Automated summary
Performs constructive devil's advocate analysis on decisions, technology choices, and architectural approaches, identifying risks, alternatives, and gaps.
Strengths
- Rigorous multi-level structure: decision critique, scope critique, and 'first day on the job' test.
- Actively forces gap-seeking with a minimum gaps rule.
- Respectful, evidence-based tone that avoids artificial risk inflation.
- Includes reversibility assessment to guide depth of analysis.
Limitations
- Requires an existing decision or document to analyze.
- May be overly critical if misapplied; nuance is key.
- Does not replace deep domain expertise or formal risk management.
Use this skill when evaluating technology choices, writing ADRs, or stress-testing a decision before committing it to documentation.
Avoid using it for trivial decisions or when speed is more important than thoroughness.
Security analysis
SafeThis skill is purely analytical, providing a structured critique framework for decisions; it does not invoke any tools or execute code, posing no security risk.
No concerns found
How this analysis is madeExamples
We're considering PostgreSQL for our event-sourcing system. Perform a devil's advocate analysis on this choice, considering scalability, complexity, and operational cost.Here is my draft ADR for adopting microservices. Act as devil's advocate and identify gaps, risks, and hidden assumptions.We're prioritizing user authentication overhaul over performance improvements. Challenge this decision as devil's advocate.name: devil-advocate description: > Performs constructive devil's advocate analysis on decisions, technology choices, and architectural approaches. Use when evaluating tradeoffs, challenging assumptions, or when a decision needs stress-testing before committing to it in documentation.
Devil's Advocate Analysis (Enhanced)
When performing devil's advocate analysis, follow this structured approach:
Trigger Conditions
Activate this skill when:
- A technology choice is being made (database, framework, hosting, etc.)
- An architectural decision is being documented in an ADR
- A build-vs-buy decision arises
- The user is confident in an approach that has non-obvious risks
- Feature prioritization involves significant tradeoffs
- After every document generation (automatic — scope critique)
Analysis Structure
Level 1: Decision Critique
1. Steel-man the current position
Before attacking, present the BEST case for the current choice. This shows fairness and ensures the critique is against a strong version of the argument.
2. Identify the three biggest risks
For each risk:
- Probability: How likely is this to happen? (cite evidence)
- Impact: What happens if it does?
- Detectability: Will we know before it's too late?
- Mitigation: Can we reduce the risk while keeping the choice?
3. Name the best alternative
Not a strawman — the genuine best alternative approach. Explain when it would be the right choice.
4. Identify reversibility
- Easily reversible: Low-cost to change later → proceed with less analysis
- Costly to reverse: Significant migration → more analysis warranted
- Irreversible: Permanent commitment → maximum scrutiny required
5. Deliver verdict
Always end with a clear, actionable recommendation. Never leave the user in analysis paralysis.
Level 2: Scope Critique (Run after every document)
Ask these SPECIFIC questions:
- "What did we FORGET?" — actively search for missing requirements
- "What breaks when this fails?" — failure mode analysis
- "What does the user need that they didn't ask for?" — implicit requirements
- "What would a regulatory auditor / security researcher / angry customer flag?"
Level 3: "First Day on the Job" Test
Imagine a developer reading this doc pack on Day 1:
- Can they set up the project without asking questions?
- Do they know which doc to read for which task?
- Is there a clear path from "I just cloned the repo" to "I deployed my first change"?
- Are gotchas and non-obvious constraints highlighted?
Minimum Gaps Rule
The devil's advocate MUST identify at least 2 potential gaps or concerns per document. If you genuinely can't find any, state: "No gaps identified — this document is comprehensive." This forces active gap-seeking rather than rubber-stamping.
Tone
- Respectful but direct
- Evidence-based, not opinion-based
- Acknowledge when the current choice IS the best option
- Never artificially inflate risks to seem thorough
- Focus on SCOPE gaps (what's missing?) not just DECISION quality (is this the right choice?)
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/devil-s-advocate-analysis-mm5t8a9d/download' --output '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md.part' && mv '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md.part' '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md' && test -s '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/devil-advocate' && cp -R '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d' '.claude/skills/devil-advocate'Cursor
test -f '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md' && test -s '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/devil-advocate' && cp -R '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d' '.cursor/skills/devil-advocate'Codex
test -f '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md' && test -s '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/devil-advocate' && cp -R '.skill-downloads/devil-s-advocate-analysis-mm5t8a9d' '.agents/skills/devil-advocate'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/devil-s-advocate-analysis-mm5t8a9d'openskills read 'devil-s-advocate-analysis-mm5t8a9d'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/devil-s-advocate-analysis-mm5t8a9d/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.