Skill UI

A comprehensive guide for academics on articulating the true theoretical novelty of a manuscript. It teaches authors how to rigorously answer 'What is new?' and 'So what?' by clearly differentiating their work from prior literature, ensuring the contribution is a genuine conceptual leap, not merely a relabeling or minor extension.

This skill guides the transformation of visual observations and documentary evidence into a sustained, contestable academic thesis, suitable for high-level scholarly publication. It teaches how to explicitly state a claim (the thesis), define its scholarly stakes, and rigorously warrant every interpretive leap using evidence chains and anticipating counter-readings. Use this when a draft is descriptive but lacks a clear, disputed argument.

A rigorous methodology for debugging complex anomalies or incidents when multiple plausible causes exist. It guides the user to enumerate competing, falsifiable hypotheses and prioritizes running the cheapest, most discriminating observation first. By iteratively eliminating hypotheses and preferring the least-assumptive survivor, it systematically localizes the root cause efficiently.

A structured debugging skill for the googleapis/mcp-toolbox repository. It guides reading the actual error, establishing what changed, reproducing the failure, isolating the root cause, and then fixing that cause rather than the symptom. Use it when tests or CI jobs are red, a build breaks, many packages fail, or a test passes locally but fails in CI.

Build a first-person shooter game with move+mouse-look controllers, hitscan or projectile shooting, weapons, health, and enemy AI. Tune aim feel, time-to-kill, recoil, and spread. Covers core combat loops, weapon systems, and feedback mechanisms for FPS titles.

This methodology guides developers to diagnose ambiguous failures, intermittent bugs, or performance regressions before implementing any code changes. It emphasizes separating observed symptoms from inferred causes, tracing inputs and state transitions, and ranking hypotheses based on evidence and cheap falsification value. Use this structured approach to ensure fixes are built upon a proven mechanism.

A comprehensive guide for authorized red team engagements, covering the end-to-end lifecycle of advanced phishing campaigns. Learn techniques for infrastructure setup (domain aging, SPF/DKIM/DMARC), payload delivery (macro weapons, HTML smuggling), and bypassing email security gateways (MFA bypass, domain spoofing). Essential knowledge for penetration testers and security professionals.

This skill guides the advanced process of reverse engineering vulnerabilities from vendor-released security patches (N-day). By performing binary diffing between patched and unpatched binaries, users can pinpoint specific code changes (e.g., new boundary checks, locks) to infer the original vulnerability class (e.g., OOB, Race Condition) and develop a working Proof of Concept (PoC) for weaponization.

A practical methodology for turning a known vulnerability into a stable working remote exploit. Covers stack overflow, heap exploitation, and Linux kernel pwn, addressing real-world gaps between local CTF success and reliable remote execution: libc version mismatches, heap spray timing, SMEP/SMAP/KASLR, stack alignment, and network buffering. Uses pwntools with GEF/pwndbg, ROPgadget/Ropper, one_gadget, libc-database, and qemu-system.

Reviews GitHub pull requests in the googleapis/mcp-toolbox repo against the team's reviewer checklist: title conventions, linked issues, logic errors, edge cases, breaking changes, tests, docs, security, and new dependencies, then proposes a paste-ready verdict for the maintainer.

Propose labels and categorize GitHub issues for maintainers without direct edits. Checks duplicates, verifies bug info, and drafts comments based on repository rules. Optimizes issue management workflow for googleapis/mcp-toolbox.

Sweeps googleapis/mcp-toolbox for issues and PRs with no real activity in N days, classifies each silence as the author's, maintainer's, or nobody's, and drafts nudge or close comments for maintainer review only.