Skills for Real Engineers. Straight from my .agents directory.
verification-before-completion
Agent skill froma5c-ai/babysitter
Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.
How to install verification-before-completion
npx skills add a5c-ai/babysitter# or add only this skill to Claude Code: copy the folder
library/methodologies/cc10x/skills/verification-before-completion/
# into
~/.claude/skills/verification-before-completion/ (all projects)
.claude/skills/verification-before-completion/ (one project)
1## Rules23- Never claim "should work" without evidence4- Never claim success without exit code 05- Never claim a bug is fixed without reproduction failure6- Always capture and report exit codes7- Always run the full test suite, not just targeted tests8- Use timeout guards (`timeout 60s`) to prevent hanging910## When to Use1112- Before completing any BUILD workflow step13- Before claiming a DEBUG fix is verified14- Before approving a REVIEW result15- Before marking any task as done1617## Agents Used1819- `integration-verifier` (primary consumer)20- `component-builder` (TDD evidence)21- `bug-investigator` (fix evidence)
Excerpt shown under the repository's MIT license.
More skills in babysitter
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Production-grade engineering skills for AI coding agents.
The open-source app everyone uses to manage agents at work
