verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Best use case
verification-before-completion is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Teams using verification-before-completion 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-before-completion/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How verification-before-completion Compares
| Feature / Agent | verification-before-completion | 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?
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
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
# Verification Before Completion
## Overview
Claiming work is complete without verification is dishonesty, not efficiency.
**Core principle:** Evidence before claims, always.
**Violating the letter of this rule is violating the spirit of this rule.**
## The Iron Law
```
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
```
If you haven't run the verification command in this message, you cannot claim it passes.
## The Gate Function
```
BEFORE claiming any status or expressing satisfaction:
1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
- If NO: State actual status with evidence
- If YES: State claim WITH evidence
5. ONLY THEN: Make the claim
Skip any step = lying, not verifying
```
## Common Failures
| Claim | Requires | Not Sufficient |
|-------|----------|----------------|
| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
| Regression test works | Red-green cycle verified | Test passes once |
| Agent completed | VCS diff shows changes | Agent reports "success" |
| Requirements met | Line-by-line checklist | Tests passing |
## Red Flags - STOP
- Using "should", "probably", "seems to"
- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
- About to commit/push/PR without verification
- Trusting agent success reports
- Relying on partial verification
- Thinking "just this once"
- Tired and wanting work over
- **ANY wording implying success without having run verification**
## Rationalization Prevention
| Excuse | Reality |
|--------|---------|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ compiler |
| "Agent said success" | Verify independently |
| "I'm tired" | Exhaustion ≠ excuse |
| "Partial check is enough" | Partial proves nothing |
| "Different words so rule doesn't apply" | Spirit over letter |
## Key Patterns
**Tests:**
```
✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"
```
**Regression tests (TDD Red-Green):**
```
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)
```
**Build:**
```
✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)
```
**Requirements:**
```
✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"
```
**Agent delegation:**
```
✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report
```
## Why This Matters
From 24 failure memories:
- your human partner said "I don't believe you" - trust broken
- Undefined functions shipped - would crash
- Missing requirements shipped - incomplete features
- Time wasted on false completion → redirect → rework
- Violates: "Honesty is a core value. If you lie, you'll be replaced."
## When To Apply
**ALWAYS before:**
- ANY variation of success/completion claims
- ANY expression of satisfaction
- ANY positive statement about work state
- Committing, PR creation, task completion
- Moving to next task
- Delegating to agents
**Rule applies to:**
- Exact phrases
- Paraphrases and synonyms
- Implications of success
- ANY communication suggesting completion/correctness
## The Bottom Line
**No shortcuts for verification.**
Run the command. Read the output. THEN claim the result.
This is non-negotiable.Related Skills
writing-wechat-tech-posts
Writes complete WeChat tech posts (hook, TOC, body, checklists, image placement, layout notes, summaries). Use when the user asks to draft a WeChat tech article, generate reusable prompts for writing, or turn a topic/outline into a publish-ready post.
titling-wechat-tech-posts
Crafts and rewrites WeChat tech post titles across multiple patterns (list, contrast, outcome, scenario, anti-myth, template). Use when the user needs headline brainstorming or “restrained but clickable” title rewrites for tech/engineering WeChat公众号.
planning-wechat-tech-account
Defines WeChat tech public-account positioning, audience segmentation, content pillars, and long-term columns. Use when the user asks about account positioning, reader personas, content strategy, or column planning for a tech/engineering WeChat公众号.
outlining-wechat-tech-posts
Builds WeChat-friendly outlines for tech posts, including multi-level TOC, reader-benefit lines per section, pitfalls and action checklists, and 30-second skim summaries. Use when the user asks for outlines, structures, or tutorial-style blueprints for tech/engineering WeChat公众号.
iterating-wechat-tech-posts
Generates endings/CTAs, pre-publish editorial QA, sentence sharpening, and post-performance retrospectives for WeChat tech posts. Use when the user needs a strong ending, final edit pass, or analytics-driven iteration plan for tech/engineering WeChat公众号.
ideating-wechat-tech-topics
Generates WeChat tech article topics, series, and angles with difficulty and “hit potential” scoring. Use when the user asks for topic ideas, content calendars, anti-myth angles, or serialized planning for tech/engineering WeChat公众号.
formatting-wechat-tech-posts
Designs image plans and rewrites formatting for WeChat-friendly readability (short paragraphs, bolding, separators, restrained emoji). Use when the user asks for illustration ideas, layout guidance, or to convert a draft into publish-ready WeChat formatting.
evidencing-wechat-tech-posts
Produces credible case-study writeups, non-hallucinated data handling, and fact-check lists for WeChat tech posts. Use when the user needs a project recap, results narrative, citations guidance, or “what to verify” checklists in tech/engineering WeChat公众号.
tech-explainer-writer
Use when drafting, rewriting, or polishing public-facing tech explainers for general readers. Trigger on requests to explain complex technical concepts, AI products, system mechanisms, industry trends, or jargon-heavy material in plain language; to turn notes, links, transcripts, slides, or drafts into popular-science articles,公众号内容, scripts, summaries, or “一看就懂” explanations.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions