Verification Before Completion logo

Verification Before Completion

Organization
MadAppGang
verification-before-completion

Use when claiming task completion or marking items as done. Covers completion evidence requirements, verification methods, and anti-rationalization patterns.

Overview

PublisherMadAppGang
Repositoryclaude-code
Skill nameverification-before-completion
Stars
281
Forks
26
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by MadAppGang on GitHub. Read the source before you install it.

Installation

Install the Verification Before Completion AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/MadAppGang/claude-code.git /tmp/claude-code
mkdir -p .claude/skills
cp -r /tmp/claude-code/plugins/dev/skills/discipline/verification-before-completion .claude/skills/verification-before-completion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Verification Before Completion in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Verification Before Completion on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Verification Before Completion is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Verification Before Completion

Iron Law: "NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE"

When to Use

This skill applies whenever you:

  • Mark a todo item as complete
  • Claim a bug is fixed
  • Report a feature is ready
  • State implementation is done
  • Close a task or issue
  • Prepare to commit changes

Red Flags (Violation Indicators)

  • "should be done" / "should work now" (assumed completion)
  • "probably works" / "likely fixed" (uncertainty without verification)
  • "seems to work" / "appears correct" (observation without test)
  • "Great!" / "Perfect!" / "All set!" (celebration without evidence)
  • "I already tested this earlier" (stale evidence)
  • Completion claim without test output shown
  • Completion claim without grep verification for file changes
  • Completion claim without screenshot for UI changes
  • Completion claim without git diff for code changes
  • Completion claim without build logs for configuration changes
  • Completion claim without CI link for deployment changes
  • "Just a small change, no need to verify" (size-based rationalization)

Key Concepts

Fresh Verification Principle

Verification must be fresh (performed after the claimed change) and explicit (evidence shown, not described).

Wrong:

Fixed the login bug in auth.ts. Should be working now.

Correct:

Fixed the login bug in auth.ts line 42:

git diff src/auth.ts:
-  if (user.token == null) {
+  if (user.token === undefined || user.token === null) {

Test output:
✓ should reject undefined token (15ms)
✓ should reject null token (12ms)
✓ should accept valid token (8ms)

Evidence Types by Change Type

Change TypeRequired EvidenceTool/Method
Logic/algorithmTest output showing passbun test, pytest, go test
File creationGrep verification or ls outputgrep -r "pattern" . or ls -la path/
UI/stylingScreenshot or videoBrowser DevTools screenshot
ConfigurationBuild logs showing successnpm run build, cargo build
DeploymentCI link or deployment logsGitHub Actions URL, kubectl logs
API changesAPI test output or curl resultcurl -X POST ...
Data migrationRow count or sample querySELECT COUNT(*) FROM ...
Performance fixBenchmark comparison (before/after)hyperfine, go test -bench

Enforcement Mechanism

Tasks Integration

When marking a todo as completed:

  1. BEFORE changing status to completed, gather fresh evidence
  2. IN THE SAME MESSAGE that marks it complete, show the evidence
  3. NEVER mark complete in one message, then show evidence later

Violation Pattern:

Message 1: "Fixed the validator. Marking todo complete."
Message 2: "Here's the test output..."

Correct Pattern:

Message 1:
"Fixed the validator. Test output:
✓ should validate email (5ms)
✓ should reject invalid format (3ms)

Marking todo complete."

Rationalization Detection

Common rationalizations and their counters:

RationalizationCounter
"It's a trivial change"Trivial = fast to verify, not skip
"I tested this before"Code changed since then, verify again
"Same pattern as working code"Different context = different bugs
"Just fixing a typo"Typos can break builds, verify
"Only changed comments"Comments can break doc generation
"Can't test without production data"Use test fixtures or staging environment

Examples

Example 1: React Component Fix (TypeScript)

Scenario: Fixed useState initialization bug

Wrong Completion:

Fixed the counter initialization bug. Should be good now!

Correct Completion:

Fixed the counter initialization bug in Counter.tsx line 8:

git diff:
-  const [count, setCount] = useState();
+  const [count, setCount] = useState<number>(0);

Test output:
 PASS  src/Counter.test.tsx
   Counter component
     ✓ renders with initial value 0 (23ms)
     ✓ increments on button click (15ms)

Build check:
✓ Type checking passed (1.2s)
✓ No lint errors

Example 2: Python API Endpoint (FastAPI)

Scenario: Fixed validation error in POST /users

Wrong Completion:

Added email validation to the users endpoint. Tested locally, works fine.

Correct Completion:

Added email validation to the users endpoint in api/users.py line 45:

git diff:
 @app.post("/users")
 def create_user(user: UserCreate):
+    if not re.match(r"[^@]+@[^@]+\.[^@]+", user.email):
+        raise HTTPException(400, "Invalid email format")
     return db.create_user(user)

Test output:
test_create_user.py::test_valid_email PASSED
test_create_user.py::test_invalid_email_rejected PASSED
test_create_user.py::test_missing_at_sign PASSED

Manual curl test:
$ curl -X POST http://localhost:8000/users -d '{"email":"invalid"}'
{"detail":"Invalid email format"}

Example 3: Go Configuration Change

Scenario: Updated Docker build configuration

Wrong Completion:

Updated the Dockerfile to use Go 1.22. Build should work now.

Correct Completion:

Updated the Dockerfile to use Go 1.22:

git diff:
-FROM golang:1.21-alpine
+FROM golang:1.22-alpine

Build verification:
$ docker build -t myapp:test .
[+] Building 45.3s (12/12) FINISHED
 => [internal] load build definition from Dockerfile
 => => transferring dockerfile: 234B
 => [1/6] FROM golang:1.22-alpine
 => [2/6] WORKDIR /app
 => [3/6] COPY go.mod go.sum ./
 => [4/6] RUN go mod download
 => [5/6] COPY . .
 => [6/6] RUN go build -o /app/server
 => exporting to image
 => => writing image sha256:abc123...

Run verification:
$ docker run myapp:test --version
v1.0.0 (go1.22.0)

Integration with Other Skills

  • test-driven-development: TDD provides the tests you'll use as verification evidence
  • systematic-debugging: Debug process ends with fix verification (this skill)
  • agent-coordination-discipline: Agents must return verification evidence, not just claims
  • quality-gates: Quality gate checks are verification evidence types

Quick Reference

Before marking ANY task complete:

  1. ✅ Run relevant tests → capture output
  2. ✅ Check file changes → show git diff or grep
  3. ✅ Verify build → show build logs
  4. ✅ For UI changes → take screenshot
  5. ✅ For deployments → link CI run
  6. ✅ Show evidence in completion message
  7. ✅ Only then mark todo as completed

Remember: If you can't show fresh evidence, the task isn't complete yet.

Frequently asked questions

What does the Verification Before Completion AI skill do?

Use when claiming task completion or marking items as done. Covers completion evidence requirements, verification methods, and anti-rationalization patterns.

Why use Verification Before Completion on TypingMind?

Because you install it once and use it with any model. Verification Before Completion is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Verification Before Completion in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MadAppGang/claude-code/tree/main/plugins/dev/skills/discipline/verification-before-completion. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Verification Before Completion?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Verification Before Completion?

As many as you like. As long as a model supports skills, you can use Verification Before Completion with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Verification Before Completion AI skill free?

Yes. It is published on GitHub by MadAppGang under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇