Agent skills for Claude Desktop

Honestly evaluate AI work quality using a two-axis scoring system.

CI-only self-healing workflow using gh-aw (GitHub Agentic Workflows) for active runtime recovery on pull requests and scheduled runs.

CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows).

Curate Claude Code's auto-memory into durable project knowledge.

Analyzes self-media performance data to provide actionable content optimization strategies and data-driven growth insights.

Generates structured creative briefs for multi-platform social media content based on minimal user input or raw materials.

Transforms account positioning and business goals into actionable social media content strategies and editorial calendars.

Automates the end-to-end self-media content lifecycle from strategy and trend research to multi-platform copywriting and performance…

Transforms research and briefs into high-converting, platform-native content for X, Xiaohongshu, WeChat, and short video platforms.

Analyzes social media trends and competitor content to generate original, data-driven topic ideas and content structures.

Tiers, checkpoints, and off-limits paths for an agent editing the app's own source.

SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning…

Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification

Build the thing from scratch — implement the core functionality yourself instead of wrapping an existing library, framework, or service…

Scanning Electron Microscopy with Energy Dispersive X-ray Spectroscopy skill for morphology and elemental analysis

Checks document semantic content against SCOPE and project goals, coverage gaps, off-topic content, SSOT.

Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API.

Automate Semanticscholar tasks via Rube MCP (Composio).

Sends a plan file to Monocle and blocks until the reviewer responds with feedback.

Hunting skill for cache poison vulnerabilities.

Automate Sendbird AI Chabot tasks via Rube MCP (Composio).