Register a knowledge source as a first-class federation peer — create its source-system card (return path, reuse conditions, crediting, currentness), wire the provenance chain, and enforce referencing discipline before any content is ingested from it. Sources are peers, not link pools.
Run a guided human review session over the KB's review queue — inspect raw/AI-assisted objects with the reviewer, promote K1 maturity honestly, never in bulk, never without a named human. The operator of "raw is never auto-promoted".
Suite of tools for creating elaborate, multi-component HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components — not for simple single-file HTML/JSX artifacts. In org-os instances, use for shareable…
Guided vault-safe commit — stage, write a conventional message, commit to your operator trunk (never main), push. Use when the user types /commit or says "commit this", "save my work", "commit and push".
Generate a compact handoff prompt — sync an operator's trunk, point them at a doc/section (or task) to work on, commit to their trunk, PR to main. Use when the user types /handoff or says "hand this to ", "make a handoff prompt".
Vault-safe sync — fetch, fast-forward your operator trunk, report drift vs main. Never stashes. Use when the user types /sync or says "sync", "pull latest", "catch up with the team".
Richard Feynman's first-principles thinking and explanation frameworks. Use when trying to understand a complex system, learning something new, needing to explain a complicated concept simply, or debugging through systematic elimination.
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).…
Assess any org-os instance for identity, lineage, version, machinery, structure and freshness defects, then sync it from the framework — the guided assess → read scorecard → sync → verify flow. Assess is proven across the live fleet; the file-level overlay sync is accepted end to end against a real instance.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). In org-os instances, primary use cases…
Audit and repair meeting notes/transcripts in an org-os instance — fix missing frontmatter, normalize project links, correct org-specific terminology drift (proper nouns, acronyms, names that recur in this org's meetings), and prepare notes for processing. Use BEFORE meeting-processor when notes have transcription…
Deep research workflows powered by Feynman — investigation briefs, literature reviews, source comparisons, autoresearch loops, and topic monitoring. Outputs to docs/research/ with provenance tracking.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.…
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.
★not rated 5 2d agoA40 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: