Skills that do not fit the categories above (14.6K skills)
Use when each agent response should end with a red/yellow/green status line showing whether work is finished, pending follow-up, or blocked.
The English summary is being prepared. Showing the original description.
Create 3D scenes, interactive experiences and visual effects with Three.js. Use for 3D graphics, WebGL, animations or interactive 3D elements.
The English summary is being prepared. Showing the original description.
Work like Manus: Use persistent markdown files as your "working memory on disk."
The English summary is being prepared. Showing the original description.
AOS go-gate status and modes. Show grants, explain blocks. Display only, human-typed commands change mode.
The English summary is being prepared. Showing the original description.
Compare, cross-review or judge competing agent plans and recommend one execution plan. Use when several agents proposed plans or the user asks to arbitrate.
The English summary is being prepared. Showing the original description.
Open a plan in a browser canvas to visualize the plan, annotate, approve. Use for "plan", "planen", "roadmap", /plan-canvas, planning or a brainstorm review.
The English summary is being prepared. Showing the original description.
Strict POSIX sh scripting for maximum portability across Unix-like systems; scripts that run on dash, ash, sh or bash --posix alike.
The English summary is being prepared. Showing the original description.
Manage Linear issues, projects, and teams
The English summary is being prepared. Showing the original description.
Obsidian Flavored Markdown: wikilinks, embeds, callouts, properties. .md files, frontmatter, tags.
The English summary is being prepared. Showing the original description.
Expert patterns for Neon serverless Postgres, branching, connection pooling, and Prisma/Drizzle integration
The English summary is being prepared. Showing the original description.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
The English summary is being prepared. Showing the original description.
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies.
The English summary is being prepared. Showing the original description.
Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
The English summary is being prepared. Showing the original description.
Collect and triage product feedback, telemetry, runtime errors and issue reports. Use when scanning signal sources for fix/reply/close rules.
The English summary is being prepared. Showing the original description.
Use when proactively checking for and installing updates to the AOS (BDB Agent OS) package via npm.
The English summary is being prepared. Showing the original description.
Summarize work needing human judgment across PRs, issues, feedback and delivery signals. Use for a human decision queue or bounded review.
The English summary is being prepared. Showing the original description.
On-demand local session memory (deja fix/wip/search). Use when an error occurs, resuming work in a repo, or past sessions matter.
The English summary is being prepared. Showing the original description.
Edit the source of a locally running app after a visual-edit item from plan-canvas. Posts a diff plan, edits one file after a yes. Not for remote sites.
The English summary is being prepared. Showing the original description.
Master software architect specializing in modern architecture
The English summary is being prepared. Showing the original description.
Scrape leads from multiple platforms using Apify Actors.
The English summary is being prepared. Showing the original description.
Interview a project folder into AOS: .aos/project.json, OpenWiki, memB memory, Synapse map, AGENTS.md. Use when onboarding a project to AOS.
The English summary is being prepared. Showing the original description.
agenttrail: the live map of a multi-agent build. Use when a /fabric pipeline runs, a plan-canvas approve lands, or agents run for a human to watch.
The English summary is being prepared. Showing the original description.
How BDB structures multi-agent build pipelines: the seven-node dispatcher graph /fabric-graph runs. Use for lifecycle framing.
The English summary is being prepared. Showing the original description.
Event agency operations: client intake, scoping, vendors, crew, production planning, logistics, wrap. Delegates technical execution to godmode-eventtech.
The English summary is being prepared. Showing the original description.