before-code-analysis
Use BEFORE reading multiple files to understand code.
Skill by eveld
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/eveld-before-code-analysis
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/before-code-analysis
What's inside
- Skill name
before-code-analysis- Description
- Use BEFORE reading multiple files to understand code. Reminds you to use codebase-analyzer agent instead of manual file reading.
- License
- MIT
- Instructions
- 35 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Before Code Analysis **STOP**: You're about to read multiple files to understand how something works. ## Use codebase-analyzer Instead The `codebase-analyzer` agent is specifically designed for understanding code implementation. It will read files in context and explain how systems work. ### Instead of: ``` Read(file_path="src/auth/handler.js") Read(file_path="src/auth/service.js") Read(file_path="src/auth/middleware.js") [manually piecing together how auth works] ``` ### Do this: ``` Task( subagent_type="codebase-analyzer", prompt="Analyze how the authentication system works, including handlers, services, and middleware", description="Analyze auth system" ) ``` ## When Manual Reading Is OK Only read files manually when: - You need to see exact implementation of a single function - You're making specific edits to known files - You're verifying a specific detail For understanding systems or flows, use `codebase-analyzer`.
From eveld/claude, MIT.
More from eveld/claude
- 0.480score
linear-issues
eveld
Fetch and view Linear issues/tickets.
SkillDFreshness: D★ 10Claude Code +9 - 0.479score
gcp-logs
eveld
Query GCP Cloud Logging for errors, service logs, and request traces.
SkillDFreshness: D★ 10Claude Code +9 - 0.479score
k8s-query
eveld
Query Kubernetes resources (pods, deployments, services, events).
SkillDFreshness: D★ 10Claude Code +9 - 0.475score
k8s-debug
eveld
Launch ephemeral debug container in running pod for interactive debugging.
SkillDFreshness: D★ 10Claude Code +9 - 0.474score
spawn-planning-agents
eveld
Use when creating implementation plans to research codebase patterns and gather context for planning.
SkillDFreshness: D★ 10Claude Code +9 - 0.474score
gather-project-metadata
eveld
Use when creating research or plan documents to gather git commit, branch, repository info.
SkillDFreshness: D★ 10Claude Code +9 - 0.474score
follow-test-patterns
eveld
Use when writing tests to ensure they follow project conventions.
SkillDFreshness: D★ 10Claude Code +9 - 0.474score
spawn-research-agents
eveld
Use when conducting codebase research to orchestrate specialized agents in parallel for comprehensive investigation.
SkillDFreshness: D★ 10Claude Code +9 - 0.474score
debug-systematically
eveld
Use when encountering errors or bugs to follow a systematic debugging process instead of jumping to conclusions.
SkillDFreshness: D★ 10Claude Code +9 - 0.472score
linear-update
eveld
Update Linear issues with debugging findings.
SkillDFreshness: D★ 10Claude Code +9 - 0.472score
agent-awareness
eveld
ALWAYS check this skill before using grep, glob, Task tool, or doing any codebase exploration.
SkillDFreshness: D★ 10Claude Code +9 - 0.472score
linear-awareness
eveld
ALWAYS check before working with Linear issues.
SkillDFreshness: D★ 10Claude Code +9
Signals
- Stars
- 10
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Dec 23, 2025 (10 months ago)
- Last release
- Dec 29, 2025 (10 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/eveld/claude
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from eveld
- 0.480score
linear-issues
eveld
Fetch and view Linear issues/tickets.
SkillDFreshness: D★ 10Claude Code +9 - 0.479score
k8s-query
eveld
Query Kubernetes resources (pods, deployments, services, events).
SkillDFreshness: D★ 10Claude Code +9 - 0.479score
gcp-logs
eveld
Query GCP Cloud Logging for errors, service logs, and request traces.
SkillDFreshness: D★ 10Claude Code +9 - 0.475score
k8s-debug
eveld
Launch ephemeral debug container in running pod for interactive debugging.
SkillDFreshness: D★ 10Claude Code +9 - 0.474score
spawn-planning-agents
eveld
Use when creating implementation plans to research codebase patterns and gather context for planning.
SkillDFreshness: D★ 10Claude Code +9 - 0.474score
gather-project-metadata
eveld
Use when creating research or plan documents to gather git commit, branch, repository info.
SkillDFreshness: D★ 10Claude Code +9
Cite this page
before-code-analysis skill. Agent Mart. https://agentmart.dev/skills/eveld-before-code-analysis (last updated 2026-10-24)