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

Prism

by LilMGenius in LilMGenius/paperthin

Split one artifact — a claim, plan, or file — across 2 to 5 independent lenses, one per genuinely distinct failure mode (correctness, security, readability, cost, adversarial-user), and return their…

MITAuto-check passedWriting & Content

Install Prism

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

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

GitHub CLI
$ gh skill install LilMGenius/paperthin prism --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/mesh/prism .claude/skills/prism && 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
prism
GitHub stars
1.1k
Token cost
~773 tokens
SKILL.md length
416 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Split one artifact — a claim, plan, or file — across 2 to 5 independent lenses, one per genuinely distinct failure mode (correctness, security, readability, cost, adversarial-user), and return their…

  • Works in 6 steps: Read the artifact end to end before… → Choose one lens per genuinely distinct… → Through each lens, produce a one-line… → …
  • One reviewer isnt enough because the failure modes are heterogeneous
  • SKILL.md covers Goal, Workflow, Rules and Verification
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prism is an agent skill from LilMGenius/paperthin. Split one artifact — a claim, plan, or file — across 2 to 5 independent lenses, one per genuinely distinct failure mode (correctness, security, readability, cost, adversarial-user), and return their convergence: where they agree, where they disagree, and the single next question that resolves the disagreement. Use when one reviewer isn't enough because the failure modes are heterogeneous, or a claim looks strong to its author and needs cross-lens pressure before it ships.

Its SKILL.md is about 770 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 Writing & Content, covering Plain language and style rules. 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

  • One reviewer isnt enough because the failure modes are heterogeneous
  • A claim looks strong to its author and needs cross-lens pressure before it ships

Example prompts

  • “/prism”

Workflow steps

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

  1. Read the artifact end to end before choosing the lenses.
  2. Choose one lens per genuinely distinct failure mode — correctness, security, readability, cost, adversarial-user, and the like. Two…
  3. Through each lens, produce a one-line verdict — pass, fail, or unclear — with its single most load-bearing reason. No hedging list; if a…
  4. Compare the verdicts and group them: full agreement, agreement for different reasons, disagreement.
  5. Where there is disagreement, name the single next question whose answer would move it into agreement or a clean split with owners. That…
  6. Where every lens agrees, return the shared verdict with the reasons that were load-bearing for at least two lenses.

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

Prism loads about 773 tokens when it runs. Until then it costs about 121 tokens; SKILL.md has 416 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~773

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). 416 words, ~773 tokens.

Download SKILL.mdSave it as .claude/skills/prism/SKILL.md (or your agent's skills folder).
name
prism
description
Split one artifact — a claim, plan, or file — across 2 to 5 independent lenses, one per genuinely distinct failure mode (correctness, security, readability, cost, adversarial-user), and return their convergence: where they agree, where they disagree, and the single next question that resolves the disagreement. Use when one reviewer isn't enough because the failure modes are heterogeneous, or a claim looks strong to its author and needs cross-lens pressure before it ships.
disable-model-invocation
true

Split one artifact across independent lenses and return where they converge and where they don't.

Goal

The result is a picture of where the lenses agree, where they disagree, and the smallest question that would resolve the disagreement. Not a checklist, and never an average — averaging the lenses is the failure this skill exists to prevent.

Workflow

  1. Read the artifact end to end before choosing the lenses.
  2. Choose one lens per genuinely distinct failure mode — correctness, security, readability, cost, adversarial-user, and the like. Two candidate lenses that share a failure mode are one lens, not two. In practice this lands between 2 and 5: below 2 there is nothing to converge, and past 5 you are almost always padding with lenses that overlap. There is no default count — the artifact's distinct failure modes set it.
  3. Through each lens, produce a one-line verdict — pass, fail, or unclear — with its single most load-bearing reason. No hedging list; if a reason isn't load-bearing, drop it.
  4. Compare the verdicts and group them: full agreement, agreement for different reasons, disagreement.
  5. Where there is disagreement, name the single next question whose answer would move it into agreement or a clean split with owners. That question is the output, not the individual verdicts.
  6. Where every lens agrees, return the shared verdict with the reasons that were load-bearing for at least two lenses.
Show full SKILL.md (185 more words)Show less

Rules

  • Independent lenses, not roles. A "security reviewer" and a "senior security reviewer" are one lens, not two.
  • One reason per lens — the load-bearing one. A lens that returns a list is hedging.
  • Disagreement is the product. A prism that agrees on everything did not need to be run.
  • Never average. If two lenses split, the answer is the question that resolves the split, not the midpoint of their verdicts.
  • Draw the lenses fresh for the artifact in hand. A lens useful for a spec may be useless for a migration; don't carry lenses across artifacts.
  • Don't manufacture disagreement. A run that finds none returns the shared verdict and stops.
  • User-invoked on purpose: plural lenses are an opt-in spend, and their convergence must never masquerade as automatic proof, so this fires only when deliberately reached for.

Verification

The result reads as a picture, not a checklist — a reader sees which lenses agreed, which disagreed, and the one question that matters, and can act on it without re-running the prism. If they'd need to re-run it to know what to do next, step 5 was skipped.

© 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/mesh/prism of LilMGenius/paperthin.

Open the folder on GitHubat commit 7d5dc62

Compare with similar skills

Prism 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.

Prism compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prism this skillLilMGenius/paperthin1.1k—~773Automated safety check: PassMIT
Simple Issue Descriptionevery-app/open-seo23k1 repos~1.2kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins10k10 repos~2.4kAutomated safety check: PassNone
Docs Reader Reviewprisma/web1.1k—~2.4kAutomated safety check: PassNone
Chinese Technical Writingleter/zh-tech-writing334—~656Automated safety check: PassMIT
Readability FeedbackJetBrains/youtrackdb437—~2.3kAutomated safety check: PassApache-2.0

Similar skills

  • Simple Issue Description

    every-app/open-seo

    Turn a rough bug report, feature request, support note, or pull request into a short, plain-language issue focused on the problem and desired behavior.

    23k GitHub starsUsed in 1 repo~1.2k tokens
    Writing & ContentAuto-check passed

  • Technical Writing Standard

    cursor/plugins

    Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    10k GitHub starsUsed in 10 repos~2.4k tokens
    Writing & ContentAuto-check passed

  • Docs Reader Review

    prisma/web

    Official

    A skill your agent uses when a docs page or section has been written or rewritten and is about to be handed over, when the operator says "reader review", "does this read like a human wrote it", "too…

    1.1k GitHub stars~2.4k tokensUpdated yesterday
    Writing & ContentAuto-check passed

  • Chinese Technical Writing

    leter/zh-tech-writing

    Sets writing rules for Chinese technical docs: short plain sentences, consistent typography and a checklist for removing AI-sounding filler.

    334 GitHub stars~656 tokensUpdated 14 days ago
    Writing & ContentAuto-check passed

  • Readability Feedback

    JetBrains/youtrackdb

    Official

    Audit a finished design document for hard-to-read or hard-to-understand paragraphs, then harden the house-style rules so future design docs avoid them.

    437 GitHub stars~2.3k tokensUpdated yesterday
    Writing & ContentAuto-check passed

  • Nbj Write Clearly

    daniel-p-green/nbj-write-clearly

    Drafts, revises, and audits reader-first technical and product documentation.

    117 GitHub stars~1.1k tokensUpdated 1 mo ago
    Writing & ContentAuto-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 7 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 7 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 7 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 7 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 7 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 7 days ago
    Auto-check passed

Categories

Questions about Prism

What does Prism do?

Split one artifact — a claim, plan, or file — across 2 to 5 independent lenses, one per genuinely distinct failure mode (correctness, security, readability, cost, adversarial-user), and return their…. Prism is an agent skill from LilMGenius/paperthin. Split one artifact — a claim, plan, or file — across 2 to 5 independent lenses, one per genuinely distinct failure mode (correctness, security, readability, cost, adversarial-user), and return their convergence: where they agree, where they disagree, and the single next question that resolves the disagreement.

When should I use Prism?

Prism fits situations like: one reviewer isnt enough because the failure modes are heterogeneous; A claim looks strong to its author and needs cross-lens pressure before it ships.

How do I install Prism in Claude Code?

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

How do I install Prism in Codex?

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

Can I use Prism 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 prism -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prism, .gemini/skills/prism, .github/skills/prism and .opencode/skills/prism in your project.

What does Prism need to run?

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

Does Prism 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 Prism 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 Prism use?

Prism 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 Prism use?

About 773 tokens (SKILL.md is roughly 3.1k 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 Prism?

Skills that share tags, products or a category with Prism: Simple Issue Description (every-app/open-seo, 23k stars), Technical Writing Standard (cursor/plugins, 10k stars), Docs Reader Review (prisma/web, 1.1k stars) and Chinese Technical Writing (leter/zh-tech-writing, 334 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prism?

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.