Ready to supercharge your AI agents?

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

verifier-setup — scaffold this repo's /verify skill · ai-builder-club | DecimalAI

agent toolingby ai-builder-club

verifier-setup — scaffold this repo's /verify skill

ai-builder-club/verifier-setup

Source ai-builder-club/skills ↗License Not recorded

Set a repo up to prove engineering-task work actually works before it ships. Investigates the repo, ensures a one-command dev stack (`dev-local`) exists, asks whether verification runs locally or in a sandbox (crabbox), confirms/installs the driver (the `playwright-cli` skill for web by default). Outputs three artifacts: a committed `/verify` skill (per-task verification SOP — spawn a verifier sub-agent → drive the app → screenshot/video proof → open a PR with the proof embedded), the `/dev-loca

SkillScore68Maintained

Automatic

QA & Test Engineering pack

Last verified 8/15/2026

What it changes

Passed 11 of 16 test cases with the skill, and 5 of 16 without it.

Without skill32%

With skill68%

Checks it passed that the model alone missed

Ensures evidence/ is added to .gitignore
Reads assets/verify.template.md as the source template
Selects playwright-cli as the driver skill for browser automation

and 5 more in the full report

8 fixed7 passed either way7 still failing0 broke

Pass-rate lift: +36 pp
Tokens: +79%
Agent turns: 0%
Response time: -57%

Model gemini-3.6-flashMeasured 8/15/2026v115 of 22 cases passed with skill · 16 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/ai-builder-club-verifier-setup/SKILL.md https://app.decimal.ai/s/ai-builder-club-verifier-setup/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ai-builder-club-verifier-setup, 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/ai-builder-club-verifier-setup/ and pins it in .decimal/skills.lock

decimalai skills add ai-builder-club-verifier-setup

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

curl -fsSL --create-dirs -o .claude/skills/ai-builder-club-verifier-setup/SKILL.md https://app.decimal.ai/s/ai-builder-club-verifier-setup/SKILL.md

Raw file: /s/ai-builder-club-verifier-setup/SKILL.md ↗ · machine-readable summary at /s/ai-builder-club-verifier-setup.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

When generating a fresh .claude/skills/verify/SKILL.md file, where is the base template markdown file retrieved from?

What was checked, without and with the skill
Checked	Without skill	With skill
Reads assets/verify.template.md as the source template	Missed	Passed

case-17 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md124 lines2 files

verifier-setup — scaffold this repo's `/verify` skill

Goal: leave the repo able to prove an engineering task works before it ships — run once, and it wires up everything the per-task /verify loop needs.

You are setting up — not verifying anything yourself right now. The /verify template lives at assets/verify.template.md (next to this skill). Parallels dev-local-setup (which generates a script + its skill doc): a setup skill that leaves behind reusable, repo-specific artifacts.

What this produces (the outputs)

Running verifier-setup end-to-end leaves the repo with:

A /verify skill — .claude/skills/verify/SKILL.md, the repo-tailored per-task verification SOP (spawn a verifier sub-agent → drive the app → screenshot/video proof → open a PR with the proof embedded). Generated in Step 5.
A /dev-local skill + its script — scripts/dev-local.sh and .claude/skills/dev-local/SKILL.md, via dev-local-setup (Step 2) if not already present. The one-command stack /verify depends on.
The driver skill installed — the playwright-cli skill for web apps (Step 2); for non-web, the concrete exercise tool confirmed present.

Step 0 — Inventory what already exists (check before you add ANYTHING)

Before creating anything, take stock — the repo may already have some of this, under whatever name or layout its team chose. Look for the capability, not a specific filename; the paths below are only examples. For each, decide reuse as-is / adapt-extend / create fresh — never blindly overwrite working setup:

A way to start the app — a one-command dev launcher, a Makefile/Procfile target, docker-compose, package scripts (e.g. scripts/dev-local.sh, but any form counts).
A prior verification SOP/skill — from an earlier run of this skill or the team's own convention.
A driver for the app's interface — a browser automation tool already available (e.g. the playwright-cli skill), or the relevant API/CLI client.
An existing test/e2e suite or checks — however organized.
Sandbox/cloud-box config — anything giving isolated per-agent stacks.
An evidence/artifact convention — where proof lands and how a reviewable link gets published (a release, bucket, CI artifacts, etc.).

Every later step is conditional on this inventory: if a capability exists and works,

Track record

Benchmark

11 / 16

test cases passed, vs 5 / 16 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 v4 — 8/3/2026

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

ai-builder-club / skills

skills/verifier-setup/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1Bundled 1 file

Other skills for the same job

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

elianiva/create-verification-skillGenerate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /skill:create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.Close match+24 pp pass-rate lift

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