Productivity & Workflow Agent Skills for HTTP / API

Move a family photo library off Google Photos onto self-hosted Immich, with a backup that actually restores.

Global TypeScript-first engineering router.

Skills required for structured analysis of Brazilian contracts to support legal counsel.

Acquisitions, financings, property, and other corporate/commercial transactions - due diligence, conditions tracking, closing mechanics.

Pure verification pass over already-drafted legal material - checking every citation, quotation, fact, and procedural claim against a…

Primary router for legal tasks - research, drafting, review, evidence, litigation, contracts, regulatory, transactions, academic work…

Draft letters of support, letters of collaboration, and consultant/resource-access letters for grant applications.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.

This guide walks through setting up the claude-mem plugin on an OpenClaw gateway.

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce…

This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly…

Execute a phased implementation plan using subagents.

This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for…

Upgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to…

Create a detailed, phased implementation plan with documentation discovery.

Comprehensive market sizing methodologies for calculating Total Addressable Market (TAM), Serviceable Available Market (SAM), and…

Search claude-mem's persistent cross-session memory database.

Use when planning or building a SaaS MVP from scratch.

Use when you have a spec or requirements for a multi-step task, before touching code

Configure which models pstack uses per role.

Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).