Audit of the library's AI/LLM skills found near-zero coverage of the newest agentic features. Adds 4 skills and upgrades 4, taking the library to 343 skills / 17 domains / 786 Python tools (engineering 82 -> 86). New skills (each: stdlib-only tools + reference knowledge bases): - extended-thinking-architect — reasoning-effort / thinking-budget decisions - batch-api-orchestrator — batch vs realtime, bulk job design - computer-use-automation — GUI/browser agent loop, reliability + safety - agentic-evaluation-framework — LLM-as-judge rubrics + pairwise ranking Enhanced: - llm-cost-optimizer — prompt caching / batch / reasoning-effort economics - context-engine — memory tool, context editing/compaction, 1M-context - agent-workflow-designer — subagent scoping + multi-model cost estimation - mcp-server-builder — streaming, batch, computer-use tool patterns All content is model-agnostic and principle-focused (no hardcoded prices or invented API signatures); all tools are stdlib-only with --json output and were compiled + run. Manifests, website (343 skill pages), and prose regenerated.
@borghei/claude-skills
Install any skill from the Claude Skills library into your AI assistant in one command.
npx @borghei/claude-skills add senior-fullstack
After a global install (npm i -g @borghei/claude-skills), the claude-skills binary is available directly.
Auto-detects Claude Code, Cursor, Codex, Gemini CLI, Copilot, Windsurf, Cline, Aider and Goose. Installs the skill into the right directory for whichever assistant you're using.
Commands
claude-skills list # All skills, grouped by domain
claude-skills list --domain engineering # Filter to one domain
claude-skills search "docker" # Match name, tags or description
claude-skills info senior-fullstack # Full detail for one skill
claude-skills add senior-fullstack # Install into the detected assistant
claude-skills add senior-fullstack --to cursor # Force target
claude-skills add senior-fullstack --dir ./my-skills # Install into a specific dir
claude-skills add senior-fullstack --force # Overwrite if already installed
claude-skills update # Update every installed skill
claude-skills update senior-fullstack # Update just one
claude-skills remove senior-fullstack # Remove an installed skill
claude-skills create my-new-skill # Scaffold a new skill from the template
Target detection
The CLI detects your AI assistant by looking for marker files in the current directory:
| Marker | Target | Install path |
|---|---|---|
.claude/ |
Claude Code | .claude/skills/<name>/ |
.codex/ or AGENTS.md |
Codex | .codex/skills/<name>/ |
.gemini/ or GEMINI.md |
Gemini CLI | .gemini/skills/<name>/ |
.cursor/ or .cursorrules |
Cursor | .cursor/rules/<name>/ |
.github/copilot-instructions.md |
GitHub Copilot | .github/skills/<name>/ |
.windsurfrules |
Windsurf | .ai-skills/<name>/ |
.clinerules |
Cline | .ai-skills/<name>/ |
.aider.conf.yml |
Aider | .ai-skills/<name>/ |
.goosehints |
Goose | .ai-skills/<name>/ |
If the CLI can't detect a target, pass --to <name> explicitly.
Lockfile
Installed skills are tracked in .claude-skills.json in the current directory. This file records what's installed, which target, and version, so update and remove work cleanly.
Requirements
Node.js 18 or later. No Python required for end users.
License
MIT + Commons Clause. See LICENSE.