Skill Tuning

by catlog22

Skill Tuning is an AI Engineering skill for Claude Code, published by catlog22 in maestro-flow.

530 stars65 forkson catlog22/maestro-flowAdded 2026/08/26+1% in starsRepository updated 2026/08/24

View source on GitHub Download repo ZIP

ai-agentsclaude-codeclicodexgeminiknowledge-graphmcpmulti-agenttypescriptworkflow-orchestration

Install in seconds

Install Skill Tuning

Copy Skill Tuning into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/catlog22/maestro-flow/tree/master/.claude/skills/skill-tuning ~/.claude/skills/skill-tuning

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/catlog22/maestro-flow.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .claude/skills/skill-tuning/SKILL.md in catlog22/maestro-flow
Installs to: ~/.claude/skills/skill-tuning
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Skill Tuning does

Skill Tuning diagnoses and repairs Claude Code skill execution problems such as context explosion, memory loss, data flow disruption, and coordination failures. Use it when a skill is producing inconsistent results or needs optimization.

Skill Tuning is cataloged under AI Engineering on DirSkills. Skill Tuning comes from a repository tagged ai-agents, claude-code, cli, codex and gemini.

Documentation

README

Excerpt

<required_reading> @~/.maestro/workflows/run-mode.md </required_reading>

Skill Tuning

Autonomous diagnosis and optimization for skill execution issues.

Pre-load (before execution)

Codebase docs: If .workflow/codebase/ARCHITECTURE.md exists, read for project context
Specs: maestro load --type spec --category coding — load coding conventions
Wiki knowledge: maestro search "skill design optimization" --json — top 5 entries as prior context
All optional — proceed without if unavailable

Architecture

This is the opening of the README. Read the full README on GitHub.

Commands Skill Tuning provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/skill-tuning

Frequently asked about Skill Tuning

What else does catlog22 publish alongside Skill Tuning?
Skill Tuning is one of 25 skills that DirSkills catalogs from catlog22/maestro-flow, the repository it ships in. Its siblings there include Maestro Companion, Maestro Fork and Maestro Guard. Each one is a separate skill with its own page in this directory, installs the same way Skill Tuning does, and is maintained by catlog22 in that same repository. The rest of the collection is listed on the catlog22/maestro-flow page.
How does Skill Tuning compare to other AI Engineering skills?
Skill Tuning ranks #2093 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Skill Tuning against them. Open each page to compare what they document and how they install.