New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Macrothink

by LilMGenius in LilMGenius/paperthin

User-invoked read-only pass for checking whether the current direction is tunnel-visioned: strip the session's bait, fan out 2 to 5 same-model fresh reads, and report divergence first without…

MITAuto-check passedDevelopment

Install Macrothink

skills CLI
$ npx skills add LilMGenius/paperthin --skill macrothink -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LilMGenius/paperthin macrothink --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LilMGenius/paperthin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/depth/macrothink .claude/skills/macrothink && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
macrothink
GitHub stars
1.1k
Token cost
~1k tokens
SKILL.md length
539 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

User-invoked read-only pass for checking whether the current direction is tunnel-visioned: strip the session's bait, fan out 2 to 5 same-model fresh reads, and report divergence first without…

  • Works in 8 steps: Name the current direction: the decision… → Strip the prompt to the underlying… → Fan out independent fresh reads of that… → …
  • Development work in your project
  • SKILL.md covers Goal, Workflow, Rules and Verification
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Macrothink is an agent skill from LilMGenius/paperthin. User-invoked read-only pass for checking whether the current direction is tunnel-visioned: strip the session's bait, fan out 2 to 5 same-model fresh reads, and report divergence first without treating convergence as proof.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/macrothink”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Name the current direction: the decision the session is about to keep building on.
  2. Strip the prompt to the underlying problem: goal, constraints, and known facts. Remove the session's own examples, suggested answer…
  3. Fan out independent fresh reads of that stripped restatement: 2 to 5, default 3. Same model is allowed because this pass does not claim…
  4. Collect each read without correcting it toward the session's current direction.
  5. Classify each read against the current direction
  6. Cluster before reporting: when several reads diverge in the same direction, name the shared root they point at — the pattern behind the…
  7. Report divergent-incompatible first, then divergent-compatible, then convergent. Label convergence as reassurance only.
  8. Return control to the main session. This skill is read-only and advisory; it does not rewrite the plan or pick the final answer.

What it can do on your machine

Read from SKILL.md and the folder at commit 7d5dc62. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Macrothink loads about 1k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 539 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~58
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LilMGenius/paperthin at commit 7d5dc62, republished under its MIT licence (© LilMGenius). 539 words, ~1,003 tokens.

Download SKILL.mdSave it as .claude/skills/macrothink/SKILL.md (or your agent's skills folder).
name
macrothink
description
User-invoked read-only pass for checking whether the current direction is tunnel-visioned: strip the session's bait, fan out 2 to 5 same-model fresh reads, and report divergence first without treating convergence as proof.
disable-model-invocation
true

Step back from the session's chosen path and ask several fresh reads what the current direction might be missing.

Goal

macrothink checks the live decision or direction in hand, not the artifact that describes it. It is for moments when the session may have inherited a framing from examples, wording, prior turns, or a first plausible answer.

The product is a spread of independent reads. Divergence is the signal. Convergence is reassurance, never proof.

Workflow

This skill is not model-invoked automatically. When a user explicitly invokes it, the invoked run may create the bounded fresh sub-sessions below; they are read-only inputs to this pass, not separate authority to change the plan.

  1. Name the current direction: the decision the session is about to keep building on.
  2. Strip the prompt to the underlying problem: goal, constraints, and known facts. Remove the session's own examples, suggested answer, preferred naming, and framing-specific wording.
  3. Fan out independent fresh reads of that stripped restatement: 2 to 5, default 3. Same model is allowed because this pass does not claim cross-model verification.
  4. Collect each read without correcting it toward the session's current direction.
  5. Classify each read against the current direction:
    • divergent-incompatible: challenges a premise the direction depends on.
    • divergent-compatible: adds or reframes something useful without discarding the direction.
    • convergent: independently lands near the current direction.
  6. Cluster before reporting: when several reads diverge in the same direction, name the shared root they point at — the pattern behind the divergences is the finding, and the individual reads sit under it as evidence. Do not report five specifics that are one gap seen five times.
  7. Report divergent-incompatible first, then divergent-compatible, then convergent. Label convergence as reassurance only.
  8. Return control to the main session. This skill is read-only and advisory; it does not rewrite the plan or pick the final answer.
Show full SKILL.md (231 more words)Show less

Rules

  • Divergence first. The most important output is the strongest divergent-incompatible finding, if any.
  • Roots over instances. A spread of specific divergences that share one underlying gap is one finding, not many; naming the root is what makes the pass actionable beyond the cases the reads happened to hit.
  • No majority vote or averaging. Do not pick a winner by count, smooth away disagreement, or present agreement as consensus.
  • Same model is allowed. The pass looks for session-framing blind spots, not model-independent truth.
  • User-invoked fan-out only. Do not trigger this skill automatically. If the user invokes it, bounded read-only fresh sub-sessions are allowed to produce the required reads.
  • Not consensus verification. Do not say the direction is verified, proved, validated, or settled by same-model convergence.
  • Convergence is reassurance, not proof. It means this pass did not surface a better angle; it does not certify correctness.
  • Read-only / advisory. Surface candidates and risks; leave decisions and edits to the main workflow.

Verification

Before finishing, confirm:

  1. The restatement removed the session's bait while preserving real constraints.
  2. Every read was classified as divergent-incompatible, divergent-compatible, or convergent.
  3. Divergences sharing one root were reported as that root, with the individual reads as evidence under it.
  4. The report put divergent-incompatible findings first.
  5. Any convergence was described as reassurance, not proof.
  6. The report did not use consensus, majority, averaging, verified, or proved wording.

© LilMGenius, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/depth/macrothink of LilMGenius/paperthin.

Open the folder on GitHubat commit 7d5dc62

Compare with similar skills

Macrothink next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Macrothink compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Macrothink this skillLilMGenius/paperthin1.1k—~1kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Vercel Composition Patterns

    supabase/supabase

    Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 59 repos~726 tokens
    DevelopmentAuto-check passed

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from LilMGenius/paperthin

All 28 skills in this repo

  • Modelchk

    LilMGenius/paperthin

    Size a task's run before spending it: the cheapest sufficient capability tier (fast, standard, frontier) and the reasoning effort within it, on a neutral scale that binds to whatever levels the…

    1.1k GitHub stars~1.6k tokensUpdated 6 days ago
    Auto-check passed

  • Re0 Loop

    LilMGenius/paperthin

    Run repeated build - QA - re0-memo - re0-work cycles while preserving learning and letting code die.

    1.1k GitHub stars~579 tokensUpdated 6 days ago
    Auto-check passed

  • Autobahn

    LilMGenius/paperthin

    Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved…

    1.1k GitHub stars~2.1k tokensUpdated 6 days ago
    Auto-check passed

  • Catchup

    LilMGenius/paperthin

    Rebuild the human's lost context on a project from live state, in plain language: what needs them, what changed, what new words mean.

    1.1k GitHub stars~785 tokensUpdated 6 days ago
    Auto-check passed

  • Debloat

    LilMGenius/paperthin

    Compress an artifact that has accreted into bloat — padding, over-qualification, fused sentences, walls of enumeration, adjacent restatement — down to its load-bearing density, meaning preserved.

    1.1k GitHub stars~813 tokensUpdated 6 days ago
    Auto-check passed

  • Factchk

    LilMGenius/paperthin

    Verify reality-grounded claims against external sources in both directions before they ship — could the 'absurd' be real, could the 'obvious' be false or long-established?

    1.1k GitHub stars~717 tokensUpdated 6 days ago
    Auto-check passed

Categories

Questions about Macrothink

What does Macrothink do?

User-invoked read-only pass for checking whether the current direction is tunnel-visioned: strip the session's bait, fan out 2 to 5 same-model fresh reads, and report divergence first without…. Macrothink is an agent skill from LilMGenius/paperthin. User-invoked read-only pass for checking whether the current direction is tunnel-visioned: strip the session's bait, fan out 2 to 5 same-model fresh reads, and report divergence first without treating convergence as proof.

When should I use Macrothink?

Macrothink fits situations like: development work in your project.

How do I install Macrothink in Claude Code?

Run `npx skills add LilMGenius/paperthin --skill macrothink -a claude-code`. Or copy the skill folder (skills/depth/macrothink in LilMGenius/paperthin) into .claude/skills/macrothink in your project. Claude Code loads it when a task matches its description.

How do I install Macrothink in Codex?

Run `npx skills add LilMGenius/paperthin --skill macrothink -a codex`. Or copy the skill folder (skills/depth/macrothink in LilMGenius/paperthin) into .agents/skills/macrothink in your project. Codex loads it when a task matches its description.

Can I use Macrothink in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LilMGenius/paperthin --skill macrothink -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/macrothink, .gemini/skills/macrothink, .github/skills/macrothink and .opencode/skills/macrothink in your project.

What does Macrothink need to run?

SKILL.md names no scripts, command-line tools or credentials: Macrothink is instructions for the agent only.

Does Macrothink access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Macrothink safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Macrothink use?

Macrothink is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Macrothink use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Macrothink?

Skills that share tags, products or a category with Macrothink: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Macrothink?

LilMGenius (a GitHub user) maintains it in LilMGenius/paperthin, which has 1,130 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on October 1, 2026.

Source: LilMGenius/paperthin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.