Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Use whenever you run a Makefile target (e.g. make travis_build, make test, make reasoned.ofn) or any one-off ROBOT / owltools / dosdp-tools / scala-cli command derived from a Makefile recipe. These must run inside the pinned ODK Docker image, not against host tools. Covers validation, reasoning, imports, and release builds in src/ontology.
Provides multi-agent workflows for Zed Agent and zcode. Supports broad work across multiple files with planning, parallel execution, verification, and resumption after crashes.
Use when Atlas diagrams need refresh from change-watch metadata.
Use when Atlas Mermaid catalog diagrams need rendering or rendered artifacts need verification.
Use when grounded Radar backlog workstreams must be created from source-backed product evidence.
Use when Radar backlog records or plan-linkage contracts need validation.
Use when concrete Odylith failure evidence needs a Casebook bug with grounded repro details.
Use when an Odylith bug record needs investigation, evidence gathering, and governed-surface linkage.
Use when an Odylith Casebook bug create or update needs prerequisite checks.
Use when a slice shows duplicate helpers, fake modularization, oversized-file pressure, or AI-shaped code slop that needs explicit cleanup discipline.
Use when Compass state, standup briefs, or executive summaries need interpretation for the active Odylith slice.
Use when a bounded execution note needs to be appended into Compass.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name