All skills

A bounded multi-agent command protocol that splits genuinely independent work across 5–100+ isolated workers, verifies outputs independently, and integrates serially.

Redesigns a personal or team operating system as a supervised learning loop with Four-C diagnostics and one bounded, reversible experiment.

An advanced playbook for designing or refactoring agent-based engineering workflows with bounded autonomy, custom evals, durable state, and verified write-back.

A blueprint skill for building, structuring, and publishing reusable Convex components.

An orchestration-discipline skill for dispatching independent, non-overlapping tasks to parallel workers or named role sessions while collecting observed runtime evidence.

A rulebook for delegating independent, non-overlapping tasks to parallel agent workers or selected persistent role sessions.

A judgment skill that returns a single artifact-free CONTINUE/STOP verdict on whether a work traversal earns its cost or is just process ceremony.

Audits the skill-improvement handoff files dropped into `.turbo/handoff/`, applies the ones you approve, clears the consumed files, and commits and pushes.

Delegate code review, research, and debugging to Google's Antigravity CLI (agy) as an independent second agent.

A hands-on guide for hardening ROS2 robots end to end: SROS2/DDS encryption, network segmentation, secrets, container security, and cyber-physical safety.

A gated end-to-end runbook for releasing Compass: sync main, bump versions, open the PR, tag the merge commit, build six platforms, and verify every download.

Sends one question to several Chinese AI platforms, preserves each raw answer and citation, aligns the claims point by point, and verifies them with authoritative evidence across four separate reports.

A 9-step pipeline that pulls a Zoom recording, adds intro/outro, builds timecodes and a thumbnail, uploads to YouTube, and files it in a playlist.

Analyzes German cease-and-desist letters over unfair T&C clauses and drafts a narrowed cease-and-desist undertaking with cost and risk assessment.

A static-analysis skill that uses abstract interpretation to summarize execution paths, variable ranges, and loop invariants without running the code.

A runbook skill for deploying TestDriver test infrastructure to AWS via CloudFormation, with EC2 instances spawned and terminated automatically per Vitest test.

Turns a single baseline character image into an identity-locked, transparent 14-frame game animation sequence.

A repo-specific conventions skill that teaches Claude the Claude Code CLI codebase layout, tool/command patterns, and naming rules.

Runs a real-user QA pass on your app and produces P0/P1/P2 bug reports, an HTML QA dashboard, and a YES/NO ship verdict.

A repo-maintenance skill that audits and fixes every skill, agent, index, and cross-reference doc in the Han plugin repository.