daeryundf2-prog/LAZYANTIGRAVITY

daeryundf2-prog/LAZYANTIGRAVITY

Skill Codex

Antigravity strategic planning consultant. Explores the codebase exhaustively, surfaces only the ambiguities exploration cannot resolve, asks the user, and waits for explicit approval before producing one decision-complete work plan. MUST USE when the work has 5+ steps, scope is ambiguous, multiple modules are…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Codex

Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

Audit and rewrite content to remove AI writing patterns ('AI-isms') from markdown, articles, READMEs, technical blogs, PRs, and documentation. Use this skill when asked to 'remove AI-isms', 'clean up AI writing', 'edit writing for AI patterns', 'audit writing for AI tells', 'make this sound less like AI', or…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory leaks, async misbehavior, unexplained timing, reverse engineering. Runs a hypothesis-driven loop: form ≥3 hypotheses, investigate in parallel, after 2 failed rounds spawn Oracles…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Codex

MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

A Korean-language skill that turns a rough image idea into a detailed prompt for gpt-image-2, OpenAI’s image-generation model.

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex needs its repo

(builtin) Initialize hierarchical AGENTS.md knowledge base.

daeryundf2-prog/LAZYANTIGRAVITY

Skill Codex

Alias for report-bug. Create a high-signal bug issue or PR in the repo that owns the defect.

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

A workflow for examining audio, images, and video using metadata checks, subtitles, extracted frames, speech transcription, and text recognition from images.

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

MUST USE for ANY work on .py .pyi .rs .ts .tsx .mts .cts .go files. One philosophy: strict types, modern stacks (Pydantic v2 / serde+thiserror / Zod / gin+sqlc+pgx+slog), modern toolchains (uv+basedpyright+ruff / cargo+clippy+miri / Bun+Biome+tsc / gofumpt+golangci-lint v2+nilaway+go-race), parse-don't-validate…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

Intelligent refactor command. Triggers: refactor, refactoring, cleanup, restructure, extract, simplify, modernize.

daeryundf2-prog/LAZYANTIGRAVITY

Skill Codex

Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyAntigravity plugin, bundled component, skill, hook, MCP, installer, or packaging bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

Post-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification), Oracle (code quality), Oracle (security), unspecified-high (hands-on QA execution), unspecified-high (context mining from GitHub/git/Slack/Notion). All must pass for review to pass. MUST USE after…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

Execute a Prometheus work plan on Antigravity with Boulder state, evidence ledger updates, worktree discipline, parallel invokesubagent workers, and Stop-hook continuation. Use after planning when the user says start work, execute plan, continue plan, resume plan, or asks to run a .omo/plans plan.

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

Shorthand alias for /ulw-loop. Triggers the full ulw-loop workflow with role routing and model recommendation.

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

Rigorous visual QA for any UI you built or changed, across BOTH web/page UIs and TUI/terminal UIs. MUST USE after building or changing any UI to verify it visually before declaring it done. Captures objective reference evidence with a bundled diff script (image-diff for screenshots, tui-check for terminal captures)…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex

A reasoning and planning mode for an agent that uses extended planning, multiple perspectives, and adversarial verification. It is activated by specified boost commands.

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex needs its repo

Chain-of-Verification (CoVe) 4-Stage Verification Skill: Meta AI & community CoVe pipeline. Generates baseline response, plans 3-5 factual verification questions, executes isolated factual checks to prevent confirmation bias, and synthesizes corrected verified output. Triggers: cove-verify, cove…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex needs its repo

SAFE (Search-Augmented Factuality Evaluator): Google DeepMind atomic fact decomposition and search-grounded verification skill. Evaluates long-form text factuality, breaks claims into individual atomic propositions, issues search queries, computes SAFE F1 score, and enforces factuality gates. Triggers: safe-evaluator…

daeryundf2-prog/LAZYANTIGRAVITY

Skill Claude CodeCodex needs its repo

A deep-research workflow that searches across multiple channels in parallel and checks claims against multiple sources. It uses a claim ledger to track and lock supporting evidence.