stock-grades
Retrieve the latest stock grades and ratings from top analysts and financial institutions using Octagon MCP. Use when tracking analyst upgrades, downgrades, rating changes, and institutional sentiment over time.
What this skill does
# Stock Grades
Retrieve analyst grades, ratings, and rating changes from top financial institutions 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 the Stock
Determine the ticker symbol for the company you want to analyze (e.g., AAPL, MSFT, GOOGL).
### 2. Execute Query via Octagon MCP
Use the `octagon-agent` tool with a natural language prompt:
```
Get the latest stock grades for the symbol <TICKER> from top analysts and financial institutions.
```
**MCP Call Format:**
```json
{
"server": "octagon-mcp",
"toolName": "octagon-agent",
"arguments": {
"prompt": "Get the latest stock grades for the symbol AAPL from top analysts and financial institutions."
}
}
```
### 3. Expected Output
The agent returns analyst rating history including:
- **Rating Actions**: Upgrades, downgrades, maintains
- **Analyst/Institution**: Source of the rating
- **Previous Rating**: Prior grade
- **New Rating**: Current grade
- **Date**: When the rating was issued
**Example**: Maxim Group upgraded from Hold to Buy on 2026-01-30
**Data Sources**: octagon-stock-data-agent
### 4. Interpret Results
See [references/interpreting-results.md](references/interpreting-results.md) for guidance on:
- Understanding rating scales
- Analyzing upgrade/downgrade trends
- Evaluating analyst credibility
- Tracking sentiment changes
## Example Queries
**Basic Query:**
```
Get the latest stock grades for the symbol AAPL from top analysts and financial institutions.
```
**Recent Changes:**
```
What are the most recent analyst rating changes for TSLA?
```
**Upgrade Focus:**
```
Show me recent upgrades for NVDA from major investment banks.
```
**Historical View:**
```
What is the history of analyst ratings for MSFT over the past year?
```
**Specific Institution:**
```
What is Goldman Sachs' current rating on AMZN?
```
## Understanding Rating Scales
### Common Rating Systems
| Rating Level | Common Terms |
|--------------|--------------|
| Strong Buy | Buy, Overweight, Outperform |
| Buy | Accumulate, Add, Positive |
| Hold | Neutral, Market Perform, Equal-Weight |
| Sell | Underweight, Underperform, Reduce |
| Strong Sell | Sell, Avoid |
### Rating Equivalencies
| Bank A | Bank B | Bank C | Meaning |
|--------|--------|--------|---------|
| Overweight | Buy | Outperform | Bullish |
| Equal-Weight | Hold | Market Perform | Neutral |
| Underweight | Sell | Underperform | Bearish |
## Rating Actions
### Action Types
| Action | Description |
|--------|-------------|
| Upgrade | Rating improved (e.g., Hold → Buy) |
| Downgrade | Rating lowered (e.g., Buy → Hold) |
| Maintain | Rating unchanged (reaffirmed) |
| Initiate | New coverage started |
| Reiterate | Rating repeated with emphasis |
| Resume | Coverage restarted |
| Suspend | Coverage temporarily halted |
### Significance Ranking
| Action | Impact |
|--------|--------|
| Upgrade from Sell | Highest positive |
| Upgrade from Hold | Significant positive |
| Initiate at Buy | Positive |
| Maintain at Buy | Stable positive |
| Downgrade to Hold | Negative signal |
| Downgrade to Sell | Highest negative |
## Analyst Credibility
### Factors to Consider
| Factor | Description |
|--------|-------------|
| Track Record | Historical accuracy |
| Institution Tier | Major bank vs. boutique |
| Sector Expertise | Specialization |
| Coverage Length | Experience with stock |
| Independence | Conflicts of interest |
### Institution Tiers
| Tier | Examples |
|------|----------|
| Bulge Bracket | Goldman Sachs, Morgan Stanley, JPMorgan |
| Major Banks | Bank of America, Citi, UBS |
| Boutiques | Wedbush, Piper Sandler, Needham |
| Independent | Morningstar, CFRA |
## Trend Analysis
### Sentiment Indicators
| Pattern | Interpretation |
|---------|----------------|
| Multiple upgrades | Improving sentiment |
| Multiple downgrades | Deteriorating outlook |
| Mixed actions | Uncertainty/debate |
| All maintains | Stable consensus |
### Momentum Signals
| Signal | Meaning |
|--------|---------|
| Upgrade cluster | Catalyst or breakout |
| Downgrade cluster | Concerns emerging |
| Initiation wave | Growing interest |
| Coverage drops | Reduced attention |
## Rating Distribution
### Consensus Rating
| Distribution | Interpretation |
|--------------|----------------|
| Mostly Buy | Strong bullish consensus |
| Mostly Hold | Neutral/wait-and-see |
| Mostly Sell | Bearish consensus |
| Mixed | Divergent views |
### Rating Counts
| Metric | What It Shows |
|--------|---------------|
| Buy % | Bullish proportion |
| Hold % | Neutral proportion |
| Sell % | Bearish proportion |
| Total Analysts | Coverage level |
## Timing Considerations
### When Ratings Change
| Catalyst | Typical Timing |
|----------|----------------|
| Earnings | Day of or day after |
| Guidance | Within 24-48 hours |
| Product News | Same day |
| Macro Events | As needed |
| Sector Rotation | Periodic |
### Staleness
| Age | Reliability |
|-----|-------------|
| <1 month | Current view |
| 1-3 months | Reasonably current |
| 3-6 months | May be outdated |
| >6 months | Likely stale |
## Common Use Cases
### Sentiment Check
```
What is the current analyst sentiment on AAPL?
```
### Change Monitoring
```
Have any analysts upgraded or downgraded TSLA recently?
```
### Catalyst Research
```
Why did analysts upgrade NVDA last week?
```
### Consensus View
```
What percentage of analysts rate MSFT as a buy?
```
### Historical Tracking
```
How has analyst sentiment on META changed over the past year?
```
## Analysis Tips
1. **Weight by institution**: Major banks carry more weight.
2. **Track changes, not just ratings**: Upgrades/downgrades signal shifts.
3. **Consider timing**: Post-earnings ratings are most current.
4. **Look for clusters**: Multiple changes = significant.
5. **Check track record**: Some analysts are more accurate.
6. **Combine with targets**: Rating + price target = complete view.
## Integration with Other Skills
| Skill | Combined Use |
|-------|--------------|
| price-target-consensus | Ratings + price targets |
| analyst-estimates | Ratings + earnings expectations |
| stock-quote | Rating changes + price reaction |
| stock-performance | Historical ratings vs. performance |
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.