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

Mandela

by LilMGenius in LilMGenius/paperthin

Audit any eval, metric, experiment, or benchmark for leakage — does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever…

MITAuto-check passedDevelopment

Install Mandela

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

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

GitHub CLI
$ gh skill install LilMGenius/paperthin mandela --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/mandela .claude/skills/mandela && 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
mandela
GitHub stars
1.1k
Token cost
~798 tokens
SKILL.md length
392 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

Audit any eval, metric, experiment, or benchmark for leakage — does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever…

  • Works in 4 steps: Identify the validation (eval / metric /… → Ask the core question: does external… → Test the validation against all 8… → …
  • Development work in your project
  • SKILL.md covers Goal, Workflow, The 8 leakage patterns and Rules, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Mandela is an agent skill from LilMGenius/paperthin. Audit any eval, metric, experiment, or benchmark for leakage — does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever produced? Use before trusting any 'how we'll know it worked' — an A/B, a holdout, a score, a validation — and whenever a result feels too clean or self-confirming. Walks an 8-pattern leakage taxonomy and returns only the patterns that fire, each with an independence fix. Read-only.

Its SKILL.md is about 800 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

  • “how we”
  • “/mandela”

Workflow steps

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

  1. Identify the validation (eval / metric / experiment / holdout / "how we'll know"). Name its components — what plays model, scorer…
  2. Ask the core question: does external ground-truth enter independently?
  3. Test the validation against all 8 patterns below (some apply only to certain components — a human subject, a scorer); report only the ones…
  4. Give the independent-ground-truth fix for each hit.

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

Mandela loads about 798 tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 392 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~122
When it runs · the whole SKILL.md, loaded when a task matches
~798

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). 392 words, ~798 tokens.

Download SKILL.mdSave it as .claude/skills/mandela/SKILL.md (or your agent's skills folder).
name
mandela
description
Audit any eval, metric, experiment, or benchmark for leakage — does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever produced? Use before trusting any 'how we'll know it worked' — an A/B, a holdout, a score, a validation — and whenever a result feels too clean or self-confirming. Walks an 8-pattern leakage taxonomy and returns only the patterns that fire, each with an independence fix. Read-only.

Audit a validation for leakage: does outside ground-truth actually enter, or is everyone confirming a result no one independently produced?

Goal

The name is the Mandela Effect — a whole population confidently remembers something that never independently happened; a leaky validation is the same shape. Walk the 8 patterns below. mandela checks one thing: whether a validation is independent, or whether the designer, model, and scorer are only confirming each other.

Workflow

  1. Identify the validation (eval / metric / experiment / holdout / "how we'll know"). Name its components — what plays model, scorer, designer, dataset.
  2. Ask the core question: does external ground-truth enter independently?
  3. Test the validation against all 8 patterns below (some apply only to certain components — a human subject, a scorer); report only the ones that fire, each by name.
  4. Give the independent-ground-truth fix for each hit.

The 8 leakage patterns

  1. Recall, not reason — a memorized answer recited instead of one actually derived; the system already knows the result it is supposedly computing.
  2. Wrong null hypothesis — an ablation that removes a surface label but not the underlying signal the system actually exploits, so the "control" still leaks.
  3. Shared hallucination — two components verifying each other; circularity reported as a number.
  4. Tautology — a scorer grading buckets it drew itself.
  5. Verifier = designer — a private, unreproducible recipe in a holdout's clothes.
  6. Shared-pool bias — train and holdout drawn from one labeler pool, so one bias enters both sides.
  7. Frame injection — a question that hands the subject the hypothesis.
  8. Demand characteristics — measured subjects who know they're being measured.
Show full SKILL.md (131 more words)Show less

Rules

  • Subtlety that bites twice: you can blind the output value and still leak the collection recipe.
  • Read-only — name the leak and the independence fix; don't rewrite the experiment.
  • For a high-stakes validation, you may add one independent fresh-context auditor (N=1) handed only the validation design, not this session's reasoning, to re-run the 8-pattern taxonomy blind; the default remains same-session and read-only.

Verification

Turn mandela on this audit:

  1. Run patterns #3–#5 on yourself: are you a scorer grading buckets you drew (Tautology, #4)? is the verifier the designer (#5)? is your verdict a shared hallucination with the design's own claims (#3)?
  2. Could a reader who didn't run the audit reach your verdict from the cited evidence alone — independent ground-truth?
  3. The report names the root, not a laundry list.

© 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/mandela of LilMGenius/paperthin.

Open the folder on GitHubat commit 7d5dc62

Compare with similar skills

Mandela 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.

Mandela compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Mandela this skillLilMGenius/paperthin1.1k—~798Automated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 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 58 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.

    297k 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 8 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 8 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 8 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 8 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 8 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 8 days ago
    Auto-check passed

Categories

Questions about Mandela

What does Mandela do?

Audit any eval, metric, experiment, or benchmark for leakage — does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever…. Mandela is an agent skill from LilMGenius/paperthin. Audit any eval, metric, experiment, or benchmark for leakage — does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever produced?

When should I use Mandela?

Mandela fits situations like: development work in your project.

How do I install Mandela in Claude Code?

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

How do I install Mandela in Codex?

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

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

What does Mandela need to run?

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

Does Mandela 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 Mandela 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 Mandela use?

Mandela 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 Mandela use?

About 798 tokens (SKILL.md is roughly 3.2k 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 Mandela?

Skills that share tags, products or a category with Mandela: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k 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 Mandela?

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.