AI Agent Skills

Command-line interface for Todoist.

Generate real-timestamp subtitle artifacts from final narration audio or merged video with a caption quality gate.

Perform a forensic company financial-statement review across earnings quality, health, fraud risk, and operating efficiency.

Turn creator performance data into a documented retrospective, grounded hypotheses, and reusable content learnings.

Screen equities with systematic value, momentum, quality, volatility, size, and growth factor frameworks.

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

narrow React component prop types to match live code paths

UmaDev: A coding agent that works like a real dev team, commanding the Claude Code / Codex / OpenCode you already use.

ccteam turns the coding agents you already run (Claude Code, Codex, Grok, Kimi…) into one team — any session can spawn, dispatch, and collect work from any vendor on any…

Formulate clear semantic abstractions from desired behavior before committing to implementation. Use when designing or revising terminology, entities, boundaries, respon…

An agent skill based on the "Details that make interfaces feel better" article

Measure portfolio returns, risk, drawdowns, benchmarks, rolling metrics, and strategy performance from approved data.

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…

Retrieve official Federal Reserve economic series for GDP, inflation, rates, employment, money supply, and volatility research.

Research a companys valuation, growth, profitability, balance sheet, competitive moat, and management quality.

Terminal-first, knowledge-grounded multi-agent software delivery pipeline: scope requirements, implement changes, run tests, and gate pull requests with deterministic QA…