maf-command-generatorのsavedataに弓パッシブ（矢の効果スキル）を追加するスキル。bow, 弓, 矢, 弓パッシブ, 矢効果, 着弾エフェクト, 飛行エフェクト などの新規追加が出たら使う。savedata/bow/ai_workspace.json への書き込みを担う。
maf-command-generatorのsavedataにカスタムエネミー（敵モブ）を追加するスキル。enemy, エネミー, 敵, カスタムモブ, ボス, ゾンビ強化, モブ追加 などの新規作成が出たら使う。savedata/enemy/ai_workspace.json への書き込みを担う。
maf-command-generatorのsavedataにエネミースキル（敵モブが使用するスキル）を追加するスキル。enemy_skill, エネミースキル, 敵スキル, モブスキル, 毒攻撃, 範囲攻撃 などの新規追加が出たら使う。savedata/enemy_skill/ai_workspace.json への書き込みを担う。
maf-command-generatorのsavedataにアイテムを追加するスキル。item, アイテム, 武器, 防具, 装備, 剣, 弓, ヘルメット, チェストプレート などの新規追加が出たら使う。savedata/item/ai_workspace.json への書き込みを担う。
maf-command-generatorのsavedataにパッシブスキルを追加するスキル。passive, パッシブ, 常時発動, 攻撃時発動, スロット装備スキル などの新規追加が出たら使う。savedata/passive/ai_workspace.json への書き込みを担う。
为 OpenClaw 配置 code.newcli.com 作为模型源，包含四个 provider：newcli（Claude 主线路）、newcli-aws（Claude AWS 特价线路，消耗 1/24）、newcli-codex（GPT 系列）、newcli-gemini（Gemini 系列）。适用于需要接入 Claude 或 GPT…
Install or refresh OneCLI as NanoClaw's gateway provider. Use when setup selects OneCLI, an existing OneCLI-backed install is migrated to the gateway seam, or its runtime,…
Use when a state-materializing command starts or is asked to upgrade — reads the setup receipt, compares the recorded contract against the shipped one, executes the declared…
Use Bats-core when an agent needs to turn fragile shell scripts or command-line workflows into something it can verify repeatedly after edits.
Use when the user wants to add ONE table (typically a newly-added Dataverse table) to an existing offline profile without re-running the full /setup-offline-profile wizard.
Adição de Tailwind CSS v4 e shadcn/ui em projetos Vite + React + TypeScript. Use após a skill init-vite-react-ts para configurar alias @, plugin do Tailwind no Vite, inicialização…
Add a new third-party service to the privacy policy generator. Trigger when user says: "add {name} service", "add third party service", "add 3rd party service", "add new service…
Fully wires up a new route with required boilerplate, following this repo's conventions for subapps. Use when user wants to add a new route or app or subapp or page or screen.
Recipe for adding a new provider (LLM, transcriber, eval, prompt). Use whenever adding Cohere, Mistral, Deepgram, Phoenix, Promptlayer, etc.
Use when adding a new anchor integration to this project — creating an anchor client, its server singleton, API wrappers, proxy routes, and flow pages, or deciding whether a new…
Use when adding new mod parsers to convert game mod strings to typed Mod objects - guides the template-based parsing pattern (project)
Vite client-only SPA conventions — VITE_-prefixed env vars (never secrets) exposed via import.meta.env, dev server proxy for CORS, static dist/ builds with index.html fallbacks,…
Go code style and conventions for the adept codebase — formatting, linters, error wrapping with sentinels, the composition-root/no-globals rule, and core invariants.
Wrapper skill: start the local Telegram bridge in the background with a deterministic script.
Wrapper skill: inspect Google Calendar meetings and create draft-confirmed events.
Turn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread…
Industrial-clean light-mode admin aesthetic: white/slate canvas (#f8f9fb / #ffffff), dark-navy sidebar (#1a2235), orange-amber accent family (#ea580c / #f59e0b), crisp status…
Windows and Git Bash compatibility guidance for Azure Pipelines. Covers path conversion issues, shell detection in pipeline scripts, MINGW/MSYS path handling, Windows agent…
Implement Adobe-specific lint rules, CI policy checks, and runtime guardrails covering credential scanning (p8_ patterns), Firefly content policy pre-screening, PDF Services quota…
Apply production-ready patterns for Adobe Firefly Services SDK, PDF Services SDK, and raw REST API usage in TypeScript and Python.
Specialized skill for generating and managing Architecture Decision Records (ADRs). Supports Nygard, MADR, and custom templates with auto-numbering, linking, and status management.
Scaffolds an Architecture Decision Record (ADR-NNN.md) at a decision moment — allocates the next global-monotonic number across BOTH core/ADRs/ and release/ADRs/, stamps the…
Specializes in generating Action-Domain-Responder (ADR) boilerplate for Gravito projects. Trigger this when adding new features or modules using the ADR pattern.
Audit project gates (jest/vitest coverage thresholds, tsconfig strictness, eslint rules, husky/lint-staged, sonar quality gate, branch protection) and flag values mathema — from…
Use when iterating on a fix after an adversarial code review (Codex, human reviewer) surfaces design-level findings — not typos, lint, or formatter work.
Use when the user asks to migrate, convert, compatibilize, or modernize legacy ADVPL procedural code to TLPP object-oriented classes on TOTVS Protheus -- turning User…
Static config-correctness linter for this instance - catches the silent-failure class (unquoted schedules, duplicate keys, unconfigured skills, mode typos, broken requires/MCP…
aerc is a terminal-based email client written in Go with first-class support for IMAP, SMTP, JMAP, Maildir, and Notmuch.
Use when Codex is asked to plan, build, continue, or seal an Aether colony and must mirror wrapper orchestration safely
เทมเพลตจริงที่ก๊อปไปใช้ได้เลย ไม่ใช่คำอธิบายว่าควรหน้าตาแบบไหน เลย์เอาต์สไลด์ 41 แบบ รวมไดอะแกรม 16 แบบที่วาดด้วย CSS กับ SVG ในไฟล์เอง ชุดสี 6 โทนใน themes/ และม่านบนภาพ 5 แบบใน…
Facilitate the installation and management of VPS solutions using the Setup Automatik engine (powered by Orion Design).
Aeuv: Behörden-, Gerichts- oder Registerweg: prüft konkret die einschlägigen Tatbestandsmerkmale, Fristen, Belege und Rechtsprechung.
Plan puzzle-based activities for classrooms, parties, and events with pre-configured generator links. Use when you need help with puzzle activity planner. — from anubhavg-icpl/vibe
Wrapper oficial de M2MCent (Node.js) para inyectar muros de pago x402 en APIs o servidores Model Context Protocol (MCP).
Interviews a user, plans, and implements one React and TypeScript widget for a FileMaker Web Viewer. Use when creating or extending a widget in an fm-starter-ai project, including…
NDA-Generator und Verschwiegenheitsvereinbarungs-Checker: Agb Kontrolle B2B Und B2C; konkretisierter Spezialmodul mit Prüfachsen, Red Flags, Varianten, Quellenhygiene und…
Analyzes Freddie Mac and Fannie Mae agency multifamily quotes (lease-up and stabilized) into a decision-ready package.
Generate scaffolds that gradually increase student choice, voice, and ownership within a learning task.
Use when a multi-agent round needs a pre-merge gate, pre-commit check, verification before push, or a PASS/FAIL decision after reconciliation.
Agent skill for base-template-generator - invoke with $agent-base-template-generator — from ruvnet/ruflo
Agent skill for base-template-generator - invoke with $agent-base-template-generator — from majiayu000/claude-skill-registry
Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and Multi-Agent Supervisors (MAS) for multi-agent — from…
Build conversational AI agents using Vercel AI SDK + OpenRouter. Use when creating Next.js frontends with streaming UI, tool calling, and multi-provider support.
Dependency checker and installer for agent-canvas, agent-eyes, and canvas-edit skills. Use BEFORE running any canvas skill for the first time, or when canvas skills fail with…
Umbrella workflow for delegating coding work to local agent CLIs such as Claude Code, Codex, and OpenCode.
Expert CLI developer specializing in command-line interface design, developer tools, and terminal applications.
Generates Agent definitions (.md files) based on user intent and standard templates.
Generate project-level AGENTS.md guides that capture conventions, workflows, and required follow-up tasks.
Generate project-level AGENTS.md guides that capture conventions, workflows, and required follow-up tasks.
AI agent development standards including frontmatter structure, naming conventions, tool access patterns, model selection, and Bash-only file operations for .opencode/ folders
A scoring scale for evaluating how well a CLI is designed for AI agents, based on the "Rewrite Your CLI for AI Agents" principles.
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
GAN Harness — Generator agent. Implements features according to the spec, reads evaluator feedback, and iterates until quality threshold is met.
Generate AGENT.md files with proper YAML frontmatter, role definitions, expertise areas, and prompt templates following Babysitter SDK conventions. — from KenKaiii/b0t
Generate AGENT.md files with proper YAML frontmatter, role definitions, expertise areas, and prompt templates following Babysitter SDK conventions.