Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Prove It Works · cursor | DecimalAI

testingby cursor

Prove It Works

cursor/principle-prove-it-works

Source cursor/plugins ↗License Not recorded

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'

SkillScore61Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

QA & Test Engineering pack

Last verified 10/6/2026

What it changes

Passed 12 of 19 test cases with the skill, and 9 of 19 without it.

Without skill48%

With skill61%

Checks it passed that the model alone missed

Rejects using dashboard indicators as proof of feature flag activation.
Prescribes making an HTTP request to inspect the live service response.
Recommends presenting test execution output in pull request review notes.

and 3 more in the full report

5 fixed9 passed either way7 still failing2 broke

Pass-rate lift: +13 pp
Tokens: +6%
Agent turns: 0%
Response time: +7%

Model gemini-3.6-flashMeasured 10/6/2026v214 of 23 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/cursor-principle-prove-it-works/SKILL.md https://app.decimal.ai/s/cursor-principle-prove-it-works/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add cursor-principle-prove-it-works, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/cursor-principle-prove-it-works/ and pins it in .decimal/skills.lock

decimalai skills add cursor-principle-prove-it-works

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/cursor-principle-prove-it-works/SKILL.md https://app.decimal.ai/s/cursor-principle-prove-it-works/SKILL.md

Raw file: /s/cursor-principle-prove-it-works/SKILL.md ↗ · machine-readable summary at /s/cursor-principle-prove-it-works.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

We added `python3-pip` to the Dockerfile for `worker-base:v2`. The Dockerfile contains `RUN apt-get update && apt-get install -y python3-pip`. How do we verify `pip3` is actually installed in the built container image?

What was checked, without and with the skill
Checked	Without skill	With skill
Rejects checking Dockerfile text as proof of package installation inside the image.	Missed	Passed
Requires executing docker run to verify binary availability inside the container image.	Passed	Passed

case-16 · gemini-3.6-flash · 10/6/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md16 linessingle file

Prove It Works

Verify every task output by checking the real thing directly. Do not infer from proxies, self-reports, or "it compiles."

Why: Unverified work has unknown correctness. Indirect verification (file mtimes, output freshness, agent self-reports, cached screenshots) feels cheaper than direct observation. Acting on a wrong inference costs far more than checking the source.

Check the real thing, not a proxy:

Check process liveness directly, not indirectly through derived state
Read the actual value, not a cached or derived representation
When verification fails, suspect the observation method before suspecting the system

Script the check when you can

The strongest proof is a deterministic script that re-runs the same comparison, not a one-time eyeball. Write the script, run it, and keep its output as an artifact a reviewer can re-run instead of trusting your word.

Keep the artifact visible for the human. Commit it only for large or complex work where the trail has to be auditable later, like a big port or migration (the show-me-your-work skill).

Track record

Benchmark

12 / 19

test cases passed, vs 9 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/30/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

cursor / plugins

pstack/skills/principle-prove-it-works/SKILL.md

View on GitHub ↗

Imported 9/30/2026Version v2

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Prove It Works

Script the check when you can

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills