All skills

A PASS/FAIL checklist skill that optimizes medical-AI papers — title, abstract, summary box, preprint, repo and model cards — so AI search engines and RAG tools find and cite them correctly.

A senior-engineer rulebook that drives a Compose/CMP feature end to end — Contract, ViewModel, Screen, navigation, DI and tests — with no TODOs or stubs left behind.

An opinionated architecture contract for Jetpack Compose / Compose Multiplatform apps covering module graph, MVI, error tiers, state ownership, Koin DI and Navigation 3.

Owns project- and build-level work for Compose / Compose Multiplatform apps: bootstrapping, incremental adoption, module creation, convention plugins, version catalog and CI guards.

Generates an AI creator speaking an approved script as multiple takes with one consistent face, room and voice, then joins them into a single continuous track.

Generate or edit images with any FAL image model, routed through the GooseWorks proxy so calls are billed to the Ads agent.

Extracts Feishu/Lark docs, wiki collections, sheets and Minutes transcripts into faithful local Markdown via the lark-cli API.

A battle-tested playbook that maps real Terraform provisioner and multi-environment failures to exact root causes and copy-paste fixes.

Turns any Claude Code skills repo into an official plugin marketplace — generating, validating, install-testing, and PR-ing marketplace.json.

When the Bigdata.com (RavenPack) MCP only returns synthesized prose, this skill drops to the official SDK and /v1 REST endpoints for raw financials, prices, estimates and sentiment.

Safely diagnose and edit openclaw.json to switch OpenClaw models and repair 401, "no available channel", and thinking-level errors.

A maintenance skill that detects, syncs, and cleans up drift between your local skill source repos and Claude Code's plugin cache.

A parallel six-inspector audit workflow for a Claude Code skills marketplace repo that verifies every serious finding before reporting it by priority.

An evidence-driven, falsification-first playbook for tracking down network, streaming and protocol bugs where the obvious cause is usually wrong.

Sets up isolated Claude Code CLI profiles so you can run Kimi, MiniMax, GLM, DeepSeek and Anthropic side by side in separate terminal windows.

Picks the correct semver bump for a change set and synchronizes every version surface in the repo plus the matching GitHub milestone.

Orchestrates a 2-layer parallel agent hierarchy for large refactors, multi-file migrations, and codebase-wide audits.

Splits huge data workloads into batches, runs them across parallel sub-agents, and merges everything back into one validated output.

Turns Claude into a CMMC 2.0 / NIST SP 800-171 consultant for gap assessments, SSP drafting, SPRS scoring and POA&M management in the US defense supply chain.

Drive a kitty-graphics terminal app headlessly in a pty and produce a recorded video, timeline and checks summary as the deliverable.