Skip to content
Agentmart
Submit a tool

lr-merge

Integrate reflection topics into the agent's lore.

Skill by zroslaw

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/zroslaw-lr-merge

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Integrate reflection topics into the agent's lore. Run after /lr-reflect.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/lr-merge

What's inside

Skill name
lr-merge
Description
Integrate reflection topics into the agent's lore. Run after /lr-reflect.
License
MIT
Instructions
11 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

`<framework-root>` is the framework root — the directory that contains the `VERSION` file, two levels up from this `.cursor-skills/lr-merge/SKILL.md`. Resolve it to an absolute path before using it below.

Begin the merge process to integrate reflection topics into lore.

Read `<framework-root>/docs/process-merge.md` for detailed instructions. The doc explains the execution model — merge always runs in a subagent, one per active agent, in parallel. Each subagent boots as its target agent before running the merge procedure, giving it that agent's role and lore context naturally. Merge does not commit; committing happens at the end of `/lr:finalize`, or by the user directly if merge is invoked standalone.

Collect active agents per `process-merge.md` — during `/lr:finalize`, participant revision's finalization host and participant list (including any retained booted guest); standalone, the booted host plus guests attached via `/lr:attach`. Spawn a subagent per agent with a brief to boot as that agent and then run the merge procedure, then aggregate the returned summaries.

When done, confirm what was integrated for each active agent.

From zroslaw/lore-framework, MIT.

More from zroslaw/lore-framework

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Oct 4, 2026 (26 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from zroslaw

Cite this page

lr-merge skill. Agent Mart. https://agentmart.dev/skills/zroslaw-lr-merge (last updated 2026-10-24)