Completion Verification
Verify all phases are complete with weighted quality scoring before allowing session exit.
Best use case
Completion Verification is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Verify all phases are complete with weighted quality scoring before allowing session exit.
Teams using Completion 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/completion-verification/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Completion Verification Compares
| Feature / Agent | Completion 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?
Verify all phases are complete with weighted quality scoring before allowing session exit.
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.
SKILL.md Source
# Completion Verification Verify all phases are complete with weighted quality scoring before allowing session exit. ## Agent Completion Verifier - `pwf-completion-verifier` ## Workflow 1. Read all three planning files in parallel 2. Parse checkbox completion state from task_plan.md 3. Cross-reference plan, findings, and progress for consistency 4. Check error resolution status 5. Calculate weighted quality score (phases 40%, errors 25%, findings 20%, continuity 15%) 6. Generate recommendations if threshold not met 7. Write verification report to progress.md ## Inputs - `projectPath` - Root path for planning files - `taskDescription` - Original task description - `qualityThreshold` - Minimum score to pass (default: 80) - `strictMode` - Require 100% checkbox completion (default: false) ## Outputs - Quality score with component breakdown - Phase completion report - Unresolved error list - Prioritized improvement recommendations ## Process Files - `planning-orchestrator.js` - Completion assessment and final verification - `planning-verification.js` - Full verification pipeline
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
shell-completion-generator
Generate shell completion scripts for bash, zsh, and fish from CLI command definitions. Creates intelligent completions with argument suggestions, file completions, and dynamic values.
verification
Verification-before-completion discipline ensuring all success criteria are met, tests pass, and reviews complete before declaring work done.
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.