skills

Skills (248)

• skill-improver

  147 lines893 words4 blocks

  "Iteratively reviews and fixes Claude Code skill quality issues until they meet standards. Runs automated fix-review cycles using the skill-reviewer a...

  text
• trailofbits:diff-review

  17 lines59 words

  Performs security-focused differential review of code changes

• adversarial-modeler

  174 lines790 words3 blocks

  "Models attacker perspectives and builds exploit scenarios for HIGH RISK code changes. Use when differential review identifies high-risk changes that ...

  markdown
• differential-review

  229 lines1035 words5 blocks

  >

• devcontainer-setup

  304 lines943 words18 blocks

  Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support ...

  dockerfilejsonmermaid
• trailmark-summary

  84 lines446 words3 blocks

  "Runs a Trailmark summary analysis on a codebase. Returns auto-detected languages, entry point count, and dependency list. Use when vivisect or galvan...

  bash
• trailmark

  205 lines970 words5 blocks

  "Builds and queries multi-language source code graphs for security analysis. Includes pre-analysis passes for blast radius, taint propagation, privile...

  bashpython
• genotoxic

  340 lines1761 words7 blocks

  "Graph-informed mutation testing triage. Parses codebases with Trailmark, runs mutation testing and necessist, then uses survived mutants, unnecessary...

  bashmarkdown
• diagramming-code

  189 lines814 words10 blocks

  >

  bashmarkdownmermaidpython
• trailmark-structural

  120 lines529 words3 blocks

  "Runs full Trailmark structural analysis on Trailmark 0.2.x by building a graph, running `preanalysis()`, and reporting hotspots, taint, blast radius,...

  bash
• audit-augmentation

  178 lines900 words5 blocks

  >

  bashpython
• mermaid-to-proverif

  462 lines2634 words16 blocks

  "Translates Mermaid sequenceDiagrams describing cryptographic protocols into ProVerif formal verification models (.pv files). Use when generating a Pr...

  proverif
• crypto-protocol-diagram

  441 lines2734 words6 blocks

  "Extracts protocol message flow from source code, RFCs, academic papers, pseudocode, informal prose, ProVerif (.pv), or Tamarin (.spthy) models and ge...

  bashmarkdown
• vector-forge

  479 lines2720 words6 blocks

  "Mutation-driven test vector generation. Finds implementations of a cryptographic algorithm or protocol, runs mutation testing to identify escaped mut...

  bash
• graph-evolution

  320 lines1508 words9 blocks

  >

  bashpython
• 3b-rust-compiler-analyzer

  287 lines1709 words10 blocks

  "Performs crate-level MIR and LLVM IR analysis for Rust in zeroize-audit. A single instance runs per crate (unlike 3-tu-compiler-analyzer which runs o...

  bashjson
• 6-test-generator

  76 lines416 words

  "Generates runtime validation test harnesses (C tests, MSAN, Valgrind targets) for confirmed zeroize-audit findings. Produces a Makefile for automated...

• 5-poc-generator

  327 lines2252 words10 blocks

  "Crafts bespoke proof-of-concept programs demonstrating that zeroize-audit findings are exploitable. Reads source code and finding details to generate...

  bashjsonrusttoml
• 4-report-assembler

  294 lines1812 words5 blocks

  "Collects all findings from source and compiler analysis, applies supersessions and confidence gates, normalizes IDs, and produces a comprehensive mar...

  bashjsonmarkdown
• 3-tu-compiler-analyzer

  208 lines1071 words8 blocks

  "Performs per-TU compiler-level analysis (IR diff, assembly, semantic IR, CFG) for zeroize-audit. One instance runs per translation unit, enabling par...

  bashjson