Chalk Labs
Need help deploying lr-summarize?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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-summarize
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.
About
Use cases: documents, writing
Reviews
Write a reviewNo 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-summarize
What's inside
- Skill name
lr-summarize- Description
- Write a committable markdown summary of the session. Run as the final step of finalization.
- License
- MIT
- Instructions
- 9 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-summarize/SKILL.md`. Resolve it to an absolute path before using it below. Begin the session summarization process. Read `<framework-root>/docs/summarize.md` for detailed instructions. The doc explains the summary file layout, frontmatter schema, narrative prompt, review gate, and UUID echo discipline. The summary is session-wide (one file per session, regardless of attached guests) and is written into the host agent's `sessions/YYYY/MM/` directory. When done, confirm the summary was written (or explicitly skipped) and emit the session UUID in the user-visible output so it can later be correlated with the Claude Code JSONL on the user's machine.
From zroslaw/lore-framework, MIT.
More from zroslaw/lore-framework
- 0.576score
lr-finalize
zroslaw
Full session finalization — reflect, merge, summarize, then commit and push.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
lr-merge
zroslaw
Integrate reflection topics into the agent's lore.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
lr-reflect
zroslaw
Extract session knowledge into reflection topics.
SkillAFreshness: A★ 1Claude Code +9 - 0.541score
lr-list-agents
zroslaw
Show which lore agents are available here, what each one covers, and whether it has a direct shortcut.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
lr-list-repos
zroslaw
Show which lore agent repos are available here, what each one covers, and whether any direct shortcuts exist.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
lr-groom
zroslaw
Iteratively improve Lore structure, retrieval efficiency, and prose quality.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
lr-style
zroslaw
Set the session's Lore communication style.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
lr-check
zroslaw
Check Lore installation health: plugin, agent repos, workspace, and repo freshness.
SkillBFreshness: B★ 1Claude Code +9 - 0.489score
lr-attach
zroslaw
Bring another lore agent's knowledge into the current session for sustained co-work, or list attached guests when called with no args.
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
lr-being
zroslaw
Manage Lore Beings from one entry point.
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
lr-pull-lore
zroslaw
Mid-session refresh of just the active agents' lore agent repos (use /lr-workspace-pull for full-workspace refresh).
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
lr-register-agent
zroslaw
Create or refresh a direct boot shortcut for one specific lore agent.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 7, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/zroslaw/lore-framework
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from zroslaw
- 0.576score
lr-merge
zroslaw
Integrate reflection topics into the agent's lore.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
lr-finalize
zroslaw
Full session finalization — reflect, merge, summarize, then commit and push.
SkillAFreshness: A★ 1Claude Code +9 - 0.576score
lr-reflect
zroslaw
Extract session knowledge into reflection topics.
SkillAFreshness: A★ 1Claude Code +9 - 0.541score
lr-list-repos
zroslaw
Show which lore agent repos are available here, what each one covers, and whether any direct shortcuts exist.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
lr-list-agents
zroslaw
Show which lore agents are available here, what each one covers, and whether it has a direct shortcut.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
lr-style
zroslaw
Set the session's Lore communication style.
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get lr-summarize running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
lr-summarize skill. Agent Mart. https://agentmart.dev/skills/zroslaw-lr-summarize (last updated 2026-10-24)