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

Epistemic Challenge

by AnastasiyaW in AnastasiyaW/codex-claude-code-config

A skill your agent uses when the user asks the agent not to agree automatically, to challenge an assumption, evaluate a proposal critically, identify counterevidence, or make a high-consequence…

MITAuto-check passed

Install Epistemic Challenge

skills CLI
$ npx skills add AnastasiyaW/codex-claude-code-config --skill epistemic-challenge -a claude-code

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

GitHub CLI
$ gh skill install AnastasiyaW/codex-claude-code-config epistemic-challenge --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/AnastasiyaW/codex-claude-code-config.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/operational/epistemic-challenge .claude/skills/epistemic-challenge && 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
epistemic-challenge
GitHub stars
154
Token cost
~1.2k tokens
SKILL.md length
531 words
Files
1
Skills in repo
50
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user asks the agent not to agree automatically, to challenge an assumption, evaluate a proposal critically, identify counterevidence, or make a high-consequence…

  • Works in 5 steps: State the operative claim or decision in… → Collect source-backed evidence before… → Name the strongest realistic… → …
  • The user asks the agent not to agree automatically
  • SKILL.md covers Purpose, When to use, Procedure and Output contract, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Epistemic Challenge is an agent skill from AnastasiyaW/codex-claude-code-config. Use this skill when the user asks the agent not to agree automatically, to challenge an assumption, evaluate a proposal critically, identify counterevidence, or make a high-consequence decision under uncertainty. Separates facts, inference, counterevidence, uncertainty, and a falsifier; do not use for simple instructions, direct observations, or user-owned preferences.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Claude Code, Codex, and multi-agent configuration system: principles, hooks, skills, and workflow patterns for AI-assisted development. The licence is MIT.

When your agent uses it

  • The user asks the agent not to agree automatically
  • Challenge an assumption
  • Evaluate a proposal critically
  • Identify counterevidence

Example prompts

  • “/epistemic-challenge”

Workflow steps

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

  1. State the operative claim or decision in a falsifiable form. Separate a
  2. Collect source-backed evidence before giving a verdict. First prefer a
  3. Name the strongest realistic counter-hypothesis and the observation that
  4. For research or a consequential decision, verify the discriminator without
  5. Return one of: SUPPORTED, REFUTED, INCONCLUSIVE, or VALUE_CHOICE.

What it can do on your machine

Read from SKILL.md and the folder at commit 67709af. 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 (its code samples are markdown).

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

  • Network

    Links to these hosts (documentation or services it may open):

    • aclanthology.org
    • openai.com
    • arxiv.org

    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

Epistemic Challenge loads about 1.2k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 531 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~98
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 AnastasiyaW/codex-claude-code-config at commit 67709af, republished under its MIT licence (© AnastasiyaW). 531 words, ~1,172 tokens.

Download SKILL.mdSave it as .claude/skills/epistemic-challenge/SKILL.md (or your agent's skills folder).
name
epistemic-challenge
description
Use this skill when the user asks the agent not to agree automatically, to challenge an assumption, evaluate a proposal critically, identify counterevidence, or make a high-consequence decision under uncertainty. Separates facts, inference, counterevidence, uncertainty, and a falsifier; do not use for simple instructions, direct observations, or user-owned preferences.

Epistemic Challenge

Purpose

Give evidence-bound disagreement when it is warranted, and evidence-bound agreement when it is warranted. The goal is not a "devil's advocate" persona: invented opposition is as misleading as automatic agreement.

When to use

Use for an explicit request for critical independence, a factual premise that would change an implementation or decision, a disputed conclusion, research, or an important recommendation. Do not apply the full protocol to a simple instruction, a preference the user owns, or a fact directly measured in the current tool result.

Procedure

  1. State the operative claim or decision in a falsifiable form. Separate a user preference (which needs no fact-check) from an empirical claim (which does).
  2. Collect source-backed evidence before giving a verdict. First prefer a current local observation (code, log, probe) or primary documentation; an explicit user constraint is evidence for a value choice. Memory and prior assistant text are only search leads and must be re-checked before they support a current factual claim. User confidence and a pleasing narrative are not evidence.
  3. Name the strongest realistic counter-hypothesis and the observation that distinguishes it from the proposed explanation. Do not create a weak counterargument merely to sound critical.
  4. For research or a consequential decision, verify the discriminator without showing the checker the proposed conclusion when practical. Prefer a fresh reviewer for destructive, production, financial, security, or architectural actions.
  5. Return one of: SUPPORTED, REFUTED, INCONCLUSIVE, or VALUE_CHOICE. Say what would change the verdict. Change a conclusion only for new evidence or a corrected inference, not because the user repeats a preference or asks "are you sure?".

Output contract

For a substantive claim, use this compact shape:

markdown
Verdict: SUPPORTED | REFUTED | INCONCLUSIVE | VALUE_CHOICE
Evidence: [observed source or command result]
Counterevidence / alternative: [strongest live alternative, or none found]
Boundary: [what was not established]
Next falsifier: [one observation that would change the verdict]

When agreement is supported, say so plainly. Do not start with praise, validation, or agreement before the evidence.

Delegated review

Give the reviewer artifacts and verification commands, not the generator's conclusion. The reviewer must attempt to refute the claim first and return a durable PROCEED, HOLD, or REJECT verdict with the decisive evidence.

Show full SKILL.md (201 more words)Show less

Gotchas

  • "Be more critical" alone does not make an answer true. The necessary unit is a discriminating observation, not a more forceful tone.
  • A response may legitimately agree. Penalize unsupported agreement, not agreement itself.
  • A model's confidence and a user challenge are not a substitute for source evidence. If no discriminator is accessible, keep the result INCONCLUSIVE.
  • Do not expose a long private reasoning trace. Report evidence, assumptions, uncertainty, and the actionable check.

Troubleshooting

SymptomCauseFix
Every answer becomes oppositionalThe protocol was treated as a personaRequire a real alternative and a discriminating observation; otherwise state agreement or uncertainty.
Agent changes a correct conclusion after "are you sure?"Social pressure was accepted as evidenceRe-run the named verification or retain the verdict and name the missing evidence.
Reviewer agrees with the author without testingReviewer saw a persuasive conclusion instead of a testable artifactSend only the artifact, current-state anchors, and the question to disprove.

Evidence basis

  • Chain-of-Verification uses independent verification questions to reduce hallucinations.
  • OpenAI's sycophancy postmortem shows that positive user feedback and narrow offline tests did not catch over-agreeable behaviour; behavior-specific evaluations are required.
  • Sharma et al. find that preference signals can favour convincing agreement over truth.

© AnastasiyaW, 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/operational/epistemic-challenge of AnastasiyaW/codex-claude-code-config.

Open the folder on GitHubat commit 67709af

Compare with similar skills

Epistemic Challenge 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.

Epistemic Challenge compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Epistemic Challenge this skillAnastasiyaW/codex-claude-code-config154—~1.2kAutomated safety check: PassMIT
Agent Challengesruvnet/ruflo74k2 repos~995Automated safety check: PassMIT
Challengealirezarezvani/claude-skills28k1 repos~1.7kAutomated safety check: PassMIT
Challengepedrohcgs/claude-code-my-workflow1.7k—~1.9kAutomated safety check: NotesMIT
Challenge Reviewwerf/werf4.7k—~1.1kAutomated safety check: PassApache-2.0
Solve Challengeljagiello/ctf-skills3.4k—~2.3kAutomated safety check: NotesMIT

Similar skills

  • Agent Challenges

    ruvnet/ruflo

    Agent skill for challenges - invoke with $agent-challenges. An agent skill from ruvnet/ruflo.

    74k GitHub starsUsed in 2 repos~995 tokens
    Auto-check passed

  • Challenge

    alirezarezvani/claude-skills

    Pre-mortem plan analysis. An agent skill from alirezarezvani/claude-skills.

    28k GitHub starsUsed in 1 repo~1.7k tokens
    Business, Finance & HRAuto-check passed

  • Challenge

    pedrohcgs/claude-code-my-workflow

    Stress-test a finding against the choices you did not make. An agent skill from pedrohcgs/claude-code-my-workflow.

    1.7k GitHub stars~1.9k tokensUpdated 13 days ago
    Testing & QAAuto-check: notes

  • Challenge Review

    werf/werf

    Independent challenge pass for a non-trivial or high-risk change.

    4.7k GitHub stars~1.1k tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed

  • Solve Challenge

    ljagiello/ctf-skills

    Solves CTF challenges by performing first-pass triage, identifying the dominant category, and routing execution to the right specialized ctf- skill.

    3.4k GitHub stars~2.3k tokensUpdated 27 days ago
    SecurityAuto-check: notes

  • Challenge

    wp-media/wp-rocket

    Adversarially review a grooming spec before implementation starts.

    767 GitHub stars~674 tokensUpdated yesterday
    Auto-check passed

More from AnastasiyaW/codex-claude-code-config

All 50 skills in this repo

  • Bug Reproducer

    AnastasiyaW/codex-claude-code-config

    Find likely software bugs in a codebase, rank concrete bug candidates, and prove or reject them with focused regression tests before proposing a fix.

    154 GitHub stars~4.1k tokensUpdated today
    Auto-check passed

  • Motion Framer

    AnastasiyaW/codex-claude-code-config

    A skill your agent uses when implementing Motion or Framer Motion in React/JavaScript: interactive UI components, micro-interactions, gestures, layout or page transitions, and scroll-based animation.

    154 GitHub starsUsed in 1 repo~5.2k tokens
    Auto-check passed

  • Proof Verify

    AnastasiyaW/codex-claude-code-config

    Plan-based verification - freeze acceptance criteria before building, then verify after with an independent fresh-context agent (the builder must not verify their own work).

    154 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Workflow Orchestration

    AnastasiyaW/codex-claude-code-config

    Написание и запуск Claude Code dynamic workflows (JS-оркестратор субагентов).

    154 GitHub stars~3.8k tokensUpdated today
    Auto-check passed

  • Notebooklm Grounded Research

    AnastasiyaW/codex-claude-code-config

    A skill your agent uses when: NotebookLM, notebooklm MCP, large documentation sets, courses, books, papers, or citation-backed research are mentioned.

    154 GitHub stars~2.4k tokensUpdated today
    Auto-check: warnings

  • Deepseek Provider Contract

    AnastasiyaW/codex-claude-code-config

    Validate a proposed DeepSeek API integration before any key or project context is sent: check thinking-mode tool-call history, strict-schema assumptions, bounded output, and provider data boundaries.

    154 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Questions about Epistemic Challenge

What does Epistemic Challenge do?

A skill your agent uses when the user asks the agent not to agree automatically, to challenge an assumption, evaluate a proposal critically, identify counterevidence, or make a high-consequence…. Epistemic Challenge is an agent skill from AnastasiyaW/codex-claude-code-config. Use this skill when the user asks the agent not to agree automatically, to challenge an assumption, evaluate a proposal critically, identify counterevidence, or make a high-consequence decision under uncertainty.

When should I use Epistemic Challenge?

Epistemic Challenge fits situations like: the user asks the agent not to agree automatically; challenge an assumption; evaluate a proposal critically; identify counterevidence.

How do I install Epistemic Challenge in Claude Code?

Run `npx skills add AnastasiyaW/codex-claude-code-config --skill epistemic-challenge -a claude-code`. Or copy the skill folder (skills/operational/epistemic-challenge in AnastasiyaW/codex-claude-code-config) into .claude/skills/epistemic-challenge in your project. Claude Code loads it when a task matches its description.

How do I install Epistemic Challenge in Codex?

Run `npx skills add AnastasiyaW/codex-claude-code-config --skill epistemic-challenge -a codex`. Or copy the skill folder (skills/operational/epistemic-challenge in AnastasiyaW/codex-claude-code-config) into .agents/skills/epistemic-challenge in your project. Codex loads it when a task matches its description.

Can I use Epistemic Challenge 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 AnastasiyaW/codex-claude-code-config --skill epistemic-challenge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/epistemic-challenge, .gemini/skills/epistemic-challenge, .github/skills/epistemic-challenge and .opencode/skills/epistemic-challenge in your project.

What does Epistemic Challenge need to run?

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

Does Epistemic Challenge access the network?

SKILL.md names 3 domains. As links in the text: aclanthology.org, openai.com and arxiv.org. This is read from the text; nothing was executed.

Is Epistemic Challenge 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 Epistemic Challenge use?

Epistemic Challenge 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 Epistemic Challenge use?

About 1.2k tokens (SKILL.md is roughly 4.7k 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 Epistemic Challenge?

Skills that share tags, products or a category with Epistemic Challenge: Agent Challenges (ruvnet/ruflo, 74k stars), Challenge (alirezarezvani/claude-skills, 28k stars), Challenge (pedrohcgs/claude-code-my-workflow, 1.7k stars) and Challenge Review (werf/werf, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Epistemic Challenge?

AnastasiyaW (a GitHub user) maintains it in AnastasiyaW/codex-claude-code-config, which has 154 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 9, 2026.

Source: AnastasiyaW/codex-claude-code-config on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.