# Lore Dev Verification

> Verifies changes to the Lore repo and Lore workflow skills. Use when working on Lore PRs, issue slices, recall/brief/handoff skills, CLI/MCP retrieval, store migrations, adapters, privacy/destructive-memory behavior, packaging, or any change that needs proof before it is called done.

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

## Install

```sh
agentstack add skill-jordanhindo-lore-lore-dev-verification
```

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

## About

# Lore Dev Verification

Use this before calling Lore work complete. Lore is memory infrastructure, so
verification must prove behavior without leaking private transcripts.

## Quick Start

1. Classify the change with `references/verification-matrix.md`.
2. Run the targeted checks for that row.
3. For skill changes, run the bundle and test-report validators:
   ```bash
   node skills/lore-dev-verification/scripts/validate-workflow-skill.mjs skills/
   ```
4. Run `npm run check` before merge unless the issue explicitly narrows the gate.
5. Record what ran in the issue or skill `evals/test-report.md`.

## Rules

- Current files, tests, and runtime artifacts beat old transcript memory.
- CLI and MCP surfaces must preserve JSON-envelope parity when they expose the
  same operation.
- Fixtures must be synthetic or scrubbed. Never commit real transcript excerpts,
  credentials, private project text, or personal memory.
- Real-store smoke checks are local proof only. Summarize counts/outcomes, not
  private message contents.
- A workflow skill is not done until `evals/test-report.md` contains concrete
  eval evidence, validator output, trigger checks when relevant, privacy notes,
  and remaining risks.

## References

- `references/verification-matrix.md` maps change type to required checks.
- `references/skill-review.md` explains workflow-skill review and report gates.
- `examples/` contains example verification plans for common Lore changes.

## Source & license

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

- **Author:** [jordanhindo](https://github.com/jordanhindo)
- **Source:** [jordanhindo/lore](https://github.com/jordanhindo/lore)
- **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-jordanhindo-lore-lore-dev-verification
- Seller: https://agentstack.voostack.com/s/jordanhindo
- 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%.