verification-before-completion
Support completion claims with actual verification results
Source: obra
At a glance
- Best for
- Tie completion claims to verification evidence
- Works with
- Completion or passing claims to verify · Check commands, results, and acceptance criteria
- Outcome
- An evidence-backed status report · Failed or unverified items
- Source
- obra/superpowers
01 / Understand the skill
About verification-before-completion
Before claiming a fix, passing tests, or completion, identify the required verification, run the relevant commands, and read their actual results. Covers tests, builds, fixes, and requirement acceptance. Distinguishes complete checks from partial results and produces a handoff stating observed results, failures, and unverified areas.
Requirements
- An agent that can run the project's checks and read their results
- Task-specific acceptance criteria and the runtime environment
Inputs
- Completion or passing claims to verify
- Check commands, results, and acceptance criteria
Outputs
- An evidence-backed status report
- Failed or unverified items
02 / Confirm the fit
Use verification-before-completion when you need to
- Tie completion claims to verification evidence
- Distinguish complete checks from partial results
- State failures and unverified areas
03 / See the workflow
How verification-before-completion works
- 01Identify the evidence each claim requires
- 02Run the relevant checks and read the results
- 03Report completion using actual results
Check before installing
Compatible platforms
Cursor · GitHub Copilot · OpenAI Codex · Claude Code
Best fit
Tie completion claims to verification evidence
Review the source instructions if the required output differs from the formats described above.
Install and use
Compatible with Cursor and GitHub Copilot and OpenAI Codex and Claude Code · Published by obra
Ready to add verification-before-completion?
Use the published instructions below, then provide the required input and describe the result you need.
General instructions · Cursor · GitHub Copilot · OpenAI Codex · Claude Code
/plugin install superpowers@claude-plugins-official Install the complete Claude Code plugin as described in the upstream README. For other hosts, follow their dedicated installation sections in the same README.
Review the source repository and license before installing third-party skills.
Continue exploring
Similar skills
Authoritative reference for the Claude API and Anthropic SDKs: model IDs, pricing, thinking/effort params, streaming, tool use, caching, managed agents, and model migration.
Read, edit, create, and fix Excel/CSV files — formulas, formatting, charts, and clean financial models with zero formula errors.
Generate distinctive, production-grade frontend UI that avoids generic AI aesthetics — pages, components, dashboards, and landing pages.
Build high-quality MCP (Model Context Protocol) servers in Python (FastMCP) or Node/TypeScript that let LLMs use external services through well-designed tools.