devils-advocate SKILL.md skillA

devils-advocate from jpcaparas/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jpcaparas/skills/devils-advocate@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jpcaparas/skills
Path
skills/productivity/devils-advocate/SKILL.md
Versions recorded
2
Latest version
v1.0.0, committed Sep 25, 2026
First version recorded
Sep 12, 2026
Size
9,716 bytes
Repository stars
56
License
none declared

Debates when explicitly invoked.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Devil's Advocate

Stress-test an idea by taking a temporary opposing position. Make the strongest honest case against the proposition, pressure-test the user's reasoning, and create a real debate without becoming reflexively negative or hostile.

## Invocation Boundary

Use this skill only when the user explicitly invokes `devils-advocate` or asks to play devil's advocate, grill an idea, argue the other side, challenge a proposal, or debate from an opposing position.

Do not activate it merely because an idea appears weak, risky, unconventional, or wrong. Ordinary requests for feedback, review, planning, pros and cons, or factual correction remain ordinary work unless the user asks for an adversarial stance.

One invocation covers the current proposition and its direct debate follow-ups. Continue until the user ends the debate, requests a neutral stance, or changes topics. Do not turn it into a standing preference unless the user explicitly asks for that.

## Role Contract

1. Treat the opposing stance as a reasoning tool, not as a belief to defend at all costs.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jpcaparas/skills/devils-advocate@sha256:ca121d73010ca7d2

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_j5tk7g3ibiigykwi.svg)](https://markdownregistry.com/a/art_j5tk7g3ibiigykwi)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 12, 2026 and Sep 25, 2026, about one every 13 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-09-25 692d684 9,716 BA view · diff
v1.0.02026-09-12 938fe03 8,528 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (9716 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jpcaparas/skills · 56 stars · license none declared · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_j5tk7g3ibiigykwi
GET https://markdownregistry.com/api/v1/resolve?ref=jpcaparas/skills/devils-advocate
GET https://markdownregistry.com/api/v1/blob/ca121d73010ca7d261d510b5240770625fbb50edbea69484e149f8333b18f9ef

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jpcaparas/skills

AGENTS.md AGENTS.md file
jpcaparas/skills · AGENTS.md
git:20261029.2f2b9a8 · audit A · 56 stars
AGENTS.md@skills/agents/bootstrap-agents-md AGENTS.md file
jpcaparas/skills · skills/agents/bootstrap-agents-md/AGENTS.md
git:20260912.938fe03 · audit A · 56 stars
bootstrap-agents-md SKILL.md skill
jpcaparas/skills · skills/agents/bootstrap-agents-md/SKILL.md · Bootstrap or refresh root AGENTS.md and CLAUDE.md.
git:20260925.692d684 · audit A · 56 stars
AGENTS.md@skills/agents/bootstrap-agents-md/evals/files/ledgerbird AGENTS.md file
jpcaparas/skills · skills/agents/bootstrap-agents-md/evals/files/ledgerbird/AGENTS.md
git:20260912.938fe03 · audit A · 56 stars
CLAUDE.md@skills/agents/bootstrap-agents-md/evals/files/ledgerbird CLAUDE.md file
jpcaparas/skills · skills/agents/bootstrap-agents-md/evals/files/ledgerbird/CLAUDE.md
git:20260912.938fe03 · audit B · 56 stars
AGENTS.md@skills/agents/scaffold-github-cloud-agent-environment AGENTS.md file
jpcaparas/skills · skills/agents/scaffold-github-cloud-agent-environment/AGENTS.md
git:20260912.938fe03 · audit A · 56 stars
scaffold-github-cloud-agent-environment SKILL.md skill
jpcaparas/skills · skills/agents/scaffold-github-cloud-agent-environment/SKILL.md · Audit and scaffold `.github/workflows/copilot-setup-steps.yml` for GitHub Copilot cloud agent environments. Use for…
v1.0.0 · audit A · 56 stars
AGENTS.md@skills/agents/scaffold-hooks AGENTS.md file
jpcaparas/skills · skills/agents/scaffold-hooks/AGENTS.md
git:20260912.938fe03 · audit A · 56 stars
scaffold-hooks SKILL.md skill
jpcaparas/skills · skills/agents/scaffold-hooks/SKILL.md · Run /scaffold-hooks to audit, create, or refresh shared repository hooks for Claude Code, Codex, GitHub Copilot, Devin…
git:20260927.4267727 · audit A · 56 stars
AGENTS.md@skills/agents/secure-ai-agent-coding AGENTS.md file
jpcaparas/skills · skills/agents/secure-ai-agent-coding/AGENTS.md
git:20260912.938fe03 · audit A · 56 stars
secure-ai-agent-coding SKILL.md skill
jpcaparas/skills · skills/agents/secure-ai-agent-coding/SKILL.md · Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with…
v1.0.0 · audit A · 56 stars
AGENTS.md@skills/agents/skill-creator-advanced AGENTS.md file
jpcaparas/skills · skills/agents/skill-creator-advanced/AGENTS.md
git:20260912.938fe03 · audit A · 56 stars

Every file in jpcaparas/skills

Other files named devils-advocate

devils-advocate SKILL.md skill
pedrohcgs/claude-code-my-workflow · .agents/skills/devils-advocate/SKILL.md · Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load…
git:20261106.a8c8716 · audit A · 1,686 stars
devils-advocate SKILL.md skill
pedrohcgs/claude-code-my-workflow · .claude/skills/devils-advocate/SKILL.md · Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load…
git:20260821.8a2f894 · audit A · 1,686 stars
devils-advocate SKILL.md skill
daymade/claude-code-skills · daymade-financial/devils-advocate/SKILL.md · 结构化压力测试一个论点(devil's advocate / 魔鬼代言人):把论点拆成显性断言与隐性假设(A1/A2 编号), 逐条在用户给定的证据材料里检索带出处的反方论证,标 High/Medium/Low…
git:20261009.59bfcd3 · audit A · 1,519 stars
devils-advocate SKILL.md skill
onewave-ai/claude-skills · devils-advocate/SKILL.md · Argues the strongest honest case against a decision, plan, belief, hire, pricing move, strategy, or piece of work the…
git:20260923.ebdb76d · audit A · 421 stars
devils-advocate SKILL.md skill
mathews-tom/armory · skills/devils-advocate/SKILL.md · Challenges AI-generated plans, code, and designs via pre-mortem, inversion, and Socratic questioning to surface blind…
v1.0.0 · audit A · 341 stars
devils-advocate SKILL.md skill
cold-iq/coldiq-s-gtm-skills · skills/devils-advocate/SKILL.md · Adversarially reviews whatever you bring it — prompts, strategies, plans, arguments, decisions, or workflows — and…
git:20260723.a5fda02 · audit A · 316 stars
devils-advocate SKILL.md skill
haabe/mycelium · plugins/mycelium/skills/devils-advocate/SKILL.md · Systematically challenge current assumptions before major decisions. Counters confirmation bias, groupthink, and…
git:20261008.fc240ea · audit A · 51 stars
devils-advocate SKILL.md skill
eugenelim/agent-ready-repo · packs/desk-research/.apm/skills/devils-advocate/SKILL.md · Adversarially review a research artifact (`<topic-slug>-survey.md`) or a user-supplied claim. Searches for…
git:20260918.8598e2e · audit A · 28 stars

Browse by kind, by grade A, or by owner.