Agent skills for Claude Code

Run the Omnigent load test and produce a results file explaining the latencies.

Cost-safety discipline for paid AI / inference APIs: treat $-cost as a third complexity dimension alongside time and space.

Create or update an operational runbook for a recurring task or procedure.

Facilitates the creation, maintenance, and drill planning of operational runbooks to improve incident response readiness.

Guide runbook writing, maintenance, drill exercises, and coverage reporting. Any deploy runbook that includes a destructive-update pattern…

Generate and update feature release runbooks from existing docs and codebase.

Run any model on RunComfy from the command line.

Creative ideation and solution exploration.

Root cause analysis for bugs and unexpected behavior.

Deploy + marketing orchestrator. Use when user says 'launch', 'ship to production', 'deploy and announce', or 'go live'. Runs the full…

Build Model Context Protocol servers from specifications.

Performance regression gate. Detects N+1 queries, sync-in-async, missing indexes, memory leaks, and bundle bloat before they reach…

Web search and external knowledge lookup.

Engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with trend tracking. Per-person breakdowns…

Generate Marp-compatible slide decks from structured JSON schema.

Choose Sail automatically when available, fall back cleanly to host PHP/Composer/Node; paired command map for both environments

Fit, summarize, plot, and interpret a chosen CausalPy experiment.

Author and run declarative YAML workflows on the Marshal fleet - reusable orchestration recipes (fan a goal out across clients, collect…

Performs placebo-in-time sensitivity analysis with hierarchical null model and optional Bayesian assurance.

numbagg-specific guidance for tend CI workflows.

Runs real-user QA, manual test plans, UX bug hunts, build sign-off, bug filing, and bug triage for web or iOS/iPadOS apps.