devil

Solid

Force N contrarian critique points against a target position. Each point carries a severity tag (BLOCKER / HIGH / MEDIUM / LOW) and a committed paragraph attacking from a distinct angle. Target is either inline (`/devil 5: <claim>`) or walked back to the latest substantive decision/claim in conversation. Manual sycophancy-breaker. Cheap alternative to /council (external) and /scrutinize (multi-phase). Single-shot per invocation. Default N=5, valid range 1-10. Honesty floor: stops early rather than fabricate weak points to hit N.

AI & Automation 11 stars 1 forks Updated 2 days ago Apache-2.0

Install

View on GitHub

Quality Score: 82/100

Stars 20%
36
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# /devil - Force N contrarian critique points Manual sycophancy-breaker. When the user invokes `/devil N` they are explicitly summoning a contrarian critic. It produces exactly N severity-tagged adversarial points against a target position, from distinct angles, in committed prose. Cheap alternative to /council (external Gemini+Grok) and /scrutinize (multi-phase VIIA). Single-shot - after Phase 2 the skill exits and normal posture resumes. Design spec: `docs/superpowers/specs/2026-05-13-devil-skill-design.md` (data overlay: `.heading-os-data/docs/superpowers/specs/2026-05-13-devil-skill-design.md`). ## Phase 1 - Pre-flight + target identification Three sub-steps, all silent on success. **Optional angle priming.** Before you identify the target, you may consult the shared method catalog to widen the attack surface beyond the default angle pool. Draw from the `risk`, `competitive`, and `framing` families: `python scripts/elicit.py list --category risk` returns Pre-mortem Analysis, Failure Mode Analysis, and Assumption Audit. Use a method only to sharpen a real cut; never let it manufacture a point that violates the honesty floor. Skip this entirely when the angles are already obvious. Catalog: `reference/elicitation-methods.md`. ### 1.1 Parse N + detect inline form Read `$ARGUMENTS`: - Empty -> `N = 5`, target = walk-back (1.3) - Token 1 is `"1"` through `"10"`: - Only one token -> `N = int(token1)`, target = walk-back - Followed by `:` -> `N = int(token1)`, target =...

Details

Author
mishahanin
Repository
mishahanin/heading-os
Created
2 months ago
Last Updated
2 days ago
Language
Python
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

devils-advocate

Pressure-tests a plan, decision, opinion, or recommendation by arguing the strongest real case against it. Use whenever the user explicitly asks to "play devil's advocate," "poke holes in this," "stress-test this," "argue against this," "steelman the other side," "tell me why I'm wrong," or invokes /devils-advocate — and also when a user states a specific decision or plan they're about to commit to and asks for a gut check. Do NOT use for casual conversation, factual questions, or a single opinion with no decision attached. Do NOT auto-trigger on emotionally loaded topics (grief, relationships, mental health, decisions the user has already made peace with) unless explicitly asked. Never overrides Claude's standard content and safety boundaries.

0 Updated 1 months ago
gomsb143
AI & Automation Listed

devils-advocate

Get an outside-Anthropic second opinion on any piece of work by sending it to Google Gemini with an adversarial critique prompt. Use when the user wants to pressure-test a decision, plan, assumption, blog draft, landing page, positioning statement, campaign, or chunk of code with a non-Claude model. Trigger when the user says 'devil's advocate,' 'play devil's advocate,' 'poke holes,' 'stress test this,' 'second opinion,' 'outside perspective,' 'non-Anthropic read,' 'sanity check from another model,' 'challenge this,' 'critique this from outside,' or '/devils-advocate.' This is explicitly a cross-model sanity check — do NOT substitute your own critique; the whole point is to surface blind spots Claude might share.

1 Updated 1 weeks ago
t0ddharris
AI & Automation Listed

devil-advocate

Use when about to commit to a decision, plan, conclusion, or recommendation and it needs to be attacked before anyone acts on it — especially when everyone already agrees, money or time is already sunk, a deadline is pushing toward yes, or the user says "poke holes", "stress test", "red team", "what am I missing".

0 Updated yesterday
hadicancatak-coder