Skip to content
Automation
Skill

/verification-before-completion

Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.

From plugin
babysitter
1.8k200 skills3 agents21 commands1 MCP
Install
$ npx -y skills add a5c-ai/babysitter --skill verification-before-completion --agent claude-code

How 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/verification-before-completion

Context preview

The summary Claude sees to decide when to auto-load this skill.

Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.

SKILL.md

verification-before-completion.SKILL.md
name: verification-before-completion
description: Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.
allowed-tools: Read, Bash, Grep, Glob
graph:
  domains: [domain:software-engineering]
  skillAreas: [skill-area:agentic-loops, skill-area:orchestration-loop]
  workflows: [workflow:feature-development]
  topics: [topic:developer-experience]
  roles: [role:tech-lead, role:backend-engineer]
2. **Test output**: pass/fail counts, coverage percentages
3. **Logs**: error messages, stack traces, resolution confirmation
4. **Build output**: compilation success/failure with timestamps

Rules

  • Never claim "should work" without evidence
  • Never claim success without exit code 0
  • Never claim a bug is fixed without reproduction failure
  • Always capture and report exit codes
  • Always run the full test suite, not just targeted tests
  • Use timeout guards (`timeout 60s`) to prevent hanging

When to Use

  • Before completing any BUILD workflow step
  • Before claiming a DEBUG fix is verified
  • Before approving a REVIEW result
  • Before marking any task as done

Agents Used

  • `integration-verifier` (primary consumer)
  • `component-builder` (TDD evidence)
  • `bug-investigator` (fix evidence)
Ships withbabysitter

Enforce obedience on agentic workforces. Manage extremely complex workflows through deterministic, hallucination-free self-orchestration.

Get the whole plugin

Other skills on babysitter.