Agent skills for Devin Desktop

The repo's plan and its task files -- reading, updating, or pruning them.

Light underwater caustics, murk, and shafts.

Use when the user explicitly asks to diagnose skill context overhead, determine whether a skill should be isolated, apply an approved…

Any deviation from the system recommendation requires a substantial justification.

Maintain a strategic development log inside a user's modpack project.

Generate player-facing release notes for a modpack update.

XClaw Intelligence Skill. Provides real-time trending tweets, KOL deep analysis, live user crawling, profile history, and social relation…

Validate Claude Code skills against the agentskills specification.

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant…

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity.

Deploy applications to Vercel with edge functions, serverless, and ISR.

Organizes, inspects, categorizes, and synchronizes AI agent skills across Claude Code, Cursor, Codex, Gemini, and Hermes.

Local-first analytics for AI agent skills.

Use when the user wants their Claude agent to self-improve from past usage, asks about a nightly/offline 'sleep' or 'dream' cycle…

Skills are structured best practices and patterns for building XMTP agents.

Chief AI Officer advisory for startups: model build-vs-buy decisions (API vs fine-tune vs in-house), AI risk classification under EU AI…

Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated…

Use when adding, retiring, or auditing feature flags.