# Verify

> Use before claiming work is complete, fixed, or passing. Requires running verification commands and reading output before making any success claims. Evidence before assertions.

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

## Install

```sh
agentstack add skill-sandsower-beislid-verify
```

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

## About

# Check Done

No completion claims without fresh verification evidence. Period.

Before ANY claim that work is done, tests pass, a bug is fixed, or code is working — you MUST run the verification command, read the output, and confirm it matches the claim.

If the repo declares custom lifecycle hooks, read `../lifecycle-hooks.md` and honor any phase-boundary hooks before and after verify.

## The Gate

When reporting durable evidence, use the terse Verification report shape from `artifact-templates.md`.

For every positive claim about work state:

1. **Identify** the verification command (test suite, linter, build, curl, etc.)
2. **Run it** fresh — not from memory, not from a previous run
3. **Read** the actual output
4. **Confirm** the output supports the claim
5. **Then** make the claim

## What Requires Evidence

| Claim | Required evidence |
|---|---|
| "Tests pass" | Test command output showing 0 failures |
| "Linter clean" | Linter output showing 0 errors |
| "Build succeeds" | Build command with exit code 0 |
| "Bug is fixed" | Failing test now passes (red to green) |
| "Feature works" | Test or manual verification output |

## Proof Requirements

When a Work Contract includes `proof_requirements`, match verification evidence to that vocabulary before claiming done. A command log can satisfy `command_gate`, review output can satisfy `review` or `fresh_eyes`, CI status can satisfy `ci_check`, and a deck/screenshot can satisfy `screenshot_show_me`. Missing required proof means stop and report the missing proof or human interrupt; do not downgrade it to advisory in chat.

## Red Flags

These words in your response without preceding evidence mean you're guessing:
- "should work", "probably works", "seems to be working"
- "I believe this fixes", "this should resolve"
- "tests should pass now"

Replace with: run the command, paste the output, state the fact.

## After Subagent Work

Agent success reports are not evidence. After a subagent completes:
1. Check the VCS diff
2. Run verification independently
3. Then confirm

## Visual Proof

If the user explicitly asks for a richer visual proof deck, invoke `show-me`. If verification would be clearer as screenshots, videos, diffs, command logs, or a browsable HTML report, suggest `show-me` and wait for a direct user request. Do not run `show-me` automatically; it is a manual/user-requested escalation in v1.

## Source & license

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

- **Author:** [sandsower](https://github.com/sandsower)
- **Source:** [sandsower/beislid](https://github.com/sandsower/beislid)
- **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:** 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-sandsower-beislid-verify
- Seller: https://agentstack.voostack.com/s/sandsower
- 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%.