/pre-deploy
Validate build, environment, and dependencies before deployment
$ npx -y skills add undeadlist/claude-code-agents --skill pre-deploy --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/pre-deploy
Context preview
The summary Claude sees to decide when to auto-load this skill.
Validate build, environment, and dependencies before deployment
SKILL.md
pre-deploy.SKILL.mdname: pre-deploy description: Validate build, environment, and dependencies before deployment
Pre-Deploy Workflow
Run before any deployment to production. All checks must pass.
Execution (Parallel)
Spawn all three agents **in parallel**:
| Agent | Focus | |-------|-------| | `deploy-checker` | Build validation, bundle size, production config | | `env-validator` | Environment variables, secrets detection, config completeness | | `dep-auditor` | Vulnerability scan, outdated packages, license compliance |
Gate Check
After all agents complete:
- **All pass** -> "Ready to deploy"
- **Any fail** -> "BLOCKED - Fix first" with specific blockers listed
Expected Output
# Pre-Deploy Checklist ## Status: READY / BLOCKED ### Build Validation (deploy-checker) - [x] Production build succeeds - [x] Bundle size acceptable - [x] No build warnings ### Environment (env-validator) - [x] All required vars set - [x] No secrets in code - [x] Production config valid ### Dependencies (dep-auditor) - [x] No critical vulnerabilities - [x] No high vulnerabilities ## Deployment Decision READY TO DEPLOY / BLOCKED - Fix issues
Claude Code Agents Prompt templates for Claude Code's subagent system. Run parallel code audits, automate fix cycles, get stuff reviewed. Built for the Claude Code Task tool. Not a framework. Just prompts that work. What This Does Claude Code can spawn subagents via Task(). These are the prompts those agents receive.
Other skills on claude-code-agents.
full-audit
Run all 11 audit agents in parallel, then consolidate findings with fix-planner

