Agent skills for Claude Desktop

This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration…

This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task…

This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy…

This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery…

This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm…

This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at…

Analyze music/audio files locally without external APIs.

Generate a new song from a creative brief (genre, mood, language, BPM, theme) via the cogmusic MCP create_production tool

Use this skill when the user requests to generate, create, compose, or produce music or songs — background music, theme songs, jingles, or…

Fetch metadata and audio_url for a single production by id

Extract MIDI/score from an existing production

Streams and controls online music playback directly from your terminal using mpv and multi-source fallbacks.

Optimize and format prompts specifically for AI music generation platforms like Suno and Udio, including platform-specific syntax and tag…

Run 4-stem separation (vocals/drums/bass/other) on an existing production

Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to…

Integrate Apple Music playback, catalog search, and Now Playing metadata using MusicKit and MediaPlayer.

Run Stryker mutation testing on a single source file and return a structured, token-frugal report that's pipeable to a follow-up…

Overview of Experimental MVCC feature - snapshot isolation, versioning, limitations

The MVP scope policy: the justification standard applied when the goal is to prove or disprove a hypothesis with the smallest thing that…

Example skill demonstrating Anthropic SKILL.md format.

Show all Linear issues assigned to you