# Check

> Run /check before merge to confirm a change is sound. Two modes: `/check verify` drives the real app and proves behavior against the spec (every acceptance criterion met, every specced surface built); `/check review` runs a senior code review on a different model than wrote the code. Verify after /develop, review before a PR. Writes findings to docs/reviews/; never edits your code.

- **Type:** Skill
- **Install:** `agentstack add skill-jsmastery-pro-pilot-check`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [jsmastery-pro](https://agentstack.voostack.com/s/jsmastery-pro)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [jsmastery-pro](https://github.com/jsmastery-pro)
- **Source:** https://github.com/jsmastery-pro/pilot/tree/main/skills/check

## Install

```sh
agentstack add skill-jsmastery-pro-pilot-check
```

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

## About

## Output style (plain words, no dashes)

Write everything this skill produces (files, reports, every message to the engineer) in plain, simple language. Keep technical terms that carry real meaning but explain each in plain words. No dashes of any kind: no em dash, no en dash, no hyphen as punctuation. Use short sentences, commas, or parentheses. Clear beats clever.

## What this skill does

`/check` is the pre-merge gate. It confirms a change is sound in two different ways, run as two modes; they are separate jobs and you usually run both, verify first:

- **`verify`** (runtime proof) — run the real app and watch the change behave. Proves the feature actually works and conforms to the spec (every acceptance criterion met, every specced surface built), which green tests never reveal. Read-only on code, owns no durable files. Runs on the main thread. Typically after `/develop`.
- **`review`** (fresh-model code review) — a rigorous senior read of the diff, on a **different model than wrote the code**, because a model reviewing its own output shares its blind spots. Writes severity-ranked findings to `docs/reviews/`. Read-only on code. Typically before opening a PR.

Neither mode edits your code. `verify` points failures at `/debug` or `/develop`; `review` reports findings for the implementer to fix.

## Pick the mode (route before doing anything else)

Read the argument and route:

- Starts with `verify` (or `run`) → runtime proof. Read `modes/verify.md` and follow it fully. Pass any remaining arguments (a feature name, a scope) through.
- Starts with `review` → code review. Read `modes/review.md` and follow it fully. Pass the review steering through unchanged (e.g. `/check review with opus`, `/check review uncommitted`).
- No mode word, or ambiguous → ask once which one, capability-first (a picker where the agent has one, else plain text): question "Which check?", header "Check", options `verify — run the real app and prove it works (recommended right after building)` · `review — a fresh-model read of the diff before a PR`. The picker appends its own free-text option; add it explicitly in a plain-text fallback. Then read that mode's file and follow it.

Do not mix the two in one run. If the engineer clearly wants both, do `verify` first (confirm it works), then offer `review`.

## Portability (any OS, any agent)

Any Agent Skills client on macOS, Linux, or Windows. `git` is the only required CLI and behaves the same everywhere; other shell snippets are POSIX reference, not literal scripts, so use your agent's own cross-platform file, process, and browser tools and apply branching logic yourself. Each mode file adds its own portability notes (browser/HTTP driving for `verify`, the cross-model spawn and bundled-file handling for `review`). No subagent support falls back to running the work inline, noted per mode.

Bundled files live in this skill's folder: `modes/verify.md`, `modes/review.md`, and (for review) `review-agent-prompt.md` and `review-guide.md`. Read only the mode file you routed to; the main agent resolves the review bundled files to absolute paths when it spawns the reviewer.

## Source & license

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

- **Author:** [jsmastery-pro](https://github.com/jsmastery-pro)
- **Source:** [jsmastery-pro/pilot](https://github.com/jsmastery-pro/pilot)
- **License:** MIT

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:** no
- **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-jsmastery-pro-pilot-check
- Seller: https://agentstack.voostack.com/s/jsmastery-pro
- 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%.