unsummarizable
Make prose dense with ideas and resistant to loss through summarization.
Skill by mrmps
Chalk Labs
Need help deploying unsummarizable?
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/mrmps-unsummarizable
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
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/unsummarizable
What's inside
- Skill name
unsummarizable- Description
- Make prose dense with ideas and resistant to loss through summarization. Use when drafting or revising essays, memos, documentation, explanations, posts, or other nonfiction that should contain no fluff, repetition, or disposable framing.
- License
- MIT
- Instructions
- 15 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Unsummarizable Write so that removing words removes interesting ideas. - Cut throat-clearing, repetition, generic framing, and sentences that only summarize nearby sentences. - Preserve specifics, causal links, examples, distinctions, and necessary qualifications. - Make every sentence advance the argument; make every paragraph earn its place. - Test each phrase by removing it. If meaning and insight survive intact, leave it out. - Keep the result clear. Density is not obscurity, jargon, or compressed grammar. When revising existing prose, return the tightened version unless the user asks for commentary. Do not merely shorten it: retain its interesting ideas and add precision where vague language was hiding missing thought. Inspired by [Paul Graham's description of unsummarizable writing](https://x.com/paulg/status/2062891972042637573). Created by [Michael Ryaboy](https://x.com/michael_chomsky).
From mrmps/chomsky-stack, MIT.
More from mrmps/chomsky-stack
- 0.589score
junk-detection
mrmps
Audit diffs, pull requests, and codebases for reward-hacked or Goodharted code, backwards-compatibility cruft, needless fallbacks and shims, accidental…
SkillBFreshness: B★ 7Claude Code +9 - 0.584score
gr
mrmps
Run a complete Greptile CLI review, merge, and production deployment loop for the current pull request: inspect findings, fix every actionable issue, verify…
SkillBFreshness: B★ 7Claude Code +9 - 0.584score
meaningful-contribution
mrmps
Require software changes to be demonstrated, not merely generated.
SkillBFreshness: B★ 7Claude Code +9 - 0.580score
office-hours
mrmps
YC-style office hours.
SkillBFreshness: B★ 7Claude Code +9 - 0.580score
plan-ceo-review
mrmps
CEO/founder-mode plan review.
SkillBFreshness: B★ 7Claude Code +9 - 0.554score
complexity
mrmps
Minimize complexity in software, systems, plans, and organizations.
SkillBFreshness: B★ 7Claude Code +9
Signals
- Stars
- 7
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 29, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mrmps/chomsky-stack
- Website
- x.com/michael_chomsky
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mrmps
- 0.748score
PDF to Markdown
mrmps
Converts PDF files to Markdown inside the browser without uploading them.
ArtifactNo sign-upIn-browser★ 383documents pdf - 0.589score
junk-detection
mrmps
Audit diffs, pull requests, and codebases for reward-hacked or Goodharted code, backwards-compatibility cruft, needless fallbacks and shims, accidental…
SkillBFreshness: B★ 7Claude Code +9 - 0.584score
meaningful-contribution
mrmps
Require software changes to be demonstrated, not merely generated.
SkillBFreshness: B★ 7Claude Code +9 - 0.584score
gr
mrmps
Run a complete Greptile CLI review, merge, and production deployment loop for the current pull request: inspect findings, fix every actionable issue, verify…
SkillBFreshness: B★ 7Claude Code +9 - 0.580score
office-hours
mrmps
YC-style office hours.
SkillBFreshness: B★ 7Claude Code +9 - 0.580score
plan-ceo-review
mrmps
CEO/founder-mode plan review.
SkillBFreshness: B★ 7Claude 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 unsummarizable 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
unsummarizable skill. Agent Mart. https://agentmart.dev/skills/mrmps-unsummarizable (last updated 2026-10-24)