agentleFS
Sign inStart free
OctagonAIOctagonAI/octagon-mcp-server/skills/octagon-analyst-master/SKILL.md

octagon-analyst-master

Skill147 starsChanged 6 months agoMITView on GitHub

Route broad company, sector, valuation, filings, transcript, and market data questions into the right Octagon workflow. Use when the user wants full-scope investment research or when multiple Octagon skills may be needed.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for broad investment research requests that span several analyst workflows.

    line 8
  2. Very specific:

    If the request is still broad after routing, use octagon-agent.

    line 24
  3. Distinctive:

    Use the live docs tools when the user asks about setup, available capabilities, or how Octagon works before starting analysis:

    line 28
  4. Very specific:

    Start with octagon-docs-search for discovery: Claude plugin, MCP server, available agents, or authentication

    line 30
  5. Very specific:

    Use octagon-docs-read for canonical context: Octagon Claude Plugin, Octagon MCP Server, Octagon Agents Guide, or How Octagon API Works

    line 31
  6. Distinctive:

    Prefer docs context over memory for installation, connector, authentication, and tool-surface questions

    line 32
  7. Distinctive:

    Start with a short investment takeaway

    line 54
  8. Distinctive:

    Call out missing context that would improve the next turn

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Octagon Analyst Master

Use this skill for broad investment research requests that span several analyst workflows.

When to use

  • The user wants a full company brief or investment memo
  • The request mixes filings, estimates, earnings, valuation, and market data
  • It is not obvious which single Octagon skill should be used first

Routing guide

  • Forward estimates and consensus expectations: analyst-estimates
  • Kalshi market reports or event history: prediction-markets-analysis
  • Earnings transcript and guidance analysis: earnings-call-analysis
  • Annual filing and risk review: sec-10k-analysis
  • Real-time pricing and market snapshot: stock-quote

If the request is still broad after routing, use octagon-agent.

Docs references

Use the live docs tools when the user asks about setup, available capabilities, or how Octagon works before starting analysis:

  • Start with octagon-docs-search for discovery: Claude plugin, MCP server, available agents, or authentication
  • Use octagon-docs-read for canonical context: Octagon Claude Plugin, Octagon MCP Server, Octagon Agents Guide, or How Octagon API Works
  • Prefer docs context over memory for installation, connector, authentication, and tool-surface questions

Default query pattern

Build an investment analyst brief on <COMPANY OR TICKER> covering business quality, latest performance, guidance, valuation context, and key near-term risks.

MCP call

{
  "server": "octagon-mcp",
  "toolName": "octagon-agent",
  "arguments": {
    "prompt": "Build an investment analyst brief on NVDA covering business quality, latest performance, guidance, valuation context, and key near-term risks."
  }
}

Output expectations

  • Start with a short investment takeaway
  • Break out the answer by business, financials, expectations, risks, and watch items
  • Call out missing context that would improve the next turn

Follow-up prompts

  • "Compare this company to its two closest public peers."
  • "Now focus only on valuation and forward expectations."
  • "Turn this into a long thesis and a short thesis."

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free