Skip to content
Agentmart
Submit a tool

lynch

Score a stock with the lynch playbook.

Skill by elliottrjacobs

IndexedMIT★ 3
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/elliottrjacobs-lynch

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Score a stock with the lynch playbook. Use for 'lynch score', 'Peter Lynch check', 'PEG ratio', or 'which Lynch category is this stock'. Gives an evidence scorecard, never a mechanical buy or sell verdict.

Use cases: finance

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/lynch

What's inside

Skill name
lynch
Description
Score a stock with the lynch playbook. Use for 'lynch score', 'Peter Lynch check', 'PEG ratio', or 'which Lynch category is this stock'. Gives an evidence scorecard, never a mechanical buy or sell verdict.
License
MIT
Metadata
args: <subject> · tier: balanced · group: playbooks · invocation: implicit · report-kind: score · default-context: none
Instructions
11 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Lynch

Follow the skill skeleton in AGENTS.md.

Apply the lynch playbook from fo score. Explain each judgment criterion using evidence, distinguish unknown from fail, and examine sensitivity to assumptions. The mechanical score never writes the verdict. Journal only when the user requests a recommendation; otherwise provide a scorecard for diligence.

Run the commands declared in metadata with --json. Use fo start for the report path and prior. Include Evidence, Analysis, Data gaps, and Next actions. Include What changed when a prior exists. Cite applicable corrections and explain how the proposed action complies.

Close the report with: Reply with corrections in your next task.

From elliottrjacobs/family-office, MIT.

More from elliottrjacobs/family-office

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Oct 15, 2026 (12 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from elliottrjacobs

Cite this page

lynch skill. Agent Mart. https://agentmart.dev/skills/elliottrjacobs-lynch (last updated 2026-10-24)