eddmann/agent-toolkit/analyze

Claude Code and agent skill by eddmann/agent-toolkit

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when investigating a complex code change or comparing implementation approaches.

Install

npx vskill@latest install eddmann/agent-toolkit/analyze

SKILL.md

Analyze

Investigate the requested problem and recommend the simplest sufficient approach. Keep analysis read-only unless implementation is requested; preserve the user's scope and existing work.

Investigate

  1. Establish the intended outcome, constraints and unresolved decisions from the request and

repository instructions. Ask only when missing information materially changes the answer.

  1. Read the relevant implementation, callers, dependencies and tests. Trace behavior far enough

to understand the cause or proposed change; use history when it helps explain a decision.

  1. Verify important assumptions with focused inspection or checks. Distinguish observed facts

from inference and identify evidence gaps. Stop expanding the search when the recommendation is supported; do not use file counts or compulsory agent passes as a measure of thoroughness.

Recommend

Compare alternatives only where they represent a meaningful choice. Assess correctness, complexity, compatibility and relevant failure cases. Prefer existing patterns and targeted changes; do not add abstractions or features for hypothetical future needs. Consider leaving the code unchanged when the evidence does not justify a change.

Lead with the recommendation and explain why it fits the problem. Include relevant file/line references, material tradeoffs, risks and unresolved questions. For a proposed implementation, outline the affected areas and how to verify the resulting behavior. Scale detail to the task; do not force a report template or an additional approval step.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
2
7-day trend score
5

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/eddmann/agent-toolkit/analyze/badge)](https://verified-skill.com/skills/eddmann/agent-toolkit/analyze)

Something wrong with this skill or its page? Tell us.