Work on an assigned Agent Kanban v2 Task through Realmroot Toolbox. Use when an Agent running in an Agency Session needs to inspect, claim, update, or submit…
agent-orchestration
ai-agents
ai-coding-agent
claude-code
cloudflare-pages
codex
developer-tools
ed25519
gemini-cli
kanban
multi-agent
task-management
Updated 2026-09-19 09:01:47 +08:00
playwright-cli: Automate browser interactions, test web pages and work with Playwright tests.; screenci: Create, show, and guide with ScreenCI videos in an already-initialized project by editing `.screenci.ts` files and running the Screenci workflow.
Updated 2026-09-19 08:57:47 +08:00
Conduct context-driven code reviews focusing on quality, testability, and maintainability. Use when reviewing code, providing feedback, or establishing review…
Updated 2026-09-19 08:45:48 +08:00
diffity-diff: Open the diffity diff viewer in the browser to see your changes; diffity-review: Review current diff and leave comments using diffity agent commands; diffity-resolve: Read open review comments and resolve them by making code fixes
Updated 2026-09-19 07:26:16 +08:00
Universal UI/UX design principles covering visual hierarchy, interaction laws, typography foundations, and WCAG accessibility requirements. Use when making…
agent-skills
ai
ai-tools
claude-design
cli
codex
design
design-md
design-system
design-tools
gemini
gemini-cli-extension
google-stitch
skills
terminal
ui
Updated 2026-09-19 07:24:37 +08:00
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts,…
Updated 2026-09-19 07:11:22 +08:00
Audits an implementation plan for requirements traceability, avoidable complexity, risky assumptions, and evidence gaps. Use when reviewing an AI-generated or…
Updated 2026-09-19 07:10:29 +08:00
gitnexus-impact-analysis: Use when the user wants to know what will break if they change something, or needs safety analysis before editing code. Examples: "Is it safe to change X?",…; gitnexus-exploring: Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How…; gitnexus-debugging: Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?"…
Updated 2026-09-19 05:58:02 +08:00
Generate Xiaohongshu (小红书) style cover images based on user topics. Use when the user wants to create a social media cover image in Xiaohongshu style, or…
Updated 2026-09-19 05:56:08 +08:00
Feishu document read/write operations + comment management. Activate when user mentions Feishu docs, cloud docs, docx links, or document comments.
Updated 2026-09-19 05:39:52 +08:00
Add existing screenshots or screen recordings to a GitHub pull request as a before/after or preview block. Use when a PR needs visual media attached to its…
Updated 2026-09-19 05:09:13 +08:00
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates,…
agent
agentic
agentic-ai
ai
ai-agent
ai-agents
dsh
dsh-plugin
harness
harness-engineering
harness-framework
llm
Updated 2026-09-19 05:06:28 +08:00
difit: Ask the user for a code review by opening the changes in difit, a local diff viewer. Explicit opt-in only — use when the user names difit, asks to open or show…; difit-review: Review a specific diff (branch, commit, or GitHub PR) and show the findings as comments inside difit, the local diff viewer. Explicit opt-in only — use when…
Updated 2026-09-19 05:03:24 +08:00
Set up and use feature flags and A/B tests with the Flags SDK (`flags` npm package) and Vercel Flags. Use when installing or configuring the SDK, adding a new…
Updated 2026-09-19 03:49:23 +08:00
frontend-design: Create distinctive, production-grade frontend interfaces with high design quality. Provides analysis tools for auditing existing designs and generation tools…; presentation-design: Design and evaluate presentations that communicate effectively. Use when designing a presentation, creating slides, getting presentation feedback, structuring…; requirements-analysis: Diagnose requirements problems and guide discovery of real needs and constraints; godot-best-practices: Guide AI agen…
Updated 2026-09-19 03:32:54 +08:00
Store and retrieve memories (notes, facts, decisions, snippets, images) using a local SQLite database with full-text search. Use when you need to remember…
Updated 2026-09-19 03:29:20 +08:00
Use context-mode tools (ctx_execute, ctx_execute_file) instead of Bash/cat when processing
large outputs. Triggers: "analyze logs", "summarize output",…
antigravity
claude
claude-code
claude-code-hooks
claude-code-plugins
claude-code-skill
codex
codex-cli
context-mode
copilot
cursor-plugin
kiro
mcp
mcp-server
mcp-tools
openclaw
opencode
pi-agent
skills
zed-extension
Updated 2026-09-19 03:27:16 +08:00
Find and remove AI slop — the generic, machine-default visual and copy tics of vibe-coded products — from a web project. Use when the user asks to "kill AI…
Updated 2026-09-19 03:09:15 +08:00
Build terminal UIs with OpenTUI. Covers Core, frameworks, components, application APIs, testing, extensions, integrations, deployment, and public API lookup.
Updated 2026-09-19 01:26:04 +08:00
Add, enrich, and manage contacts in Joel's Vault. Fire the Inngest enrichment pipeline for full multi-source dossiers, or create quick contacts manually. Use…
Updated 2026-09-19 01:24:05 +08:00