All Skills

Debug and recover from agent team errors including common errors, hooks for quality gates, known limitations, and recovery strategies. Use when encountering team errors, enforcing quality gates with hooks, understanding limitations, or debugging agent issues.

# Video Breakdown A professional video analysis skill powered by a **dual-model architecture**: ByteDance **Seed-2.0-Mini** for rapid previews and Google **Gemini 2.5 Pro** for deep, cinematic-grade analysis. It provides quantitative quality assessments and meticulous shot-by-shot breakdowns (拉片)

Use when defining a feature, writing a PRD, or scoping work - reframes requirements around the user's job instead of the feature or team that owns it. Use before design or development begins.

Use when writing or reviewing UI copy - rewrites labels, CTAs, helpers, and placeholders through a Jobs to Be Done lens so every element reflects the user's actual goal, not the system's internal model.

Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing features for parallel development, establishing file ownership boundaries, or managing integration between parallel work streams.

Guide an end-of-session reflection to capture learnings and feelings. Use when finishing a work session, after completing a challenging task, when wanting to consolidate what was learned, or to build a personal learning log over time.

Build reusable Terraform modules for AWS, Azure, and GCP infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.

Act as an experienced Product Owner to manage product backlogs, write user stories, define acceptance criteria, prioritize work, and align stakeholders. Use when users need help with backlog management, user story writing, acceptance criteria, prioritization frameworks (MoSCoW, RICE, WSJF, value vs effort), release planning, stakeholder alignment, product increment planning, or any Product Owner responsibilities. Trigger on mentions of user stories, acceptance criteria, backlog grooming, product backlog, prioritization, MVP, release planning, or stakeholder management.

Use when reviewing, auditing, or improving existing E2E test specs. Triggers on tasks like "review tests", "improve test quality", "audit specs", "check test scenarios". Detects naming-assertion mismatch, missing Then, error swallowing, always-passing assertions, boolean traps, conditional bypass, raw DOM queries, render-only tests, duplicate scenarios, misleading names, over-broad assertions, hard-coded timeouts, flaky selectors, and YAGNI violations in Page Objects.

Three-agent adversarial legal analysis methodology — advocate/adversary/judicial workflow, argument scoring, objectivity validation, and Swiss Erwägung synthesis structure

Swiss data protection law — nDSG/FADP framework, GDPR adequacy assessment, cantonal data protection laws (IDG/KDSG/LIPAD), DPIA methodology, and cross-border data transfer mechanisms

Swiss financial regulatory compliance frameworks — FINMA supervision, GwG/AMLA anti-money laundering, FIDLEG/FINIG financial institution licensing, banking secrecy, and cross-border compliance requirements

Swiss legal citation formatting across DE/FR/IT/EN — BGE/ATF/DTF Federal Supreme Court decision formats, statutory article citations (Art./Abs./lit./Ziff.), doctrine references, cantonal court citations, and abbreviation tables for all Swiss official languages

Guide for writing idiomatic, effective, and standard Go code. Use this skill when writing, refactoring, or reviewing Go code to ensure adherence to established conventions and best practices.

Auto-activates structured briefing sessions for complex legal queries -- detects when multi-agent coordination benefits from pre-execution intake and plan building

Persist plans and tasks across Claude Code sessions. Use when starting multi-step work, resuming incomplete plans, or updating task progress.

Generates user-friendly changelogs from git history using conventional commits. Writes entries in benefit language ("You can now..." not "Refactored internal..."). Follows Keep a Changelog format. Use when creating or updating CHANGELOG.md.

Webhook relay SDK and CLI integration for pgns

Generate professional, evidence-backed research reports for crypto projects.

Use when you need a conservative Morpho Vaults leaderboard across Ethereum/Base/Arbitrum with strict exposure-asset allowlists and liquidity/whitelist filters.

Aggregates crypto news from multiple sources and generates curated daily markdown reports with automated scoring and deduplication.

Use when external agents must construct PubFi DSL requests for OpenSearch and Postgres without server-side natural language compilation.

Swiss litigation strategy including case strength analysis, risk assessment, procedural strategy (ZPO), cost-benefit analysis, settlement evaluation, and alternative dispute resolution for Swiss federal and cantonal courts

API design system in the AEP (API Enhancement Proposals) collection. AEPs provide high-level, concise documentation for API development, serving as the source of truth for consistent, intuitive, and machine-readable API designs. Use this skill when designing, reviewing, or implementing APIs to ensure compliance with these established standards.