workspace-surface-audit

Audit repo, MCP servers, plugins, and env surfaces to recommend ECC-native skills and workflows.

2|Updated Mar 29, 2015
One-click install
npx skills add https://github.com/ovisan/dotfiles --skill workspace-surface-audit-ovisan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: workspace-surface-audit
Source: https://github.com/ovisan/dotfiles/tree/main/.agents/skills/workspace-surface-audit
Command: npx skills add https://github.com/ovisan/dotfiles --skill workspace-surface-audit-ovisan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? When setting up Claude Code or evaluating a workspace, it is hard to know which capabilities are already available, which are only partially covered, and which integrations are missing entirely. This Skill performs a read-only audit of your repo, MCP servers, plugins, connectors, and environment surfaces, then recommends the highest-value ECC-native skills, hooks, agents, and operator workflows to add next. ## Core Features & Use Cases - Surface Inventory: Catalogs active harness targets, installed plugins, connected apps, MCP servers, LSP servers, env-backed services, and existing ECC skills. - Gap Benchmarking: Compares your workspace against official and installed plugins to classify each capability as already covered, primitive-only, or missing entirely. - ECC-Native Recommendations: Maps every gap to the right ECC shape (skill, hook, agent, MCP server, or connector) and outputs a prioritized list of 3-5 next moves. - Use Case: You just connected Stripe and Google Drive to your environment. Run this audit to discover that while the primitives exist, ECC lacks a billing-operator skill and a Google Workspace workflow, and get concrete recommendations for what to build first. ## Quick Start Audit my current workspace and tell me what Claude Code capabilities I already have, what is missing, and which ECC skills or hooks I should add next.

Frequently Asked Questions about workspace-surface-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit my Claude Code setup and available capabilities?▼

Run a workspace surface audit that inventories your repo config, MCP servers, installed plugins, connected apps, and env-backed services. The audit classifies each capability as available, primitive-only, or missing, then recommends concrete ECC-native skills, hooks, or agents to close the gaps.

How to decide between a skill, hook, agent, or MCP server?▼

Use a skill for repeatable operator workflows, a hook for automatic enforcement or side effects, an agent for specialized delegated roles, and an MCP server or connector for bridging external tools. The audit maps each identified gap to the correct shape based on this decision table.

Does the workspace audit expose my API keys or secrets?▼

No. The audit never prints secret values. It only surfaces provider names, capability names, file paths, and whether a key or config exists, such as noting that STRIPE_API_KEY is present without revealing its value.

Can the audit compare my setup against official Claude plugins?▼

Yes. The audit benchmarks your workspace against official marketplace plugins and locally installed plugins, evaluating what each one does, whether ECC already has parity, whether only primitives exist, or whether the workflow is missing entirely.

Does the workspace audit modify any files in my repo?▼

No. The audit is strictly read-only and only inspects files like package.json, .mcp.json, .claude settings, and .env key names. It modifies files only if you explicitly ask for follow-up implementation of its recommendations.