Agent skill

Devils Advocate On Demand

by mohitagw15856 in mohitagw15856/pm-claude-skills

Argue hard against whatever you just concluded — so your decision has to survive a real challenge instead of an echo chamber.

MITAuto-check passed

Install Devils Advocate On Demand

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill devils-advocate-on-demand -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills devils-advocate-on-demand --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/devils-advocate-on-demand .claude/skills/devils-advocate-on-demand && 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
devils-advocate-on-demand
GitHub stars
1.4k
Token cost
~893 tokens
SKILL.md length
431 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Argue hard against whatever you just concluded — so your decision has to survive a real challenge instead of an echo chamber.

  • Works in 5 steps: Take the opposing position seriously.… → Ask what you're dodging. Surface the… → Bring the counter-evidence. Present the… → …
  • Asked to play devils advocate
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: Genuinely Argue The… and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Devils Advocate On Demand is an agent skill from mohitagw15856/pm-claude-skills. Argue hard against whatever you just concluded — so your decision has to survive a real challenge instead of an echo chamber. Use when asked to play devil's advocate, argue against this, challenge my conclusion, or talk me out of it. Produces the strongest case against your position, the uncomfortable questions you're avoiding, the evidence that cuts the other way, and an honest read on whether your conclusion survives the challenge — deliberately countering the 'that's a great idea!' agreement bias.

Its SKILL.md is about 890 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: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked to play devils advocate
  • Argue against this
  • Challenge my conclusion
  • Talk me out of it

Example prompts

  • “s a great idea!”
  • “/devils-advocate-on-demand”

Workflow steps

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

  1. Take the opposing position seriously. Argue against the conclusion as if you believed the opposite — no token objections.
  2. Ask what you're dodging. Surface the questions the person is avoiding because they sense the answer undermines them.
  3. Bring the counter-evidence. Present the facts, base rates, and considerations that point the other way, fairly.
  4. Attack the reasoning, not just the conclusion. Find the weak link in how they got there.
  5. Then judge honestly. Say whether the position survives — sometimes the challenge confirms it (now stronger), sometimes it cracks. Don't…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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

Devils Advocate On Demand loads about 893 tokens when it runs. Until then it costs about 133 tokens; SKILL.md has 431 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~133
When it runs · the whole SKILL.md, loaded when a task matches
~893

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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 431 words, ~893 tokens.

Download SKILL.mdSave it as .claude/skills/devils-advocate-on-demand/SKILL.md (or your agent's skills folder).
name
devils-advocate-on-demand
description
Argue hard against whatever you just concluded — so your decision has to survive a real challenge instead of an echo chamber. Use when asked to play devil's advocate, argue against this, challenge my conclusion, or talk me out of it. Produces the strongest case against your position, the uncomfortable questions you're avoiding, the evidence that cuts the other way, and an honest read on whether your conclusion survives the challenge — deliberately countering the 'that's a great idea!' agreement bias.

Devil's Advocate On Demand

AI and friendly humans have a strong bias toward agreeing with you — which feels nice and teaches you nothing. This does the opposite on command: it argues hard against your conclusion, asks the questions you're dodging, and surfaces the evidence pointing the other way. If your decision survives, you can trust it more. If it doesn't, better to find out now.

What This Skill Produces

  • The strongest counter-case — the best argument against your position, made in earnest
  • The uncomfortable questions — the ones you're avoiding because you suspect the answers
  • The evidence the other way — facts and considerations that cut against your conclusion
  • The survival verdict — whether your position holds up under the challenge, honestly

Required Inputs

Ask for these if not provided:

  • Your conclusion — what you've decided or believe
  • Your reasoning — how you got there
  • Your confidence — how sure you are (high confidence often needs the hardest challenge)
  • What would change your mind — if anything (a tell for how open the question really is)

Framework: Genuinely Argue The Other Side

  1. Take the opposing position seriously. Argue against the conclusion as if you believed the opposite — no token objections.
  2. Ask what you're dodging. Surface the questions the person is avoiding because they sense the answer undermines them.
  3. Bring the counter-evidence. Present the facts, base rates, and considerations that point the other way, fairly.
  4. Attack the reasoning, not just the conclusion. Find the weak link in how they got there.
  5. Then judge honestly. Say whether the position survives — sometimes the challenge confirms it (now stronger), sometimes it cracks. Don't manufacture doubt where the conclusion is sound.
Show full SKILL.md (158 more words)Show less

Output Format

Challenging: [your conclusion]

The case against it: [strongest honest counter-argument]. Questions you're avoiding: [the uncomfortable ones]. Evidence the other way: [what cuts against you]. Weak link in your reasoning: [where it's shakiest]. Verdict: [survives — stronger now / cracks — reconsider / genuinely 50/50 — here's the deciding factor].

Quality Checks

  • Genuinely argues the opposing side, not token objections
  • Surfaces the questions being avoided
  • Brings real counter-evidence, fairly
  • Attacks the reasoning, not only the conclusion
  • Gives an honest verdict, without manufacturing doubt on a sound call

Anti-Patterns

  • Agreeing with a few soft caveats.
  • Token objections that are easy to dismiss.
  • Manufacturing doubt on a genuinely sound conclusion.
  • Attacking the person instead of the position.

Example Trigger Phrases

  • "Play devil's advocate on my plan to quit and go freelance."
  • "Argue against my conclusion here."
  • "Challenge this — I want to know if it holds up."
  • "Try to talk me out of this decision."
  • "I think I'm right — prove me wrong if you can."

© mohitagw15856, 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/devils-advocate-on-demand of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Devils Advocate On Demand 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.

Devils Advocate On Demand compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Devils Advocate On Demand this skillmohitagw15856/pm-claude-skills1.4k—~893Automated safety check: PassMIT
Devil Advocatejeremylongshore/tons-of-skills-marketplace2.8k—~2.1kAutomated safety check: PassMIT
Devils Advocatedaymade/claude-code-skills1.4k—~1.7kAutomated safety check: PassMIT
Devils Advocatepedrohcgs/claude-code-my-workflow1.7k2 repos~641Automated safety check: PassMIT
Devils AdvocateOneWave-AI/claude-skills336—~2kAutomated safety check: PassMIT
Hard Callalirezarezvani/claude-skills28k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Devil Advocate

    jeremylongshore/tons-of-skills-marketplace

    Constructive critic and stress-tester for ideas and proposals.

    2.8k GitHub stars~2.1k tokensUpdated yesterday
    Sales & SupportAuto-check passed
  • Devils Advocate

    daymade/claude-code-skills

    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 风险等级,补基础比率外部视角, 最后给出「可监测的证伪信号」清单;输出结构化 findings + 人读叙事双层结果。找不到反证时如实声明「未找到」, 绝不编造。复刻自…

    1.4k GitHub stars~1.7k tokensUpdated yesterday
    EducationAuto-check passed
  • Devils Advocate

    pedrohcgs/claude-code-my-workflow

    Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation.

    1.7k GitHub starsUsed in 2 repos~641 tokens
    Documents & OfficeAuto-check passed
  • Devils Advocate

    OneWave-AI/claude-skills

    Argues the strongest honest case against a decision, plan, belief, hire, pricing move, strategy, or piece of work the user is leaning toward.

    336 GitHub stars~2k tokensUpdated 9 days ago
    Testing & QAAuto-check passed
  • Hard Call

    alirezarezvani/claude-skills

    /em:hard-call — Framework for decisions with no good options.

    28k GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Idea Devils Advocate

    majiayu000/spellbook

    想法群聊室 — 反方角色。被 idea-team 主编排器调用,或用户单独说"反方意见"、"挑这个想法的刺"、"为什么会失败"、"找漏洞 / 反例"、"devil's advocate"时触发。专门挑漏洞、找隐藏假设、给反例——不安慰、不"也许可以这样"、不全盘否定。Do NOT use when 用户要数据(用 idea-research)、要类比启示(用…

    287 GitHub stars~446 tokensUpdated 2 days ago
    Research & ScienceAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Devils Advocate On Demand

What does Devils Advocate On Demand do?

Argue hard against whatever you just concluded — so your decision has to survive a real challenge instead of an echo chamber. Devils Advocate On Demand is an agent skill from mohitagw15856/pm-claude-skills. Argue hard against whatever you just concluded — so your decision has to survive a real challenge instead of an echo chamber.

When should I use Devils Advocate On Demand?

Devils Advocate On Demand fits situations like: asked to play devils advocate; argue against this; challenge my conclusion; talk me out of it.

How do I install Devils Advocate On Demand in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill devils-advocate-on-demand -a claude-code`. Or copy the skill folder (skills/devils-advocate-on-demand in mohitagw15856/pm-claude-skills) into .claude/skills/devils-advocate-on-demand in your project. Claude Code loads it when a task matches its description.

How do I install Devils Advocate On Demand in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill devils-advocate-on-demand -a codex`. Or copy the skill folder (skills/devils-advocate-on-demand in mohitagw15856/pm-claude-skills) into .agents/skills/devils-advocate-on-demand in your project. Codex loads it when a task matches its description.

Can I use Devils Advocate On Demand 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 mohitagw15856/pm-claude-skills --skill devils-advocate-on-demand -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/devils-advocate-on-demand, .gemini/skills/devils-advocate-on-demand, .github/skills/devils-advocate-on-demand and .opencode/skills/devils-advocate-on-demand in your project.

What does Devils Advocate On Demand need to run?

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

Does Devils Advocate On Demand 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 Devils Advocate On Demand 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 Devils Advocate On Demand use?

Devils Advocate On Demand 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 Devils Advocate On Demand use?

About 893 tokens (SKILL.md is roughly 3.6k 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 Devils Advocate On Demand?

Skills that share tags, products or a category with Devils Advocate On Demand: Devil Advocate (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Devils Advocate (daymade/claude-code-skills, 1.4k stars), Devils Advocate (pedrohcgs/claude-code-my-workflow, 1.7k stars) and Devils Advocate (OneWave-AI/claude-skills, 336 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Devils Advocate On Demand?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.