All skills
AgentDB Advanced Features
A reference skill that teaches Claude AgentDB's advanced side: QUIC sync, hybrid vector+metadata search, multi-DB sharding, MMR and production patterns.
German AGB Change-Reservation Clause Checker (§308 No. 4 BGB)
Reviews unilateral change-reservation clauses in German standard terms against §§305–310 BGB and returns a risk verdict plus safer replacement wording.
Desk Execution Protocol (Hyperliquid)
An execution trader's protocol for turning an approved ticket into exactly one Hyperliquid send and fully reconciling the outcome.
Abstract Domain Explorer
Applies abstract interpretation with interval, sign, congruence, octagon, and polyhedra domains to infer variable ranges and loop invariants without running the code.
Terraform Module Reviewer
A strictly read-only reviewer for changes to reusable Terraform modules that returns structured findings.
Night Market Build & Env Bootstrap
Rebuilds the claude-night-market dev environment from a bare machine and verifies it in under an hour, with a documented traps table.
Night Market Architecture Contract
Documents the load-bearing design decisions, enforced invariants, and known weak points of the claude-night-market repo for judging design changes.
Night Market Change Control
Repo-specific skill that classifies changes and enforces the gate, PR and release process when landing code or amending rules.
Event-Driven Messaging (Spring Boot 3)
Guardrails for building Kafka, RabbitMQ, Pulsar, and JMS producers/consumers in Spring Boot 3 with versioned event contracts, idempotency, bounded retries, DLQs, and the transactional outbox.
Night Market Completion-Integrity Campaign
A five-phase (P0–P4) executable campaign that binds an autonomous loop's "done" signal to gates the agent cannot fake.
Han Release Cutter
Cuts a full release: changelog section, per-plugin version bumps, per-plugin tags, and a GitHub release — with approval gates before anything irreversible.
Balanced Coupling (Modularity Design Model)
A reference skill that evaluates coupling across integration strength, distance, and volatility to guide split-or-merge and architecture decisions.
Modular High-Level Design (Balanced Coupling)
Turns a functional requirements file into a coupling-balanced modular architecture plus per-module design docs, test specs, and an architecture overview.
PMAX Copy Production & Review
Builds and audits Google Performance Max text assets — 15 short headlines, 5 long headlines, 5 descriptions — anchored to one need scenario and real landing-page evidence.
Contributor Issue Pipeline Gardening (awesome-claude)
A scheduled maintenance skill that closes already-shipped issues and keeps a curated 15–25 issue contributor backlog for the awesome-claude repo.
Agent Observability
A skill for designing privacy-aware traces, spans, metrics, alerts, and investigation runbooks for AI agents.
Human in the Loop (Approval Gate Design)
Designs and verifies auditable human approval gates, escalation paths, and safe state transitions for risky AI agent actions.
Agent Evaluation Design
A skill for designing reproducible AI agent evaluations with representative datasets, rubrics, graders, regression gates, and a release decision memo.