dvduongth
46 verified skills
design-consolidate
(Designer) Consolidate Source GDD + server code extraction + optional refs into enriched consolidated-gdd.md under docs/runs/<feature_id>/...
development
skills/agent-teams-deep-understanding
# agent-teams-deep-understanding **Purpose**: Hiểu sâu hệ thống 9-agent CCN2 — trả lời câu hỏi về kiến trúc pipeline, trạng thái live (tickets/health), và từng agent cụ thể. Không cần đọc file thủ công. **Version**: v1.2 (2026-04-01) — Migration: shared/playtest/ → shared/godot-client/ **Spec**: `agent-teams/docs/superpowers/specs/2026-03-25-agent-teams-deep-understanding-design.md` --- ## Triggers Invoke skill này khi user hỏi về bất kỳ điều gì liên quan đến hệ thống agent-teams: **Nhóm 1
tools
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
testing
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
testing
bluebubbles
Use when you need to send or manage iMessages via BlueBubbles (recommended iMessage integration). Calls go through the generic message tool with channel="bluebubbles".
tools
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
documentation
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
development
apple-reminders
Manage Apple Reminders via remindctl CLI (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.
tools
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
development
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
development
blogwatcher
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
tools
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume.
tools
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
development
clientccn2-project-editor
Editor and project manager for the CCN2 game client (clientccn2/). Use this skill whenever the user wants to: manage client modules, add new game actions or effects, plan or design client-side features, generate or update client technical documentation, edit client feature ideas before coding, check consistency between client code and server/GDD, add new scenes or UI components, manage the action queue system, work with the event bus, review or refactor client architecture (legacy → new), manage config loaders, or plan new UI panels. Also trigger when the user mentions: "client code", "client module", "client architecture", "action queue", "ActionQueue", "BaseAction", "EventBus", "EventKeys", "BaseModule", "GameHUD", "SceneGame", "BaseScene", "BaseGUI", "game logic", "client scan", "client tech doc", "Cocos2d-x", "cocos client", "client config", "ConfigManager", "ServiceContainer", "AppContext", "NavigationCoordinator", "gv.bus", "gv.signalMgr", or any request involving clientccn2/ project management. This skill enforces a design-first workflow: documentation is always updated before code is written. Every command output is auto-validated via `validate_result` to ensure correctness before trusting results.
tools
coding-agent
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
tools
create-gdd
Quy trình 7 bước tạo GDD → dev-specs → dev-plan cho bất kỳ module CCN2 nào. Dùng khi cần tạo tài liệu thiết kế mới từ concepts folder, từ code hiện có, hoặc từ PM requirements. Bao gồm template prompts copy-paste cho từng step và worktree merge policy.
development
csd2tscn
Convert Cocos Studio published JSON (.json / layer_setting.json) to Godot 4 .tscn scenes. Use when asked to convert CSD JSON to Godot, preview Cocos UI in Godot, or run csd2tscn. Keywords: csd2tscn, convert cocos, cocos to godot, layer_setting, zcsd, preview cocos ui.
development
design-doc
(Designer) Draft a feature Design Doc from the latest ingest package; save canonical output to docs/design-docs/<feature_id>/design-doc.md plus run artifacts.
testing
design-evaluate
(Evaluator) Score a feature Design Doc's mechanics quality across 6 dimensions: feedback loop, pacing, progression, replayability, extensibility, emotional arc; writes a scored evaluation report under docs/runs/<feature_id>/...
testing
design-ingest
(Designer) Ingest sources into a structured package (manifest + summary + open questions) saved under docs/runs/<feature_id>/...
documentation
design-validate
(Tester/Reviewer) Validate a feature Design Doc for clarity, completeness, edge cases, and testability; writes a validation report under docs/runs/<feature_id>/...
testing
dev-analyze-design
(Architect) Analyze specs + tech-requirements → analysis report + Mermaid diagrams (usecase, sequence, flow, class) separated by client/server/shared. Creates tech-requirements if missing. Supersedes former dev-analyze and dev-design.
tools
dev-implement
(Implementation Orchestrator) Execute tasks.md by dispatching subagents per milestone — parallel where possible, sequential where dependent. Review per milestone, escalate blockers.
development
dev-plan
(Tech Lead) Smart entry-point for dev workflow: auto-detects pipeline state, runs missing steps (analyze → tasks). Requires user confirmation before generating tasks.
development
dev-specs
(Tech Lead) Promote validated Design Doc into feature-scoped specs (requirements/use-cases/acceptance-criteria) and record promotion run artifacts.
development
dev-tasks
(Tech Lead) Break architecture into granular implementation tasks mapped to ACs. Requires user-confirmed analyze + design results before generating.
development
discord
Discord ops via the message tool (channel=discord).
tools
skills/doc-wave-analysis
--- name: doc-wave-analysis description: Tự động hóa phân tích tài liệu theo wave-based parallel subagents với Top Rules enforcement. Use when user wants to: analyze multiple research documents in parallel, review and synthesize technical documentation, perform wave-based analysis with progress tracking, or enforce token budget and Vietnamese output rules across subagents. Triggers include: "phân tích tài liệu", "wave analysis", "doc review", "research synthesis", "parallel document analysis", "
documentation
eightctl
Control Eight Sleep pods (status, temperature, alarms, schedules).
tools
skills/eval-harness
# eval-harness — AI Agent Evaluation Skill Automate evaluation (evals) for AI agents. Covers coding, conversational, research, computer-use, and sub-agent types. Implements Swiss Cheese Model (6 layers). **Based on:** Anthropic Engineering — Demystifying Evals for AI Agents (2026-01-09) --- ## When This Skill Applies Use when the user wants to: - Set up an eval suite for an AI agent or task - Run evals with pass@k or pass^k metrics - Add graders (code-based, model-based, human) - Generate C
development
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
testing
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
data-ai
skills/gdscript-syntax-rules
--- name: gdscript-syntax-rules description: Enforcement checklist cho GDScript 4. Bắt buộc chạy TRƯỚC khi viết .gd và TRƯỚC khi mark done. Trigger khi: viết GDScript, parse error, import failure, hoặc sau khi tạo file .gd. --- # GDScript 4 — Syntax Rules & Enforcement Checklist ## Khi nào dùng skill này - Trước khi viết BẤT KỲ file .gd nào - Sau khi viết, trước khi claim "done" - Khi gặp parse error hoặc import/class_name failure - Khi convert code từ GDScript 3 / JavaScript / C# sang GDScrip
development
gifgrep
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.
tools
git-nexus-deep-understanding
Hiểu sâu bất kỳ codebase nào đã được GitNexus index — architecture, execution flows, symbol relationships, blast radius. Dùng khi hỏi về codebase architecture, symbol context, impact analysis, hoặc index status.
development
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]
documentation
1password
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
tools
skills/canvas
# Canvas Skill Display HTML content on connected OpenClaw nodes (Mac app, iOS, Android). ## Overview The canvas tool lets you present web content on any connected node's canvas view. Great for: - Displaying games, visualizations, dashboards - Showing generated HTML content - Interactive demos ## How It Works ### Architecture ``` ┌─────────────────┐ ┌──────────────────┐ ┌─────────────┐ │ Canvas Host │────▶│ Node Bridge │────▶│ Node App │ │ (HTTP Server) │ │ (TCP
tools
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
development
gemini
Gemini CLI for one-shot Q&A, summaries, and generation.
tools
apple-notes
Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks OpenClaw to add a note, list notes, search notes, or manage note folders.
tools
bear-notes
Create, search, and manage Bear notes via grizzly CLI.
tools
camsnap
Capture frames or clips from RTSP/ONVIF cameras.
tools
clawhub
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.
tools
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
tools
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
development