Guides an AI agent to pause and ask clarifying questions when a request has ambiguous objectives, unclear scope, or missing constraints.
A collection of 11 skills for smart contract security across Algorand, Cairo, Cosmos, Solana, Substrate, and TON.
Interprets Culture Index behavioral assessments for individuals and teams.
A structured analysis skill for the pre-audit phase of code review.
Searches and extracts data from Burp Suite project files (.
Runs security-focused differential reviews on PRs, commits, and diffs.
Detects timing side-channel vulnerabilities in cryptographic code across 12 languages.
Adds deep knowledge of the DWARF debug format (versions 3-5) to an agent.
Diagnoses and fixes connectivity failures between the Claude in Chrome MCP extension and Claude Code CLI on macOS.
Analyzes smart contract codebases to map all state-changing entry points for security audits.
Configures Python projects with uv, ruff, and ty — the modern replacements for pip, flake8/black, and mypy.
Guides property-based testing across Python, JavaScript, Rust, and Solidity/Vyper.
Detects fail-open security vulnerabilities where applications run insecurely due to missing or weak configuration.
Scans Android APKs for Firebase security misconfigurations by decompiling the app, extracting Firebase configuration, and actively testing endpoints for vulnerabilities.
Creates custom Semgrep rules for detecting security vulnerabilities and code patterns.
Takes an existing Semgrep rule and ports it to one or more target languages.
Evaluates whether APIs, configurations, and interfaces are resistant to developer misuse.
Static analysis toolkit combining CodeQL, Semgrep, and SARIF parsing for security vulnerability detection.
Verifies that a smart contract codebase implements exactly what its specification documents describe.
A meta-skill that reads the Trail of Bits Application Security Testing Handbook and generates Claude Code skills from it.
Variant analysis skill for finding similar vulnerabilities across a codebase after an initial bug is identified.