Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Lightweight research-plan-implement workflow for small tweaks, isolated bugfixes, copy edits, and low-blast-radius polish in this repo. Use when the change can be understood from 1-3 files and stays inside one subsystem without changing shared data flow.
Security-focused agent logic for identifying and fixing vulnerabilities.
Coordinate BioETL multi-agent workflow across py-* profiles using the Codex-local orchestration map.
>-
>
Setup and configure oh-my-codex using current CLI behavior
`web/`의 Prisma 7 설정과 generated client import 규칙을 맞추기 위한 스킬이다. 스키마 변경, migration, import 패턴 정리, Prisma 타입 사용 시 적용한다.
Plan and implement NovaTune Player SPA with auth, library, playback, playlists, and telemetry (plan) (project)
Format high-quality Git commit messages from staged or unstaged changes with stable conventions. Use when Codex is asked to create, polish, or validate commit messages, especially for Conventional Commits, commitlint-compatible repositories, squash/fixup flows, or teams that require consistent subject/body/footer structure.
Use this skill when a bug report needs structured investigation before planning or coding.
'Assess non-functional requirements (performance, security, reliability, maintainability) before release with evidence-based validation'
How to choose and configure data sources for MapLibre GL JS — rendering your own data without tiles, hosted tile services, serverless PMTiles, self-hosted tile servers, tile schemas, glyphs, and sprites.
Conecta e realiza operações (CRUD e Aggregations) em bancos de dados MongoDB utilizando configurações de conexão salvas. Suporta queries JSON e auxílio na sua construção.
Configure GSD workflow preferences including model profiles and agent settings. Use when the user says 'settings', 'configure', 'change profile', or wants to adjust workflow parameters. (Codex adapter)
Generate and maintain AGENTS.md as a living project context document by scanning the repository, discovering agents/skills, and extracting conventions. Use when initializing Codex context for a repo, refreshing stale AGENTS.md, or after significant project structure changes.
>-
Retrieve authoritative library documentation and code examples.
Expert C4 Container-level documentation specialist. Synthesizes Component-level documentation into Container-level architecture, mapping components to deployment units, documenting container interfaces as APIs, and creating container diagrams. Use when synthesizing components into deployment containers and documenting system deployment architecture.
Build, query, and inspect the project knowledge graph in .planning/graphs/
Plan and implement Python changes with ruff, pyright, and pytest validation before commit.
Git 변경사항을 분석하여 Conventional Commits 형식의 커밋 메시지를 생성합니다. 커밋, commit, 커밋 메시지 요청 시 자동 활성화됩니다.
Build an installable ZIP for the Lime Pipeline Blender add-on. Use for release candidates, QA handoff to artists, or whenever version/changelog changes must ship as a distributable artifact.
Use when working on ScenePilotix across multiple threads or when a task may change product flow, workspace boundaries, naming, save/export behavior, prompt-engine routing, or platform execution strategy. Ensures the shared development strategy doc is treated as the single source of truth and updated at the end.
Conduct deep research on a topic using web search and analysis. Use when you need comprehensive understanding of a topic.
Adversarially review proposed mew self-improvement loops for product-goal drift, M5 safety boundaries, weak evidence, missing verification, hidden rescue edits, and whether the loop should be approved, rejected, or revised.
Master Flutter development with Dart 3, advanced widgets, and multi-platform deployment. Handles state management, animations, testing, and performance optimization for mobile, web, desktop, and embedded platforms. Use PROACTIVELY for Flutter architecture, UI implementation, or cross-platform features.
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
Use this skill for mission/sector/upgrade balancing and authored data changes.
This document teaches any AI coding assistant how to build a voice-enabled agent using Amazon Nova 2 Sonic, Strands Agents SDK, and Amazon Bedrock AgentCore Runtime. It is distilled from the insurance
AWS security finding analysis: analyze findings, map to Atmos components/stacks, generate structured remediation with exact Terraform changes and deploy commands
workleap-chromatic-best-practices
>
**Skill Name**: browser-local-chrome-remote-debugging
Use Moneta shared memory via MCP tools to recall project knowledge
>
Use this skill when the project uses shadcn-svelte and the task involves implementing or refactoring UI with that library.
Use when developing, reviewing, or closing work in beamHO-bench that is governed by an active pending SDD, especially when the task requires reading PROJECT_CONSTRAINTS, active pending status, validation rules, and lifecycle-sync docs before editing code.
Use when starting any active phase/group in ntn-sim-core platform refactor, or before promoting a downstream MODQN/UI prompt into active work, to verify authority docs, phase status, prompt freshness, and go/no-go conditions.
Query, create, update, delete, and track WeCom work items through wecom-cli.
>
Applies the project's commit message convention. Use when writing commit messages, making git commits, or summarizing changes.
Solve one assignment problem file using a single endpoint with two logical tracks: (A) Math/Physics PDF problem solving (lecture slides/lecture notes as ground truth) and (B) code artifact generation. Save a final answer with detailed explanation next to the problem file.
>
>
Fast semantic code navigation via LSP. Load FIRST before ANY code task - even 'simple' ones. Trigger scenarios: (1) fixing lint/type/pyright/mypy warnings or errors, (2) fixing reportAny/reportUnknownType/Any type errors, (3) adding type annotations, (4) refactoring or modifying code, (5) finding where a function/class/symbol is defined, (6) finding where a symbol is used/referenced/imported, (7) understanding what a function calls or what calls it, (8) exploring unfamiliar code or understanding architecture, (9) renaming symbols across codebase, (10) finding interface/protocol implementations, (11) ANY task where you'd use ripgrep to find code or read-file to view a function. Use `leta show SYMBOL` instead of read-file, `leta refs SYMBOL` instead of ripgrep for usages, `leta grep PATTERN` instead of ripgrep for definitions, `leta files` instead of list-directory.
>
>
Use when validating beamHO-bench changes, deciding which project gates to run, preparing SDD closure, or checking whether lifecycle docs and manual acceptance evidence are sufficient before marking work complete.
Use when ntn-sim-core phase/group prompt packs, todo status, or group sequencing need updating so the repo keeps an accurate handoff surface for future agents.
Generates high-quality, predictable, and efficient .agent/skills/ directories based on user requirements. Reference this at any time you are creating any other skill for Antigravity.