Design and audit Claude Code tooling artifacts like SKILL.md and CLAUDE.md.
npx skills add https://github.com/lgerard314/global-plugin --skill org-ai-tooling
Please help me install this Agent Skill. Skill: org-ai-tooling Source: https://github.com/lgerard314/global-plugin/tree/main/plugin/skills/org-ai-tooling Command: npx skills add https://github.com/lgerard314/global-plugin --skill org-ai-tooling
Senior-engineer mindset for Claude Code tooling — plugins, skills, hooks, subagents, MCP servers, and the Agent SDK. The harness is the product. Every problem is a question of: where does this work live, and which primitive is it? Activates on tooling-file edits and tooling-design tasks. Explicitly does not activate on app code — consumer guard skills cover that.
The persona to inhabit: a senior engineer at Anthropic whose day job is building with Claude Code, thinking the way Karpathy thinks when he vibe-codes a 2,000-line AI project over a weekend — first-principles, empirical, minimal, composable, tasteful. The harness spec is known cold; primitives are reached for instinctively, without ceremony.
This skill provides the vocabulary, patterns, and guardrails for designing safe, scalable tooling works; it does not edit consumer app code.
Design and audit Claude Code tooling artifacts when editing tooling files such as SKILL.md, CLAUDE.md, or agent specifications.
High-intent search queries and answers about installing and using this skill.
To design safe Claude Code tooling, apply primitives, patterns, and harness rules that guide deterministic tooling design for SKILL.md, CLAUDE.md, agent specs, hooks, and MCP configurations. This approach ensures scalable and safe tooling works.
Claude Code primitives like Subagents, Hooks, and MCP servers serve distinct roles in the harness. The skill provides clear separations of these primitives and patterns to help you determine where specific work lives within your plugin projects.
No, this tooling guidance explicitly does not activate on consumer app code. It is designed strictly for designing and auditing Claude Code tooling artifacts, while separate consumer guard skills cover application code editing.
To write hooks for deterministic Claude Code tool life-cycle management, follow the hooks and scripts guidance provided by the skill. This ensures safe, scalable tooling by applying progressive, context-aware patterns to your tooling files.
You need to audit Claude Code MCP configurations and agent specs when editing tooling files within plugin projects. The skill applies a senior-engineer mindset to evaluate these artifacts against known harness rules and best-practice patterns.
biwakonbuMigrate CLAUDE.md content into .claude/rules files with references.
Folken2Implement lifecycle hooks for the Claude Agent SDK to manage agent behavior.
phrazzldSynchronize Spellbook primitives from a manifest across Claude Code, Codex, and Pi.
rhpdsCreate Claude Code hooks that guard and monitor tool execution workflows.
