Q Reality Check — Development skill for Claude Code
Challenger mode.
How to install Q Reality Check
Installs to ~/.claude/skills/assafkip-huntkit-q-reality-check/SKILL.md
mkdir -p ~/.claude/skills/assafkip-huntkit-q-reality-check && curl -fsSL https://raw.githubusercontent.com/assafkip/huntkit/HEAD/commands/q-reality-check.md -o ~/.claude/skills/assafkip-huntkit-q-reality-check/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Q Reality Check does
Challenger mode. Argue AGAINST current hypotheses and findings to find weak spots.
Different from /q-challenge (which audits evidence quality). This command adopts the opposing perspective and stress-tests conclusions.
Steps
- Read the active case's scope, findings, and investigation state
- For each major hypothesis or finding, temporarily argue the OPPOSITE:
- "What if this person is NOT the harasser?"
- "What if the accounts are NOT connected?"
- "What if the evidence support
Alternatives in Development
- Obsidian Challenge — Red-team your current idea against your own vault history — finds contradictions, past failures, and flawed as 277 ★
- 02a Empirical Reality Check — Stage 2a: Empirical Reality Check / Institutional Context Check 164 ★
- Bib Coverage — Compare a project .bib against a Paperpile project/topic folder to find 130 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Weak Spots
../../skills/weak-spot-hunter.md
Learning With Claude
Turns Claude Code into a learning loop: quizzes you on your own diffs, tracks weak spots per developer.
Check Project
Validate that project docs reflect current reality. Asks targeted questions, detects drift, offers to update.
Dependency Watch
Check new vulnerability advisories against portfolio dependencies and route affected repositories into finding
Auto Optimize
Self-improving agent optimization — generates challenger variants of any agent/command, benchmarks against bas
Ads Check Obligatory
Cross-reference your must-have products whitelist against Merchant Center to find missing/blocked products
Related Agents
Challenger Cto
Challenger persona "cto" — CTO-level peer reviewer. Challenges the substance of the principal's thinking — ass
Claims Verifier
Fresh-context, refute-framed cross-check of an audit/review's findings against current source. Use to spot-che
Simulation Analyst
Lightweight single-pass analysis of a completed simulation run against Mechanics Bible ranges — spots anomalie