# Prove It

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-adit-jain-srm-skill-forge-prove-it`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Adit-Jain-srm](https://agentstack.voostack.com/s/adit-jain-srm)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Adit-Jain-srm](https://github.com/Adit-Jain-srm)
- **Source:** https://github.com/Adit-Jain-srm/skill-forge/tree/main/skills/prove-it
- **Website:** https://github.com/Adit-Jain-srm/skill-forge#quick-start

## Install

```sh
agentstack add skill-adit-jain-srm-skill-forge-prove-it
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Overview

The #1 agent failure: claiming "done" without proof. This skill forces evidence-before-assertion on every completion claim.

## Process

Never say "done" without proof. Never say "fixed" without running it. Never say "implemented" without showing it works.

## Persistence

ACTIVE on EVERY completion claim. Whenever you're about to say "done", "fixed", "implemented", "completed", "all set", "should work now" — STOP. Prove it first.

## The Gate

Before ANY statement claiming work is complete:

```
1. WHAT CLAIM am I about to make? (state it explicitly)
2. WHAT EVIDENCE proves this claim? (name the specific command/test/verification)
3. RUN the evidence NOW (not "I could run..." — actually run it)
4. READ the output (full output, not just exit code)
5. DOES the output CONFIRM the claim? 
   YES → show the evidence, THEN make the claim
   NO  → fix the issue, then re-run from step 3
```

## Examples

**BAD:** "Fixed the authentication bug." ← Where's the proof?

**GOOD:** 
```
Claim: "Login now works with expired refresh tokens"
Evidence: Running test suite
→ npm test -- auth.test.ts
→ Output: 14 passing, 0 failing
→ Specifically: "should refresh expired token" ✓
Confirmed: fix works.
```

**BAD:** "Implemented the search feature." ← Did you try it?

**GOOD:**
```
Claim: "Search returns results matching query"
Evidence: Running the feature
→ curl localhost:3000/api/search?q=test
→ Output: {"results": [{"title": "Test Item", ...}], "total": 3}
Confirmed: feature works.
```

## What Counts as Evidence

| Claim Type | Minimum Evidence |
|-----------|-----------------|
| Bug fix | Test that WAS failing now passes |
| New feature | Demo showing it works (command + output) |
| Refactor | All existing tests still pass |
| Performance fix | Before/after metrics |
| Config change | Proof the config is loaded correctly |
| "Everything works" | Full test suite output, exit code 0 |

## What Does NOT Count

- "It should work" ← run it
- "Based on the code changes" ← that's what you WROTE, not what RUNS  
- "The logic is correct" ← prove it with execution
- Citing your own diff as proof ← the diff is the CLAIM, not the EVIDENCE
- A passing linter ← linter checks syntax, not behavior

## Why

The #1 agent failure pattern (2026): "says done but isn't." Users report spending MORE time verifying false completions than if they'd done it themselves. This single discipline — prove before claiming — eliminates the entire category of wasted cycles.

> "Claiming work is complete without verification is dishonesty, not efficiency."

## Red Flags — STOP if you think any of these

- "The change is so small it obviously works"
- "I'll verify in the next step"
- "Based on my understanding of the code..."
- "It should work because the logic is sound"
- "The tests passed earlier, so this is fine"
- "Let me just confirm it's done" (without running anything)

**All of these mean: you're about to claim without evidence. Run the verification FIRST.**

## Common Mistakes

- Treating your code diff as evidence (the diff is the CLAIM, execution is the EVIDENCE)
- Running tests but not reading output (exit code 0 with skipped tests is not passing)
- "It worked earlier" as justification (prove it works NOW)
- Verifying in your head instead of on the machine

## Rationalizations (countered)

| Excuse | Reality |
|--------|---------|
| "It's a one-line change" | One-line changes break production. Run the test. |
| "I already verified mentally" | Mental verification = no verification. Execute it. |
| "The test suite takes too long" | Run the RELEVANT test, not all of them. No excuse. |
| "It's just a config change" | Config errors are the hardest to debug. Prove it loaded. |
| "I'll run tests after I finish everything" | By then you won't know which change broke what. Prove EACH. |
| "The user can verify" | YOU verify. Don't outsource your responsibility. |

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Adit-Jain-srm](https://github.com/Adit-Jain-srm)
- **Source:** [Adit-Jain-srm/skill-forge](https://github.com/Adit-Jain-srm/skill-forge)
- **License:** MIT
- **Homepage:** https://github.com/Adit-Jain-srm/skill-forge#quick-start

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-adit-jain-srm-skill-forge-prove-it
- Seller: https://agentstack.voostack.com/s/adit-jain-srm
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.