verification
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
Best use case
verification is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
Teams using verification should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/verification/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How verification Compares
| Feature / Agent | verification | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Verification Before Completion ## Overview Ensures no step or phase is declared complete without running verification. All success criteria must be met before finishing. ## When to Use - After each implementation step - At phase checkpoints - Before final completion declaration - When validating that all acceptance criteria are met ## Verification Checklist 1. All automated tests pass 2. Manual verification steps confirmed 3. Code review completed (APPROVE or APPROVE_WITH_NITS) 4. Security review passed 5. Plan document updated with completion status 6. All success criteria from the plan are satisfied 7. No untracked deviations from the plan ## Key Rules - Never declare done without running verification - Document any verification failures - Verification failures halt progress until resolved ## Tool Use Integrated into `methodologies/rpikit/rpikit-implement` (step execution and completion)
Related Skills
formal-verification
Formal property verification and model checking skill for FPGA designs
requirements-verification
Skill for aerospace requirements verification and validation matrix management
Completion Verification
Verify all phases are complete with weighted quality scoring before allowing session exit.
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
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.
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.