capabilities

In the author's own words, from each skill's SKILL.md — showing the first 30 of 138 files.

• clean-test-skill

  A clean skill used for security scanner testing

  scripts/fixtures/clean-skill/SKILL.md on GitHub (opens in a new tab)

• malicious-skill

  Test malicious skill for security scanner validation

  scripts/fixtures/malicious-skill/SKILL.md on GitHub (opens in a new tab)

• analytics-interpretation

  Guide for reading and interpreting AIRT analytics output including ASR, risk scores, severity, and compliance metrics

  capabilities/ai-red-teaming/skills/analytics-interpretation/SKILL.md on GitHub (opens in a new tab)

• attack-selection-guide

  Decision tree for selecting AIRT attacks based on goals, target type, and constraints

  capabilities/ai-red-teaming/skills/attack-selection-guide/SKILL.md on GitHub (opens in a new tab)

• auth-setup-guide

  Guide the user through authenticating the target, attacker, and judge models from their own environment (any cloud, any auth mode) before running an assessment

  capabilities/ai-red-teaming/skills/auth-setup-guide/SKILL.md on GitHub (opens in a new tab)

• compliance-mapping

  Maps AIRT attacks, transforms, and scorers to OWASP LLM Top 10, OWASP ASI (ASI01-ASI10), MITRE ATLAS, NIST AI RMF, and Google SAIF

  capabilities/ai-red-teaming/skills/compliance-mapping/SKILL.md on GitHub (opens in a new tab)

• error-troubleshooting

  Diagnose and fix common errors in AIRT attack generation, execution, and results collection

  capabilities/ai-red-teaming/skills/error-troubleshooting/SKILL.md on GitHub (opens in a new tab)

• provisioning-and-lifecycle

  Provision a hosted target, pick the right endpoint per target type, tear down to stop billing, and interpret transient vs fatal errors. Load this whenever the user wants to provision/attack a bundled target (ml-extraction-*, *-mesh) or asks about environments, sandboxes, teardown, or billing.

  capabilities/ai-red-teaming/skills/provisioning-and-lifecycle/SKILL.md on GitHub (opens in a new tab)

• scorer-reference

  Complete catalog of all 84 scorers with exact names, categories, and when to use each

  capabilities/ai-red-teaming/skills/scorer-reference/SKILL.md on GitHub (opens in a new tab)

• trace-analysis-advisor

  Analyzes historical attack traces to provide intelligent recommendations for attack selection, transform effectiveness, and strategic adaptation

  capabilities/ai-red-teaming/skills/trace-analysis-advisor/SKILL.md on GitHub (opens in a new tab)

• transform-reference

  Complete catalog of all 183 transforms with exact names, parameters, categories, and LLM requirements

  capabilities/ai-red-teaming/skills/transform-reference/SKILL.md on GitHub (opens in a new tab)

• workflow-patterns

  Python workflow templates for common AIRT assessment scenarios using the Assessment API

  capabilities/ai-red-teaming/skills/workflow-patterns/SKILL.md on GitHub (opens in a new tab)

• recursive-code-analysis

  Use when code analysis, vulnerability research, or architecture mapping needs a durable worklist that can resume across context or session boundaries.

  capabilities/analysis-ledger/skills/recursive-code-analysis/SKILL.md on GitHub (opens in a new tab)

• android-corpus-prep

  Use when preparing Android APK corpora — AndroZoo metadata download, popular-package selection via DuckDB, APK download from Play or AndroZoo, and per-pass provenance manifests.

  capabilities/android-apk-research/skills/android-corpus-prep/SKILL.md on GitHub (opens in a new tab)

• android-protector-triage

  Use when an Android APK is packed by a commercial protector — detect with apkid + protector_detect, structurally unpack DexProtector (arm64) where supported, and triage what survives in JADX. Routes between detection, optional unpack, and protector-aware adjacency analysis.

  capabilities/android-apk-research/skills/android-protector-triage/SKILL.md on GitHub (opens in a new tab)

• android-semantic-vuln-hunting

  Use when hunting Android APK logic bugs at scale — deep links, intent redirection, WebView trust, exported components, auth/session/client-state bypasses that scanners miss or flatten to generic warnings.

  capabilities/android-apk-research/skills/android-semantic-vuln-hunting/SKILL.md on GitHub (opens in a new tab)

• android-targeted-assessment

  Use when assessing one Android APK deeply — inventory, decompile, ripgrep + Semgrep triage, Joern/CodeQL/FlowDroid escalation where warranted, hypothesis report, authorized validation plan.

  capabilities/android-apk-research/skills/android-targeted-assessment/SKILL.md on GitHub (opens in a new tab)

• atlassian

  Use when the user wants to connect to Jira, Confluence, or Compass — search issues with JQL, read or create issues and pages, link content across products, or set up Atlassian auth. The connector — not security tradecraft.

  capabilities/atlassian/skills/atlassian/SKILL.md on GitHub (opens in a new tab)

• bbot-module-reference

  BBOT module and preset reference for reconnaissance scanning. Use when choosing which modules, presets, or flags to use for a BBOT scan, or when you need to understand what a specific module does.

  capabilities/attack-surface-management/skills/bbot-module-reference/SKILL.md on GitHub (opens in a new tab)

• cypher-query-playbook

  Neo4j Cypher query patterns for analyzing BBOT reconnaissance data in the graph database. Use when you need to analyze scan results, map infrastructure, find anomalies, or synthesize findings from the attack surface graph.

  capabilities/attack-surface-management/skills/cypher-query-playbook/SKILL.md on GitHub (opens in a new tab)

• reconnaissance-planning

  Strategic reconnaissance planning for external attack surface management. Use when starting a new engagement, choosing initial scan strategy, or deciding how to expand coverage after initial results.

  capabilities/attack-surface-management/skills/reconnaissance-planning/SKILL.md on GitHub (opens in a new tab)

• screenshot-triage

  Triage web application screenshots to identify high-value targets for manual investigation. Use when analyzing WEBSCREENSHOT nodes from BBOT scans or when visually assessing discovered web assets.

  capabilities/attack-surface-management/skills/screenshot-triage/SKILL.md on GitHub (opens in a new tab)

• shodan-reconnaissance

  Shodan query strategies for internet-wide host intelligence, asset discovery, vulnerability correlation, and attack surface mapping. Use when enriching BBOT results with Shodan data, hunting for exposed services, or correlating CVEs with discovered infrastructure.

  capabilities/attack-surface-management/skills/shodan-reconnaissance/SKILL.md on GitHub (opens in a new tab)

• azure-devops

  Use when the user wants to connect to Azure DevOps — query Boards work items with WIQL, read PRs, inspect pipeline runs, create or update work items and wiki pages, or set up ADO auth. The connector — not security tradecraft.

  capabilities/azure-devops/skills/azure-devops/SKILL.md on GitHub (opens in a new tab)

• binary-analysis

  Reverse-engineer native binaries (PE, ELF, Mach-O, shellcode) end-to-end — triage, identify and unpack packers, bypass anti-debug checks, decompile and trace, recover protected artifacts (keys, configs, payloads), and emulate cross-arch with Qiling. Use for malware triage, incident response, vulnerability research, license validation, and CTF reversing.

  capabilities/binary-analysis/skills/binary-analysis/SKILL.md on GitHub (opens in a new tab)

• ad-entity-walk

  Investigate a single AD or Azure principal — who controls it, what it controls, where it has admin rights, and what's reachable via its credentials. Use when the caller asks "tell me about this user", "what does X have access to", "who can compromise Y", or when triaging a finding tied to a specific principal.

  capabilities/bloodhound-enterprise/skills/ad-entity-walk/SKILL.md on GitHub (opens in a new tab)

• attack-path-triage

  Walk a BloodHound Enterprise deployment's active attack-path findings, prioritise them by severity and exposure, and produce a ranked action list. Use when the caller asks "what should we fix first", "what attack paths are active", "review BHE findings", or after an ingest cycle that surfaced new findings.

  capabilities/bloodhound-enterprise/skills/attack-path-triage/SKILL.md on GitHub (opens in a new tab)

• attack-pattern-explore

  Drive a self-directed survey of a BloodHound Enterprise deployment using the curated attack-pattern catalog. Walks the canonical AD / Azure / PKI patterns (Kerberoasting, unconstrained delegation, ADCS ESC1-15, ACL abuses, SID history, etc.) and surfaces concrete findings with evidence. Use when the caller asks "go find interesting things", "self-audit this deployment", "what's exploitable here",…

  capabilities/bloodhound-enterprise/skills/attack-pattern-explore/SKILL.md on GitHub (opens in a new tab)

• bhe-bootstrap

  Establish a working session against a BloodHound Enterprise deployment — verify credentials, identify the environment, list domains, and confirm the API is responding. Run this at the start of every session before any other BHE skill, or whenever a tool fails because no credentials are configured.

  capabilities/bloodhound-enterprise/skills/bhe-bootstrap/SKILL.md on GitHub (opens in a new tab)

• cypher-investigation

  Open-ended graph investigation via raw OpenCypher queries. Use when the prebuilt tools don't capture the question — bespoke "find every X that can reach Y via Z" queries, ad-hoc relationship walks, novel attack-path patterns, or one-off exports for analysis. Read-only by default; writes require explicit opt-in.

  capabilities/bloodhound-enterprise/skills/cypher-investigation/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• rufloby ruvnet 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems.… 79.1k stars · 30 skills
• text-to-cadby earthtojake Give your agent CAD superpowers. 22.9k stars · 14 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 379k stars · 1 skill
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 288k stars · 30 skills
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 176k stars · 6 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 134k stars · 1 skill