a single factor — EP voting is shaped by ideology, nationality, committee …
- Distinctive: line 74
Ignoring Non-Legislative Work: Do NOT focus exclusively on plenary votes — committee work, written questions, and reports reveal different …
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Political Science Analysis Skill
Context
This skill applies when:
- Analyzing MEP voting behavior patterns across 27 EU member states
- Studying political group cohesion and fragmentation in the European Parliament
- Evaluating EU legislative process dynamics (ordinary legislative procedure, consent, consultation)
- Performing comparative analysis of national delegation voting within transnational political groups
- Assessing policy positions using roll-call vote data from EP plenary sessions
- Studying coalition-building patterns between political groups (EPP, S&D, Renew, Greens/EFA, ECR, ID, The Left, NI)
- Analyzing rapporteur assignment patterns and committee influence
- Tracking political group switching and MEP mobility
This skill is grounded in the European Parliament MCP Server's access to EP Open Data Portal datasets and aligns with Hack23 ISMS Secure Development Policy for data integrity.
Rules
- Use Established Frameworks: Apply recognized political science methodologies — Hix-Noury-Roland spatial models, NOMINATE-style scaling for EP, Cohesion Index (Agreement Index) for political groups
- Distinguish Data Levels: Separate individual MEP votes, national delegation patterns, and political group aggregates — never conflate levels of analysis
- Account for Institutional Context: Consider EP's unique features: multilingual deliberation, rotating presidency influence, co-decision with Council, and committee gatekeeping power
- Control for Confounders: When analyzing voting behavior, control for national party discipline, political group whip strength, salience of policy area, and legislative procedure type
- Temporal Awareness: Respect legislative term boundaries (EP5–EP10), mid-term political group realignments, and enlargement effects (EU-15 → EU-27)
- Use EP-Specific Terminology: Reference rapporteurs (not sponsors), political groups (not parties), plenary (not floor), trilogue (not conference committee)
- Validate Against Multiple Sources: Cross-reference MCP Server data with VoteWatch Europe, EP Think Tank publications, and official EP roll-call records
- GDPR Compliance: MEP voting records are public data under EU transparency rules, but personal contact data requires GDPR-compliant handling per Hack23 Privacy Policy
- Attribution: Always cite European Parliament Open Data Portal as the authoritative data source
- Quantitative Rigor: Report confidence intervals, effect sizes, and sample sizes when presenting statistical findings on voting patterns
Examples
Analyzing Political Group Cohesion
Use the EP MCP Server's plenary vote data to calculate the Agreement Index (AI)
for each political group on environmental legislation in EP10:
- AI = (max(Yes, No, Abstain) - 0.5 * (votes - max(Yes, No, Abstain))) / votes
- Compare cohesion across policy domains (environment vs. economic affairs)
- Identify national delegations that deviate most from group line
- Control for vote salience using roll-call request patternsComparative National Delegation Analysis
Compare Swedish MEP voting patterns across political groups:
- Map Swedish national parties to EP political groups (S → S&D, M → EPP, etc.)
- Calculate loyalty scores: how often Swedish MEPs vote with their group majority
- Identify policy areas where national interest overrides group discipline
- Use MCP Server tools: get_meps (country filter), get_voting_recordsLegislative Procedure Analysis
Track legislative outcomes through the ordinary legislative procedure:
- Use track_legislation tool to identify dossiers by policy area
- Analyze first-reading agreements vs. second-reading/conciliation outcomes
- Study rapporteur influence: compare committee vote to plenary vote alignment
- Assess EP vs. Council bargaining success rates by policy domainAnti-Patterns
- Ecological Fallacy: Do NOT infer individual MEP positions from political group averages — always check individual roll-call votes
- Selection Bias on Roll-Calls: Do NOT treat roll-call votes as representative of all EP votes — they are a biased sample (requested strategically by political groups)
- Ignoring Absences: Do NOT exclude abstentions and absences from analysis — they carry political meaning in EP (strategic abstention is common)
- National Party Conflation: Do NOT assume all MEPs from a country share positions — national party affiliation within political groups is the key unit
- Static Analysis: Do NOT analyze EP voting without accounting for temporal dynamics — political group composition changes within and across legislative terms
- Monocausal Explanations: Do NOT attribute voting patterns to a single factor — EP voting is shaped by ideology, nationality, committee membership, rapporteur relationships, and trilogue outcomes simultaneously
- Ignoring Non-Legislative Work: Do NOT focus exclusively on plenary votes — committee work, written questions, and reports reveal different dimensions of MEP activity
In this repository41 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- ai-development-governanceSkill
- ai-governanceSkill
- architecture-documentationSkill
- aws-security-architectureSkill
- behavioral-analysisSkill
- business-model-canvasSkill
- c4-architecture-documentationSkill
- code-quality-excellenceSkill
- compliance-frameworksSkill
- contribution-guidelinesSkill
- data-science-for-intelligenceSkill
- documentation-standardsSkill
- electoral-analysisSkill
- european-parliament-apiSkill
- european-political-systemSkill
- gdpr-complianceSkill
- github-actions-workflowsSkill
- github-agentic-workflowsSkill
- incident-responseSkill
- intelligence-analysis-techniquesSkill
- isms-complianceSkill
- legislative-monitoringSkill
- mcp-gateway-configurationSkill
- mcp-gateway-securitySkill
- mcp-server-developmentSkill
- open-source-governanceSkill
- osint-methodologiesSkill
- performance-optimizationSkill
- risk-assessment-frameworksSkill
- secrets-managementSkill
- secure-code-reviewSkill
- secure-development-lifecycleSkill
- security-by-designSkill
- seo-best-practicesSkill
- strategic-communication-analysisSkill
- testing-mcp-toolsSkill
- testing-strategySkill
- threat-modeling-frameworkSkill
- typescript-strict-patternsSkill
- vulnerability-managementSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

