A checklist-driven skill that bumps the version across every manifest, then builds, tags, publishes a GitHub release, and regenerates the changelog.
Teaches the agent when and how to use language-server tools for diagnostics, definitions, references, and safe renames.
Copies, registers, and validates the Cisco Webex channel adapter for a NanoClaw project in one guided pass.
Turns a vague bug complaint into a source-backed GitHub issue or PR routed to the repository that actually owns the defect.
A release gate skill that fans out 16 parallel agents to audit every unpublished change and returns a SAFE/CAUTION/RISKY/BLOCK verdict before you npm publish.
An isolated-environment QA skill that proves omo Codex plugin hooks, installer, and TUI work without ever touching your real ~/.codex.
Turns Claude into an orchestrator that dispatches subagents to implement, verify, and only then commit each phase of a plan.
An orchestrator skill that executes a phased implementation plan through dedicated subagents, verifying each phase before committing.
Installs OpenAI's Codex app-server as a first-class agent backend for NanoClaw, switchable per group.
A reference skill that guides Claude to design PostGIS tables with the right geometry types, SRIDs, indexes and query patterns.
Launches a local web dashboard that visualizes your codebase's knowledge graph.
Turns your PRD and Tech Design docs into a complete AGENTS.md, MEMORY.md and per-tool AI configuration set.
A battle-tested playbook mapping real Terraform provisioner, multi-environment, and first-deploy failures to copy-paste fixes.
Runs parallel AI agents to audit your product's UX, API, architecture and docs, then synthesizes a prioritized optimization report.
Scaffolds a React + Tailwind + shadcn/ui project and bundles it into a single self-contained HTML artifact.
A reference skill explaining which project rule files Codex Rules injects and which environment variables control it.
Diffs HEAD against the latest published npm versions and reports every unpublished change grouped by release layer, with per-layer version bump advice.
Lets Claude write and run custom Playwright scripts to test sites, capture screenshots, and automate logins and forms.
Turns an experiment blueprint JSON into a runnable Python project skeleton with models, training, evaluation, and ablation configs.
A reference skill that feeds Claude the architecture, naming rules, and tool/command patterns of the Claude Code CLI codebase.