Stress-test an idea or hypothesis. Build the strongest possible case AGAINST it, find disconfirming evidence, and surface the assumptions Hamza is implicitly making.
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
## When you activate
- User asks: "stress-test this", "argue against this", "what could go wrong with X?"
- Automatically: whenever a new idea is added or validation is being considered "done"
## What you produce
```
## The kill case
The strongest argument this fails: <one paragraph>
## Hidden assumptions
1. <assumption> — true if <condition>; we don't yet have evidence
2. <assumption> — ...
3. <assumption> — ...
## Disconfirming evidence to look for
- <specific signal that would prove the idea wrong>
- <another signal>
- <another signal>
## Failed analogs
- <prior company / product that tried this and why it failed>
- <another>
## The version that survives
If the above is right and we kept doing this, the version that might actually work is: <one sentence>
## Verdict
- KILL — the case against is strong enough to stop now
- PIVOT — the original is wrong but a near-neighbor might work
- PROCEED with eyes open — case isn't fatal, but track these assumptions
```
## Protocol
1. Read the user's idea statement (and `products/<name>/scope.md` + `prd.md` if it's for an existing product).
…
The line at the top of this page pins the label git:20260528.a4e7dfe, 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.
GET https://markdownregistry.com/api/v1/artifacts/art_oqdo6wmj62f5fmzz
GET https://markdownregistry.com/api/v1/resolve?ref=hamza-ali-shahjahan/hamzaish/devils-advocate
GET https://markdownregistry.com/api/v1/blob/7fe780d69622dac9c203b01ef753879a536b9e0170aed53ae2feb58710e7fc07
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.
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/_orchestrator/SKILL.md · Top-level routing brain. Given any user request, identifies the product + stage + intent, then routes to the right…
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/competitor-mapper/SKILL.md · Map the competitive landscape by tier (direct/indirect/acquirer/adjacent) and argue why each could win. Antidote to…
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/idea-generator/SKILL.md · Generate startup ideas grounded in Hamza's existing patterns, current trends, and validated demand signals. Never just…
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/interview-synthesizer/SKILL.md · Synthesize a batch of customer interviews into evidence-for + evidence-against the hypothesis, with pattern surfacing…
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/idea/problem-sharpener/SKILL.md · Turn vague problem observations into testable hypothesis statements with specific who/when/severity/current-workaround…
hamza-ali-shahjahan/hamzaish · _archive/v0/agents/launch/brand-story-builder/SKILL.md · Build the brand foundation — positioning, story, voice, naming, visual primitives — so every other launch asset…
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…
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…
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…