Dual-runtime Agent Skills for Claude Code, Codex GPT, CC Switch, and authorized CTF workflows.
Skill Claude CodeCodex
AI and machine learning analysis for authorized CTF challenges. Use when a challenge ships a model, weights file, or inference endpoint, or asks the agent to evaluate, perturb, extract, invert, or stress-test an ML or LLM system.
Skill Claude CodeCodex
Cryptographic and mathematical analysis for authorized CTF challenges. Use when a challenge involves classical ciphers, modern block or stream ciphers, RSA, ECC, DSA/ECDSA, PRNGs, lattices, zero-knowledge proofs, or number theory, and the task is to recover keys, decrypt, or break the construction.
Skill Claude CodeCodex
Digital forensics, steganography, and signal analysis for authorized CTF challenges. Use when evidence lives in disk images, memory dumps, packet captures, event logs, side-channel signals, embedded media, or blockchain traces, and the task is to recover, reconstruct, or decode it.
Skill Claude CodeCodex
Suspicious-sample and network-traffic analysis for authorized CTF challenges. Use when the artifact is a sample, packed payload, or PCAP that needs deobfuscation, triage, protocol recovery, IOC extraction, or behavior reconstruction within competition scope.
Skill Claude CodeCodex
Cross-category CTF challenges that do not fit a single specialist. Use when a challenge is genuinely hybrid — encodings, jails, RF/SDR, game logic, Z3 or constraint solving, custom VMs, or Linux privilege escalation — and a narrower category skill is not the right starting point.
Skill Claude CodeCodex
Triage, route, and validate authorized CTF investigations. Use when the category is unknown, the user is stuck, evidence conflicts, or a claimed solve must be reproduced from a clean baseline. Dispatches to the most relevant fieldops-ctf- specialist.
Skill Claude CodeCodex
Competition-scoped open-source intelligence and geolocation. Use when a challenge depends on public sources — social media, image geolocation, DNS/WHOIS, username traces, dorking, archived pages, or registries — and the task is to attribute, locate, or identify a sandbox-internal target.
Skill Claude CodeCodex
Binary exploitation and runtime memory analysis for authorized CTF challenges. Use when the target is a vulnerable native binary, a service, a kernel image, or a sandbox and the task is to turn a memory bug or low-level primitive into code execution. See the linked technique files for the specific playbook.
Skill Claude CodeCodex
Reverse engineering of compiled, packed, virtualized, or obfuscated targets for authorized CTF challenges. Use when the task is to understand, decompile, disassemble, or unpack an unknown executable across ELF, PE, Mach-O, APK, WASM, firmware, bytecode, or custom-VM targets.
Skill Claude CodeCodex
Web, API, browser, and identity attack-surface analysis for authorized CTF challenges. Use when the target is an HTTP service, an API, a SPA, or an auth flow and the task is to confirm, exploit, or chain a web-class primitive within competition scope.
Skill Claude CodeCodex
Generate a submission-style writeup for a solved CTF challenge. Use after a solve, when the user wants a reproducible competition report covering metadata, ordered solution steps, the solve script, and the recovered flag.
Skill Claude CodeCodex
Diagnoses, implements, and verifies non-trivial or risk-sensitive changes in an existing repository while preserving the user's uncommitted work, following repository instructions (AGENTS.md or CLAUDE.md), keeping edits within authorized scope, and handing off with runtime evidence. Use when the user asks to fix a…
Skill Claude CodeCodex
Coordinates multiple FieldOps skills for complex, unfamiliar, or mixed-domain work spanning research, prompt control, authorized CTF evidence, repository changes, PowerShell Unicode handling, or prompt refinement. Use when a task needs two or more FieldOps workflows, when the correct specialist is unclear, or when the…
Skill Claude CodeCodex
Writes, reviews, and repairs PowerShell so Persian/Farsi and other Unicode text survives console input, console output, native-process pipelines, and file I/O. Use when text turns into mojibake or question-mark boxes, when a UTF-8 BOM must be added or removed, for multilingual or non-ASCII automation, or when a script…
Skill Claude CodeCodex
Interprets and executes Prompt Decorators written with +++Name(key=value) syntax, handling message vs. chat scope, parameter validation, decorator composition, conflict resolution, meta-decorator expansion (N2 and Storm), retained-state inspection (ActiveDecs and AvailableDecs), selective clearing, and conversation…
Skill Claude CodeCodex
Transforms rough, ambiguous, overloaded, or reusable requests into precise, execution-ready prompts for coding agents. Use when asked to improve, rewrite, refine, tighten, structure, modularize, audit, or professionalize a prompt, AGENTS.md instruction set, task brief, system prompt, or agent workflow. Preserves…
Skill Claude CodeCodex
Investigates externally verifiable, uncertain, current, comparative, or high-consequence questions and delivers concise, evidence-backed, actionable answers. Use when facts may have changed, claims need fact-checking, sources disagree, the user wants a recommendation or comparison (which is better, is it still true…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: