verify-task
MUST use after completing any multi-step task or project. Verifies completion against the original plan, checks quality criteria, and documents outcomes.
Best use case
verify-task is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
MUST use after completing any multi-step task or project. Verifies completion against the original plan, checks quality criteria, and documents outcomes.
Teams using verify-task 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/verify-task/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How verify-task Compares
| Feature / Agent | verify-task | 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?
MUST use after completing any multi-step task or project. Verifies completion against the original plan, checks quality criteria, and documents outcomes.
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
# Verify Task ## Overview Confirm successful completion and document outcomes against the original plan. ## When to Verify - All tasks from plan are marked complete - User asks "is it done?" or "did it work?" - Before declaring a project finished - After each checkpoint in long-running tasks ## Verification Process ### Step 1: Load Original Plan Read the plan that was created by write-plan skill. ### Step 2: Verify Each Checkpoint Go through each checkpoint and confirm: - [ ] All tasks marked complete - [ ] Verification criteria met - [ ] Quality standards achieved ### Step 3: Final Quality Checks **General quality criteria:** - [ ] Output matches original goal - [ ] No obvious errors or issues - [ ] Documentation updated (if applicable) - [ ] User can use/access the result ### Step 4: User Confirmation ``` "Verification complete. Final checks: ✓ All tasks from plan completed (X/Y) ✓ Quality criteria met ✓ [Specific checks] [Preview/demonstrate result] Does this meet your expectations? Any adjustments needed?" ``` ### Step 5: Document Completion Save completion report to: `memory/plans/YYYY-MM-DD-<project>-complete.md` Template: ```markdown # [Project] - Completion Report **Date Completed:** YYYY-MM-DD **Original Goal:** [from plan] **Final Result:** [brief description] ## Completion Summary | Metric | Planned | Actual | |--------|---------|--------| | Checkpoints | X | X | | Tasks | Y | Y | | Time | Z min | W min | ## Verification Checklist - [x] All tasks complete - [x] Quality criteria met - [x] User approved ## What Was Delivered [Description of final output] ## Blockers Encountered 1. [Blocker] → [Resolution] ## Lessons Learned - [What worked well] - [What to do differently next time] ``` ## Handling Issues ### If verification fails: **Minor issues:** Quick fixes, proceed **Major issues:** Return to doing-tasks or re-plan ## Principles - **Objectivity** - Verify against the plan, not assumptions - **Thoroughness** - Check all criteria - **Honesty** - Report issues, don't hide problems - **User-centric** - Final approval comes from user satisfaction
Related Skills
task-tracker
Personal task management with daily standups and weekly reviews. Use when: (1) User says 'daily standup' or asks what's on their plate, (2) User says 'weekly review' or asks about last week's progress, (3) User wants to add/update/complete tasks, (4) User asks about blockers or deadlines, (5) User shares meeting notes and wants tasks extracted, (6) User asks 'what's due this week' or similar.
task-monitor
Real-time web dashboard for OpenClaw sessions and background tasks. Mobile-responsive with auto-refresh.
task-runner
Manage tasks and projects across sessions with persistent task tracking.
farm-task-manager
*Daily, weekly, and seasonal farm chore management with task scheduling and priorities.*.
taskmaster
Project manager and task delegation system. Use when you need to break down complex work into smaller tasks, assign appropriate AI models based on complexity, spawn sub-agents for parallel execution, track progress, and manage token budgets. Ideal for research projects, multi-step workflows, or when you want to delegate routine tasks to cheaper models while handling complex coordination yourself.
opentask-worker
Autonomous worker agent for OpenTask.ai — the agent-to-agent task marketplace.
task-scheduler
Schedule tasks and commands to run at specific times.
autotask-mcp
Use when you need to interact with Datto/Kaseya Autotask PSA via an MCP server (tickets, companies, contacts.
straker-verify
Professional AI-powered translation with optional human verification. Supports 100+ languages. Quality boost for existing translations. Enterprise-grade security and privacy by straker.ai.
proactive-tasks
Proactive goal and task management system. Use when managing goals, breaking down projects into tasks, tracking progress, or working autonomously on objectives. Enables agents to work proactively during heartbeats, message humans with updates, and make progress without waiting for prompts.
tasktime
CLI task timer for AI agents — benchmark learning progression with auto-save logs and visualizations.
clawprint-verify
Issue ClawPrint reverse-CAPTCHA challenges to verify that another user or agent is a real AI, not a human. Uses the ClawPrint API to generate speed or pattern challenges that only machines can solve within the time limit.