AI Agent Skills

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thr…

A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS). Security-first, phase-aware engineering dis…

React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.

Complete and link income statement, balance sheet, and cash flow statement model templates with formulas and checks.

Review portfolio-company financial packages, flag variance to plan, and prepare monitored KPI summaries.

Run tests using Jest & Puppeteer 🎪✨

Repository analysis, pull request review, issue triage, and release workflow automation.

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove th…

Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plu…

Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a cha…

Use when user wants to create a GitHub issue for the current repository. Must read and follow the repository's issue template format.

Audit concentration, factor exposure, correlation, liquidity, and stress-test risks in an existing portfolio.

Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the directories the branc…

Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger, escalation when fixes st…

The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence…

A Claude/Codex skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice.