smithery.ai

devloop-audit

Audit devloop against Claude Code updates to identify integration opportunities. Use after Claude Code releases, monthly maintenance, or when exploring new features.

First seen Apr 5, 2026

Installation

$ npx skills add https://smithery.ai

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

Allowed toolsRead, Grep, Glob, LSP, WebFetch, WebSearch, Write, AskUserQuestion
Declared agents claude-code

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,327 B
  • docs SUMMARY.md 186 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

Devloop Audit

Audit devloop against Claude Code's evolving capabilities.

When to Run

  • After major Claude Code releases
  • Monthly maintenance check
  • When noticing new Claude Code features

Audit Process

Step 1: Gather Claude Code Information

  1. Fetch Release Notes: https://code.claude.com/docs/en/changelog.md
  2. Review Key Docs: Skills, Plugins, Hooks, Sub-agents at code.claude.com/docs/en/

Step 2: Analyze Current devloop

ls plugins/devloop/agents/
ls plugins/devloop/skills/

Step 3: Compare and Identify Gaps

Category Questions
Overlap Does native Claude Code now provide this?
Enhancement Can new features improve this?
Deprecation Are we using outdated patterns?
Missing New capabilities to adopt?

Step 4: Generate Findings Report

Priority Ranking:

  • High: Native feature replaces devloop, security issue, blocks users
  • Medium: Partial overlap, improves UX, aligns with best practices
  • Low: Minor improvement, nice-to-have

Effort Estimation:

  • Low: <1 day, localized change
  • Medium: 1-3 days, multiple files
  • High: 3+ days, architectural change

Save to .devloop/spikes/claude-code-audit-YYYY-MM-DD.md:

# Claude Code Audit Findings

**Date**: YYYY-MM-DD
**Claude Code Version**: X.Y.Z
**devloop Version**: X.Y.Z

## Summary
Brief overview.

## Integration Opportunities

### High Priority
| Finding | Current State | Action | Effort |
|---------|--------------|--------|--------|

### Medium Priority
...

## Deprecated Patterns
| Pattern | Native Alternative | Migration |
|---------|-------------------|-----------|

## New Features to Adopt
| Feature | Use Case | Notes |
|---------|----------|-------|

Step 5: Offer Next Steps

AskUserQuestion:
  questions:
    - question: "Audit complete. What next?"
      header: "Action"
      options:
        - label: "Create spike from findings"
        - label: "Create plan from findings"
        - label: "Review findings"

Audit Checklist

  • Commands: State detection, run patterns, ship workflow current?
  • Skills: Standard frontmatter, discoverable by Claude?
  • Agents: Standard format, aligned with Agent tool?
  • Hooks: Current API, best practices?
  • Task Management: Plan vs session tasks clear?
  • State: .devloop/ structure current?

Key Documentation Links

Output

Produces:

  1. Findings report at .devloop/spikes/claude-code-audit-YYYY-MM-DD.md
  2. Summary of integration opportunities
  3. Option to create spike/plan for follow-up