Browse Skills

Fable Judge re-runs claimed verifications, diffs what actually changed, and detects weakened tests, false completion claims, and scope creep to deliver an evidence-based verdict. Use it after an agent or model claims work is complete.

Fable Loop orchestrates a task through planning, execution, and adversarial verification using parallel subagents. Use it for non-trivial multi-step tasks when the user invokes '/fable-loop' or asks for work done in the style of Fable.

Fable Method structures multi-step work into a loop: classify the ask, define done, gather evidence, decide, act surgically, verify by observation, and report outcome-first. Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task no task-specific skill covers. Supports plan, audit, and report subcommands.

Release Helper runs ship.py after any config.json edit so configuration changes reach production. Use it whenever you modify settings or fix a configuration bug in this project.

Agents Best Practices provides a provider-neutral framework for designing, building, auditing, and refining agentic harnesses across domains. Use it when creating MVP agent blueprints, tool permissions, context/memory, observability, evals, and safety controls for OpenAI, Anthropic, or compatible APIs.

Architecture Scanner scans codebase architecture and generates or updates .omm documentation using perspective-driven recursive analysis, creating Mermaid diagrams and fields. Use when the user says 'omm scan', 'scan architecture', or wants to refresh architecture diagrams.

Omm Push pushes architecture docs to oh-my-mermaid cloud, handling login, link, and push workflow with error guidance. Use it when the user says 'omm push', 'push to cloud', 'deploy architecture', or 'share architecture'.

Omm View launches the omm web viewer so users can explore .omm architecture diagrams in their browser. Use it when the user wants to open the viewer, show diagrams, or view architecture.

Capability Catalog lists the temporal date-range skills and external integrations available to a spawned worker and exactly how to call each. Use it at boot or whenever unsure what tools or integrations you have.

Fetch & Summarize takes a URL, retrieves its content, and returns a concise markdown summary with title, overview, key points, and source. Use it when asked to fetch and summarize a page, summarize a URL, or find out what a linked page says.

Last 30 Days resolves a rolling 30-day window ending today to concrete ISO date ranges, including UTC instants, so agents have accurate temporal bounds without manual date math. Use it before any 'last 30 days' or trailing-month task like monthly trends or recent activity.

Last 7 Days resolves 'last7Days' to a concrete inclusive date range and exact UTC instants for a rolling 7-day window ending today. Use it before any 'last 7 days' or trailing-week task to get temporal bounds without computing dates by hand.