Claude Skills by ShockRock2004

Agamotto — adversarial AI code/plan review with foresight. Opens the Eye of Agamotto banner on summon and does a quick foresight self-review, then sends the work to an external reviewer (Codex, or a fresh Claude reviewer subagent if codex is not installed or configured) while Claude fixes, looping until approved. Auto-detects plan/code/code-vs-plan mode. Invoke with /agamotto.

Use when the user invokes /askagy, or asks to consult, cross-check, second-opinion, sanity-check, or hand off a question to Antigravity, agy, or the Antigravity CLI about the work currently in progress. Requires the Antigravity CLI (`agy`) to be installed; if it is not, the skill says so and stops rather than faking a second opinion.

A rigorous "iterate until verified" working loop for any non-trivial build or fix. Use when the user prefixes a request with /dormammu, or asks you to be exhaustive, to "not stop until it's truly done", to self-critique hard, or to keep going until the solution is flawless. It defines a verifiable end-state and hands the user a ready-to-paste /goal command to lock the session until that state is met (it never runs /goal itself — /goal is user-only), then implements, aggressively self-audits a...

Use when the user invokes /handoff, and ALWAYS when starting work in a repo that already contains a HANDOFF.md — reading that file is the first job before exploring the codebase. Creates and maintains a git-ignored HANDOFF.md at the repo root that carries task state between sessions and agents.

Use when the user shares a DSA or competitive-programming solution — a LeetCode/Codeforces problem number, link, screenshot, or pasted code — and wants interview-grade critique instead of encouragement. Reviews the solution as a hiring panel would, scores it, names the input that breaks it, and always ends with the best possible solution in the user's own language.

Compile everything Claude did today across ALL sessions and repos into one dated teaching-guide markdown saved in "~/Daily Log", render it as a phone-readable PDF, and upload to Google Drive. Safe to run multiple times a day — it appends only newly-uncovered work to that day's single file rather than overwriting. Use when the user runs /wong, or says "log today's work", "end of day log", "daily log", "wrap up the day", or any similar end-of-day trigger. Accepts an effort level (light/medium/h...