# Lore Brief

> Produces proposal-only Lore continuity briefs for the last 24 hours by default, with cited evidence, open work, learned signals, memory-card candidates, contradiction candidates, and sideEffects:false. Use for daily briefs, recap/continuity summaries, scheduled read-only synthesis, or proposing next actions from Lore without creating anything automatically.

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

## Install

```sh
agentstack add skill-jordanhindo-lore-lore-brief
```

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

## About

# Lore Brief

Use this when the user wants a continuity brief, daily recap, or proposal-only synthesis from Lore. Default window is the rolling last 24 hours ending at run time unless the user supplies a window.

## Workflow

1. Compute retrieval bounds: local date label for humans, explicit ISO `fromIso`/`toIso` values for output and `--since`/`--until` values for Lore commands.
2. Run `lore status --json --since  --until ` and stop on unhealthy status. If status is `possibly_unsynced` and `schemaVersion` is greater than `supportedSchemaVersion`, do not recommend bare `lore sync` as sufficient; say Lore must be updated before write/sync recovery can refresh the window.
3. Use `lore-recall` evidence packet rules for searches and citations.
4. Produce a brief with `sideEffects: false`.
5. Propose follow-up objects only. Do not create jobs, issues, wiki pages, skills, tasks, memory cards, code, or automations unless the user asks as a follow-up.

## Output Sections

- `window`: `fromIso`, `toIso`, `timeZone`, `localDateLabel`.
- `completedActivity`: evidence-backed work that finished in the window.
- `openWork`: unresolved work with cited ids or marked uncited.
- `changes`: evidence-backed changes to code, docs, skills, workflow, setup, or state.
- `learnedSignals`: things discovered while briefing.
- `proposals`: read-only suggestions using `references/proposal-vocabulary.md`.
- `memoryCardCandidates`: decision, claim, commitment, artifact, contradiction, open_question.
- `contradictionCandidates`: both sides with evidence, no averaging.
- `gaps`: optional notes for what Lore could not prove.

## Rules

- Always state `sideEffects: false`.
- Scheduled use is read-only synthesis, never mutation authority.
- Date labels shown to the user use local timezone; retrieval filters use explicit ISO instants.
- Contradictions preserve both sides and evidence. Do not resolve unless current artifacts prove a side.
- If evidence is stale, label it and propose verification instead of acting.

## References

- `references/brief-schema.md` for structure.
- `references/proposal-vocabulary.md` for shared proposal/candidate shapes reused by handoff.
- `examples/` for good and bad outputs.

## 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-brief
- 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%.