# Layerkit Checker Assist

> Read-only checker assistant — risk checklist only; never approve, apply, or write checks[].

- **Type:** Skill
- **Install:** `agentstack add skill-hariharapanigrahy-layerkit-layerkit-checker-assist`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [hariharapanigrahy](https://agentstack.voostack.com/s/hariharapanigrahy)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [hariharapanigrahy](https://github.com/hariharapanigrahy)
- **Source:** https://github.com/hariharapanigrahy/layerkit/tree/main/skills/layerkit-checker-assist

## Install

```sh
agentstack add skill-hariharapanigrahy-layerkit-layerkit-checker-assist
```

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

## About

# layerkit-checker-assist

Assist a **human checker**. This skill is **read-only** on the approval path.

## Allowed

1. Read proposals, maps, `{projectDir}/memory/`, doctor output, eval results.
2. Produce a **risk checklist markdown**:
   - sources quality (primary docs vs blog vs catalog-only)
   - invented or uncited rules
   - privacy gaps / missing consent
   - empty maps treated as complete
   - maker ≠ checker identity
   - client package verification coverage of primary intents
3. Suggest residual questions for the human reviewer.
4. Point at failing gates (`npm run eval:ci`) without re-running network research unless asked.

```bash
layerkit proposal list
layerkit doctor
layerkit memory list --type proposals
# optional local: npm run eval:ci
```

## Forbidden (hard)

- Calling `layerkit proposal apply`, `approve`, `promote`, or any approve/promote CLI
- Writing `checks[]` on a proposal or mutating proposal/map JSON in place
- Self-approving as the same actor as the maker
- Inventing missing evidence to make a proposal look ready
- Submitting proposals as maker while acting as checker in the same session (strict)

## Output

Checklist only. Human checker decides approve/reject via:

```bash
layerkit proposal approve  --by  --role checker
# or
layerkit proposal reject  --by  --role checker --comment "..."
```

## Success criteria

- [ ] Checklist covers sources, invention risk, privacy, maker≠checker
- [ ] No apply/approve side effects from this skill
- [ ] Residual questions are actionable

## Source & license

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

- **Author:** [hariharapanigrahy](https://github.com/hariharapanigrahy)
- **Source:** [hariharapanigrahy/layerkit](https://github.com/hariharapanigrahy/layerkit)
- **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-hariharapanigrahy-layerkit-layerkit-checker-assist
- Seller: https://agentstack.voostack.com/s/hariharapanigrahy
- 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%.