Guides an AI agent to pause and ask clarifying questions when a request has ambiguous objectives, unclear scope, or missing constraints. The agent asks 1-5 targeted questions before doing any work, of
A structured analysis skill for the pre-audit phase of code review. It guides Claude through line-by-line function analysis, cross-boundary call tracing, and invariant mapping before any vulnerability
A collection of 11 skills for smart contract security across Algorand, Cairo, Cosmos, Solana, Substrate, and TON. Covers platform-specific vulnerability scanning and development guidance based on Trai
Searches and extracts data from Burp Suite project files (.burp) via the command line. Supports regex search across response headers and bodies, extraction of audit findings with severity and confiden
Diagnoses and fixes connectivity failures between the Claude in Chrome MCP extension and Claude Code CLI on macOS. The core problem it solves is a conflict between Claude.app (Cowork) and Claude Code
Detects timing side-channel vulnerabilities in cryptographic code across 12 languages. It analyzes assembly and bytecode for variable-time operations like secret-dependent branches, divisions, and tab
Interprets Culture Index behavioral assessments for individuals and teams. Maps survey results to 19 archetypes, detects burnout risk by comparing Survey vs Job trait energy, and evaluates team gas/br
Runs security-focused differential reviews on PRs, commits, and diffs. Scales analysis depth to codebase size, calculates blast radius for high-risk changes, checks test coverage gaps, and writes a ma
Adds deep knowledge of the DWARF debug format (versions 3-5) to an agent. Covers parsing and validating DWARF data from compiled binaries, answering questions about the standard, and writing or review
Analyzes smart contract codebases to map all state-changing entry points for security audits. Detects externally callable functions across Solidity, Vyper, Solana/Rust, Move, TON, and CosmWasm, then c
Scans Android APKs for Firebase security misconfigurations by decompiling the app, extracting Firebase configuration, and actively testing endpoints for vulnerabilities. Checks Realtime Database, Fire
Detects fail-open security vulnerabilities where applications run insecurely due to missing or weak configuration. Focuses on distinguishing exploitable defaults (app runs with a weak secret) from fai
Configures Python projects with uv, ruff, and ty — the modern replacements for pip, flake8/black, and mypy. Covers new projects, standalone scripts using PEP 723 inline metadata, and migrations from l
Guides property-based testing across Python, JavaScript, Rust, and Solidity/Vyper. Detects high-value patterns like serialization pairs, normalizers, and smart contract state invariants, then suggests
Creates custom Semgrep rules for detecting security vulnerabilities and code patterns. Guides you through a test-first workflow: write tests, analyze the AST, write the rule, iterate until all tests p
Takes an existing Semgrep rule and ports it to one or more target languages. For each language, it runs applicability analysis, writes test cases first, translates the rule syntax to match target lang
Evaluates whether APIs, configurations, and interfaces are resistant to developer misuse. Focuses on cases where the easy path leads to insecurity, such as algorithm selection footguns, dangerous defa
Verifies that a smart contract codebase implements exactly what its specification documents describe. It works by extracting intent from whitepapers, design docs, and protocol specs, then mapping each
Static analysis toolkit combining CodeQL, Semgrep, and SARIF parsing for security vulnerability detection. Covers taint tracking, data flow analysis, and pattern-based scanning across Python, JavaScri
A meta-skill that reads the Trail of Bits Application Security Testing Handbook and generates Claude Code skills from it. It covers fuzzers (libFuzzer, AFL++, cargo-fuzz), static analysis tools (Semgr
Variant analysis skill for finding similar vulnerabilities across a codebase after an initial bug is identified. It guides systematic pattern generalization using ripgrep, Semgrep, and CodeQL, moving