Skip to content
Back to search

agent37-skills-collection

Collection of useful Claude AI skills and commands

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/agent37-platform--agent37-skills-collection/badge.svg)](/listings/agent37-platform--agent37-skills-collection)

HTML

<a href="/listings/agent37-platform--agent37-skills-collection"><img src="/api/listings/agent37-platform--agent37-skills-collection/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 32 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "agent37-skills",
  3. "owner": {
  4. "name": "Agent 37"
  5. },
  6. "metadata": {
  7. "description": "A collection of Claude Code skills by Agent 37"
  8. },
  9. "plugins": [
  10. {
  11. "name": "yc-advisor",
  12. "source": "./plugins/yc-advisor",
  13. "description": "Provides access to Y Combinator's complete library of 434 curated startup resources including essays by Paul Graham, founder interviews, and startup school lectures.",
  14. "version": "1.0.0",
  15. "keywords": ["startup", "yc", "ycombinator", "founder", "entrepreneurship"]
  16. },
  17. {
  18. "name": "local-review",
  19. "source": "./plugins/local-review",
  20. "description": "Code review uncommitted local changes for bugs, security vulnerabilities, and CLAUDE.md compliance",
  21. "version": "1.0.0",
  22. "keywords": ["code-review", "git", "security", "bugs", "typescript"]
  23. },
  24. {
  25. "name": "generate-prompt-request",
  26. "source": "./plugins/generate-prompt-request",
  27. "description": "Generate a compact 'prompt request' one-pager that summarizes the current session for a pull request: every ask and decision folded into one User block, plus an Assistant summary of what was built.",
  28. "version": "1.0.0",
  29. "keywords": ["pull-request", "pr", "prompt", "summary", "session", "documentation"]
  30. }
  31. ]
  32. }
README.md · README · 44 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Agent 37 Skills Collection
  2. A collection of Claude Code plugins
  3. ## yc-advisor
  4. YC startup advice from 434 curated resources (Paul Graham essays, founder interviews, startup school).
  5. ```bash
  6. /plugin marketplace add agent37-platform/agent37-skills-collection
  7. /plugin install yc-advisor@agent37-skills
  8. ```
  9. This is a **skill** - automatically triggered when you ask about startups, fundraising, etc.
  10. You can interact with this live at https://www.agent37.com/yc
  11. ## local-review
  12. Code review for uncommitted local changes. Inspired by Anthropic's official `code-review` plugin which reviews PRs - this one reviews your local staged/unstaged changes before you commit.
  13. ```bash
  14. /plugin marketplace add agent37-platform/agent37-skills-collection
  15. /plugin install local-review@agent37-skills
  16. ```
  17. This is a **command** - invoke with `/local-review:local-review`
  18. Reviews for: bugs, security vulnerabilities (OWASP top 10), CLAUDE.md compliance, TypeScript issues. Filters false positives and groups by severity.
  19. ## generate-prompt-request
  20. Summarize the current session into a compact "prompt request" one-pager for a pull request: every ask and decision folded into one `User:` block, plus an `Assistant:` block summarizing what was built.
  21. ```bash
  22. /plugin marketplace add agent37-platform/agent37-skills-collection
  23. /plugin install generate-prompt-request@agent37-skills
  24. ```
  25. This is a **skill** - triggered when you ask to "generate a prompt request", or automatically when opening a PR. Wire it into a repo's AGENTS.md / CLAUDE.md with a line like "When opening a PR, invoke the generate-prompt-request skill and include its output in the PR body." Output is inline markdown, ready to paste into a PR.
  26. ## License
  27. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.