Builds a sponsor-ready business case covering costs, benefits, risks and evidence when you need budget or timeline approval.
A step-by-step playbook for designing, implementing, hardening, and verifying production-grade MCP servers.
Designs and verifies auditable human approval gates, escalation paths, and safe state transitions for risky AI agent actions.
Scores any text across nine AI-tell signal categories and returns a structured report with quoted evidence and concrete fixes.
A step-by-step skill for listing tables, describing columns and types, and mapping foreign-key relationships in a database.
x
A skill for designing reproducible AI agent evaluations with representative datasets, rubrics, graders, regression gates, and a release decision memo.
A dense rulebook for Obsidian plugin development: ESLint rules, API conventions, accessibility, and the community submission workflow.
A skill for designing privacy-aware traces, spans, metrics, alerts, and investigation runbooks for AI agents.
Takes a video plus an SRT and either burns the subtitles into the pixels with libass or soft-muxes a togglable track, and can mix a dub over the original audio in a single ffmpeg pass.
Drives the Superdesign CLI to design UI, slide decks, posters and image/video assets on an infinite canvas across multiple frontier models.
Forces Claude to use trace-mcp's apply_codemod for any edit pattern repeated 2+ times instead of firing off repetitive Edit calls.
A routing skill that makes Claude use trace-mcp's semantic code tools instead of Read/Grep/Glob, cutting tokens while improving accuracy.
Joins your kasetto install lock with each agent's session history to show which skills and MCP servers are actually used, and renders an HTML usage dashboard.
The designer lane of codeck: reads deck.md, defines a validated design system, and assembles a single self-contained HTML presentation.
An editor-role skill that reads your local materials, asks the few questions that matter, and writes deck.md with the full story arc and slide-by-slide outline.
Turns your Git history into a categorized CHANGELOG.md with a Semantic Versioning bump suggestion.
Joins your kasetto lock file with each AI agent's local session history to show which installed skills and MCP servers are actually used, and renders an HTML dashboard.
The official operating manual that teaches Claude to build widgets and views for a moi web workspace, plus theming, env handling and verification.
Turns Chinese text into two-host conversational podcast audio using Volcengine's Podcast AI model.