🔧
AI EngineeringTypeScript

Skill Tuning

by catlog22

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

2.1K stars164 forkson catlog22/Claude-Code-WorkflowAdded 2026/08/18Repository updated 2026/06/18
View source on GitHubDownload repo ZIP
claudeclaude-codecli-toolscodexcontext-managementgemini-clijson-drivenqwen-codetask-orchestrationworkflow-automation
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/Claude-Code-Workflow/tree/main/.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/Claude-Code-Workflow.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/Claude-Code-Workflow
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 fixes skill execution issues such as context explosion, long-tail forgetting, data flow disruption, and agent coordination failures. Use it to run diagnosis, apply fixes, and verify quality gates for any skill.

Skill Tuning is cataloged under AI Engineering on DirSkills. Skill Tuning comes from a repository tagged claude, claude-code, cli-tools, codex and context-management.

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/Claude-Code-Workflow, the repository it ships in. Its siblings there include Brainstorm, CCW Chain and CCW Help. 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/Claude-Code-Workflow page.

  • How does Skill Tuning compare to other AI Engineering skills?

    Skill Tuning ranks #860 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.

More from catlog22/Claude-Code-Workflow

Skill Tuning is one of 25 skills cataloged on DirSkills from catlog22/Claude-Code-Workflow.

See all 25 skills →
🧠
2w ago

Brainstorm

Brainstorm is a unified brainstorming skill that guides Claude Code through interactive framework generation, parallel multi-role analysis, and cross-role synthesis. Use it when you need structured ideation, role-based analysis, or feature specifications for a project.
AI Engineering
2.1K164
⛓️
2w ago

CCW Chain

CCW Chain orchestrates chain-based workflows through intent analysis, routing, and progressive skill pipeline execution. Use it to route tasks to workflow chains and execute multi-step Claude Code workflows.
Automation
2.1K164
🔍
2w ago

CCW Help

CCW Help provides an in-context help system for the CCW workflow, allowing users to search commands, get recommendations, and browse skills and teams. It triggers on keywords like ccw-help and ccw-issue.
Automation
2.1K164
🔍
2w ago

Delegation Check

Delegation Check validates workflow delegation prompts against agent role definitions to detect content separation violations. Use it to catch conflicts, duplication, boundary leaks, and missing contracts in Claude Code skills.
AI Engineering
2.1K164
🐞
2w ago

Frontend Debug Team

Frontend Debug Team orchestrates multi-agent frontend debugging using Chrome DevTools MCP, with dual pipelines for feature-list testing and bug-report debugging.
Quality
2.1K164
🔍
2w ago

Investigate

Investigate is a systematic debugging skill that enforces the Iron Law: never fix without a confirmed root cause. It walks through 5 phases from evidence collection to verified fix, producing structured debug reports.
Quality
2.1K164

More AI Engineering skills

Skill Tuning is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #860 by stars among them.

Browse all AI Engineering skills →
📐
3w ago

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.
AI Engineering
239.8K36.4K
🤖
3w ago

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.
AI Engineering
239.8K36.4K
🤖
3w ago

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.
AI Engineering
239.8K36.4K