Prove It

Before declaring any task complete, actually verify the outcome. Run the code. Test the fix. Check the output. Claude's training optimizes for plausible-looking output, not verified-correct output. This skill forces the verification step that doesn't come naturally. No victory laps without proof.

62 stars 2 forksTesting & QA

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ElliotJLT/Claude-Skill-Potions --skill prove-it
Manual install
git clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/prove-it ~/.claude/skills/prove-it

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Prove It

<purpose>
Claude generates code by pattern-matching on training data. Something can look
syntactically perfect, follow best practices, and still be wrong. The model
optimizes for "looks right" not "works right." Verification is a separate
cognitive step that must be explicitly triggered. This skill closes the loop
between implementation and proof.
</purpose>

## Why This Matters (Technical Reality)

<technical-honesty>
Claude's limitations that this skill addresses:

**1. Generation vs Execution**
I generate code but don't run it. I predict what it would do based on patterns.
My confidence comes from "this looks like working code I've seen" not from
"I executed this and observed the result."

**2. Training Signal Mismatch**
My training optimizes for plausible next-token prediction, not outcome
verification. Saying "Done!" feels natural. Verifying feels like extra work.
But verification is where correctness actually lives.

**3. Pattern-Matching Blindness**
Code that matches common patterns feels correct. But subtle bugs hide in the
gaps between patterns. Off-by-one errors. Wrong variable names. Missing edge
cases. These "look right" but aren't.

**4. Confidence-Correctness Gap**
High confidence in my output doesn't correlate with actual correctness.
I'm often most confident when I'm most wrong, because the wrong answer
pattern-matched strongly.

**5. No Feedback Loop**
I generate sequentially. I don't naturally go back and check. Without
Read the full skill on GitHub

Details

Skill name
prove-it
Path
skills/prove-it/SKILL.md
License
MIT
Repo updated
12 February 2026

FAQ

What does the Prove It skill do?

Before declaring any task complete, actually verify the outcome. Run the code. Test the fix. Check the output. Claude's training optimizes for plausible-looking output, not verified-correct output. This skill forces the verification step that doesn't come naturally. No victory laps without proof.

How do I install the Prove It skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ElliotJLT/Claude-Skill-Potions --skill prove-it. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Prove It popular?

It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.

Related skills

Agent Audit

62

ElliotJLT/Claude-Skill-Potions

When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.

AI, LLMs & Agents

Battle Plan

62

ElliotJLT/Claude-Skill-Potions

Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.

Software Development

Breadcrumbs

62

ElliotJLT/Claude-Skill-Potions

Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.

Productivity & Notes

Test Driven Development (TDD)

43

obra/clank

Write the test first, watch it fail, write minimal code to pass

Testing & QA26

Power Calculations

36

dariia-m/my_claude_skills

Power, minimum detectable effect (MDE) and sample-size calculations in R for randomized experiments and survey experiments - two-arm and multi-arm designs with a shared control, ANCOVA vs change-score vs post-only, binary outcomes, within-subject differences, interactions/heterogeneity, clustered assignment, attrition and exclusions, and multiple-testing adjustment (per-test, Bonferroni bound, Holm/Romano-Wolf). Combines closed-form MDEs with Monte Carlo simulation of the exact pre-registered regression, including size checks. Use whenever the user asks for power calculations, an MDE table, "h

Testing & QA11

Testing Anti Patterns

43

obra/clank

Never test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.

Testing & QA26

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.