Connect an AI agent client to Memory Proxy, which adds team memory, skills, and knowledge to model requests. The guided workflow checks existing settings, tests connectivity, and writes the appropriate client configuration.
Install and configure the memory-tencentdb plugin for OpenClaw to retain and retrieve conversation information. Verify the setup through logs and searches, adjust memory settings, and troubleshoot missing recall or vector search results.
Run Python code and Shell commands in an isolated Cube Sandbox environment. The skill covers file access, host directory mounting, network restrictions, and pausing and resuming execution while preserving the sandbox's memory state.
Build, test, and format CubeSandbox components using make targets and a Docker builder. Also covers the web dashboard’s development workflow, API type synchronization, and troubleshooting for missing services, outdated build tools, and environment requirements.
Assess operational risks in processes, projects, or suppliers using provided evidence. Separate observed facts from possible consequences, propose practical responses, and prepare concise summaries or risk registers without treating unknown controls as confirmed gaps.
Compare supplier quotes and renewal options by cost, service terms, operational fit, and contract risks. Get calculations for the requested period and, when needed, conditional recommendations based on stated priorities.
Write reusable operating procedures for recurring business tasks and handovers. Organize prerequisites, roles, steps, success checks, and exception handling, while clearly separating approved recovery actions from decisions that still need confirmation.
Turn work records, performance metrics, and authorized project information into weekly or monthly status reports. It checks calculations, highlights progress and unresolved issues, and marks missing information without inventing plans or assigning unsupported ratings.
Analyze waiting, rework, and handoff waste in business processes using the facts provided. It proposes concrete improvements and, when verification is needed, defines measurement formulas and the minimum records required to assess specific issues.
Turn existing or proposed business processes into reusable standard operating procedures. Organize steps, roles, conditions, and known exceptions while marking missing details, producing clear handover documents without inventing approvals or responsibilities.
Compare assigned work from connected trackers with TASKS.md, review stale tasks, and fill gaps in stored context about people and projects. An optional comprehensive scan finds possible missed commitments in recent activity, with changes confirmed by the user.
Manages tasks in a shared TASKS.md file that both the user and agent can edit. Adds commitments, records deadlines, tracks waiting items, and moves finished work to Done, with a dashboard for visual organization.
Prepare a deployment checklist covering tests, approvals, database changes, release steps, and monitoring. Tailor it to the release and document rollback triggers, the conditions for reverting a change, before production deployment begins.
Plan tests for APIs, interfaces, data pipelines, and infrastructure. Choose suitable test types, prioritize critical behavior, and produce a plan with coverage targets and example cases while balancing thoroughness, execution speed, and maintenance effort.
Investigate errors and unexpected behavior through reproduction, isolation, diagnosis, and a proposed fix. Receive a structured report covering the root cause, necessary code or configuration changes, and suggested tests to prevent the issue from returning.
Adapt a Claude Code or Cowork plugin to an organization's tools and workflows. Update instructions, team settings, and service connections, then package the customized files for installation while preserving the plugin's original name.
Review a Figma design, screenshot, or written description for usability, visual hierarchy, consistency, and accessibility. Receive specific findings, explanations, and prioritized improvements, with feedback tailored to the design stage and intended users.
Help Claude interpret workplace shorthand by storing people, acronyms, project names, and preferences in local files. Keep frequent references in CLAUDE.md and detailed context in memory/, so requests can be understood using recorded workplace knowledge.
Compare technology options, review a system design, or plan a new component from requirements and constraints. The skill organizes the reasoning into an architecture decision record, a document covering alternatives, trade-offs, consequences, and next steps.
Plan a system or service from requirements through components, APIs, data storage, and reliability. Produce a structured design document with diagrams, stated assumptions, trade-offs between choices, and decisions to revisit as usage grows.
Identify maintenance problems across code, architecture, tests, dependencies, documentation, and infrastructure. Rank them by impact, risk, and effort, then produce a prioritized backlog with business reasons and a phased improvement plan alongside feature development.
Write and review interface text, including button labels, error messages, empty screens, and onboarding instructions. Get recommended wording, alternatives, and explanations tailored to the user's situation, tone, and character limits.
Turn recent work or rough notes into a concise daily standup update organized by yesterday, today, and blockers. Connected tools can supply commits, pull requests, ticket changes, and relevant discussions to help assemble the report.
Create a Claude Cowork plugin through guided conversation, from defining its purpose to designing components and checking files. Receive a packaged .plugin file containing the skills and integrations needed for the agreed workflow.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)