Search the registry

Reproduce a reported bug, fix it, and add a regression test.

Root-causes a failing test or bug and proposes a minimal fix.

Bump dependencies, run the test suite, and open a PR if green.

Plan, implement, and test a new feature end to end.

Neon

1.0.0

Neon

MCP

Serverless Postgres with branch-based migrations — the agent tests migrations on an instant copy-on-write branch before applying.

Playwright

1.0.0

Microsoft

MCP

Drive a real browser — navigate, click, fill forms, screenshot, and run plain-English smoke tests.

Designs, tests, and refines prompts for LLM features.

Safely refactor a module behind its existing tests.

Find under-tested code and add the highest-value missing tests.

Writes focused unit and integration tests for existing code.

Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

Use when performing security research, red-teaming, or threat modeling. 753+ structured cybersecurity skills mapped to MITRE ATT&CK tactics and techniques.

Exploratory QA of web apps: find bugs, evidence, reports.

Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. Use when you need reproducible quality scoring for `skills/*/SKILL.md`, want to gate merges with a score threshold (for example 90+), or need concrete improvement items for low-scoring skills. Works across projects via --project-root.

Use when a Hermes Kanban worker wants to run Codex CLI as an isolated implementation lane while Hermes keeps ownership of task lifecycle, reconciliation, testing, and handoff.

Statistical arbitrage tool for identifying and analyzing pair trading opportunities. Detects cointegrated stock pairs within sectors, analyzes spread behavior, calculates z-scores, and provides entry/exit recommendations for market-neutral strategies. Use when user requests pair trading opportunities, statistical arbitrage screening, mean-reversion strategies, or market-neutral portfolio construction. Supports correlation analysis, cointegration testing, and spread backtesting.

Design new Claude skills from structured idea specifications. Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt that creates a complete skill directory (SKILL.md, references, scripts, tests) following repository conventions.

TDD: enforce RED-GREEN-REFACTOR, tests before code.

thirdweb

1.0.0

thirdweb

MCP

Deploy and interact with smart contracts across EVM chains. Contract deploys are irreversible and cost gas — test on a testnet first.