sec-proxy-analysis
Analyze proxy statements (DEF 14A) to extract executive compensation, governance information, and shareholder voting matters using Octagon MCP. Use when researching CEO pay, board composition, say-on-pay votes, and corporate governance practices.
What this skill does
# SEC Proxy Analysis
Analyze proxy statements (DEF 14A) to extract executive compensation and governance information for public companies using the Octagon MCP server.
## Prerequisites
Ensure Octagon MCP is configured in your AI agent (Cursor, Claude Desktop, Windsurf, etc.). See [references/mcp-setup.md](references/mcp-setup.md) for installation instructions.
## Workflow
### 1. Identify Analysis Parameters
Determine the following before querying:
- **Ticker**: Stock symbol (e.g., AAPL, MSFT, GOOGL)
- **Focus Area** (optional): Compensation, governance, proposals
- **Comparison** (optional): Peer companies, prior years
### 2. Execute Query via Octagon MCP
Use the `octagon-agent` tool with a natural language prompt:
```
Extract executive compensation details and governance information from <TICKER>'s latest proxy statement.
```
**MCP Call Format:**
```json
{
"server": "octagon-mcp",
"toolName": "octagon-agent",
"arguments": {
"prompt": "Extract executive compensation details and governance information from TSLA's latest proxy statement."
}
}
```
### 3. Expected Output
The agent returns structured proxy analysis including:
**Director Compensation:**
- Stock awards valued at over $3 billion collectively
- Comparison to peer compensation levels
**Governance Framework:**
- Board standards for employees, officers, and directors
- Governance policies and oversight
**Voting Matters:**
- Non-binding votes on executive compensation frequency
- Director compensation disclosures
**Data Sources**: octagon-companies-agent, octagon-sec-agent, octagon-web-search-agent
### 4. Interpret Results
See [references/interpreting-results.md](references/interpreting-results.md) for guidance on:
- Understanding compensation structures
- Evaluating governance practices
- Analyzing shareholder proposals
- Comparing to peer companies
## Example Queries
**Full Proxy Analysis:**
```
Extract executive compensation details and governance information from TSLA's latest proxy statement.
```
**CEO Compensation Focus:**
```
What is the total compensation for AAPL's CEO in the latest proxy statement?
```
**Board Composition:**
```
Analyze the board of directors composition and independence from MSFT's latest DEF 14A.
```
**Say-on-Pay Results:**
```
What were the say-on-pay voting results for AMZN in their latest proxy?
```
**Peer Comparison:**
```
Compare executive compensation between GOOGL and META based on their latest proxy statements.
```
**Shareholder Proposals:**
```
What shareholder proposals were included in JPM's latest proxy statement and how did they fare?
```
## Proxy Statement Components
### Executive Compensation (Item 402)
| Component | Description |
|-----------|-------------|
| Summary Compensation Table | Total pay for Named Executive Officers (NEOs) |
| Salary | Base salary amounts |
| Bonus | Cash bonus payments |
| Stock Awards | Equity grants at grant date fair value |
| Option Awards | Stock options at grant date fair value |
| Non-Equity Incentive | Performance-based cash compensation |
| Pension Value | Change in pension/deferred compensation |
| All Other Compensation | Perks, 401(k) match, insurance |
### CEO Pay Ratio
| Element | Description |
|---------|-------------|
| CEO Total Compensation | All-in CEO pay |
| Median Employee Pay | Median worker compensation |
| Pay Ratio | CEO pay / median employee pay |
### Compensation Discussion & Analysis (CD&A)
| Section | Content |
|---------|---------|
| Philosophy | Compensation objectives and strategy |
| Pay Mix | Balance of fixed vs. variable pay |
| Performance Metrics | Goals used for incentive pay |
| Peer Group | Companies used for benchmarking |
| Decisions | Rationale for pay decisions |
### Corporate Governance
| Area | Details |
|------|---------|
| Board Composition | Directors, independence, diversity |
| Committees | Audit, Compensation, Nominating |
| Leadership Structure | Chair/CEO separation, lead director |
| Risk Oversight | Board role in risk management |
| Shareholder Rights | Voting standards, proxy access |
### Shareholder Proposals
| Type | Common Topics |
|------|---------------|
| Governance | Board declassification, majority voting |
| Environmental | Climate disclosure, emissions targets |
| Social | Human rights, DEI reporting |
| Compensation | Pay for performance, clawbacks |
## Compensation Analysis
### Pay Components Breakdown
| Component | Typical Range | What to Look For |
|-----------|---------------|------------------|
| Base Salary | 10-20% | Stability, changes |
| Cash Bonus | 15-25% | Metrics, achievement |
| Stock Awards | 40-60% | Vesting, performance |
| Options | 5-15% | Strike price, term |
| Other | 1-5% | Perks, benefits |
### Pay-for-Performance Alignment
| Metric | Strong Alignment | Weak Alignment |
|--------|------------------|----------------|
| TSR Correlation | Pay tracks returns | Pay disconnected |
| Metric Rigor | Challenging targets | Easy thresholds |
| Vesting | Performance-based | Time-based only |
| Peer Rank | Median position | Outlier high |
### Red Flags in Compensation
1. **Excessive perks** - Private jets, security, housing
2. **Guaranteed bonuses** - No performance link
3. **Option repricing** - Underwater options reset
4. **Pension spiking** - Inflated pension values
5. **Golden parachutes** - Excessive change-in-control pay
6. **Tax gross-ups** - Company pays executive taxes
## Governance Assessment
### Board Quality Indicators
| Factor | Strong Governance | Weak Governance |
|--------|-------------------|-----------------|
| Independence | >75% independent | <50% independent |
| Diversity | Diverse backgrounds | Homogeneous |
| Tenure | Balanced mix | All long-tenured |
| Overboarding | Limited seats | Directors overcommitted |
| Attendance | >90% average | Low attendance |
### Committee Structure
| Committee | Key Oversight | Best Practices |
|-----------|---------------|----------------|
| Audit | Financials, controls | All independent, financial experts |
| Compensation | Executive pay | All independent, no interlocks |
| Nominating | Board composition | Independent, clear criteria |
| Risk | Enterprise risk | Defined charter, regular meetings |
### Shareholder Rights
| Right | Shareholder-Friendly | Concern |
|-------|---------------------|---------|
| Voting Standard | Majority voting | Plurality only |
| Proxy Access | Available | Not available |
| Special Meetings | Low threshold | High/no threshold |
| Written Consent | Allowed | Prohibited |
| Dual Class | Single class | Multi-class voting |
## Voting Analysis
### Say-on-Pay Voting
| Support Level | Interpretation |
|---------------|----------------|
| >90% | Strong approval |
| 70-90% | Acceptable |
| 50-70% | Concerns raised |
| <50% | Failed - action required |
### Director Elections
| Support Level | Interpretation |
|---------------|----------------|
| >95% | Strong support |
| 80-95% | Normal range |
| <80% | Significant opposition |
| <50% | Failed (if majority vote) |
### Shareholder Proposals
| Support Level | Interpretation |
|---------------|----------------|
| >50% | Passed - expect action |
| 30-50% | Significant support |
| 20-30% | Moderate interest |
| <20% | Limited support |
## Analysis Tips
1. **Track trends**: Compare compensation over 3-5 years, not just one year.
2. **Read the CD&A**: Narrative explains rationale behind numbers.
3. **Check peer group**: Ensure peers are truly comparable.
4. **Note changes**: New compensation elements or governance provisions.
5. **Follow the votes**: Declining support signals concerns.
6. **Review related transactions**: Conflicts of interest disclosed.
## Use Cases
- **Investment analysis**: Assess management alignment with shareholders
- **Governance screening**: Evaluate board quality and practices
- **Activist research**: Identify governance improvement opportunities
- **Compensation benchmarking**: Compare pay across companies
- **ESG analysis*Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.