investigating-anomalous-results
Use when a result is surprising, impossible, contradicts a sanity check, a pipeline fails, a model won't converge, or a replication fails - before adjusting anything
npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Investigating Anomalous Results ## Overview Random tweaks waste time and manufacture false findings. Quietly dropping the inconvenient data point, nudging the cutoff, or re-running until it "works" doesn't fix the problem — it fabricates a result. **Core principle:** ALWAYS find the root cause before adjusting anything. An adjustment made before you understand the cause is, at best, noise and, at worst, fraud. **Violating the letter of this process is violating the spirit of it.** The first question for any anomaly: **is this a code bug, a data issue, or a real finding?** You cannot answer by guessing, and you must not "fix" it until you know — because a real finding is not something to fix. ## The Iron Law ``` NO ADJUSTMENTS WITHOUT ROOT-CAUSE INVESTIGATION FIRST ``` No dropping data, changing a test, transforming a variable, re-running with new parameters, or "cleaning" until Phase 1 is complete. If you haven't found the cause, you cannot justify the adjustment. ## When to Use - A result is surprising, too good, or contradicts what's known - An impossible value (negative count, probability > 1, age of 500) - A pipeline errors or a model won't converge - A result contradicts a s
- Overview
- The Iron Law
- When to Use
- The Four Phases
- Phase 1: Characterize the Anomaly
- Phase 2: Pattern Analysis
- Phase 3: Hypothesis and Test
- Phase 4: Resolution
- Red Flags - STOP and Investigate
- Your Human Partner's Signals You're Doing It Wrong
- Common Rationalizations
- Quick Reference
- Related Skills
What does the investigating-anomalous-results skill do?
Use when a result is surprising, impossible, contradicts a sanity check, a pipeline fails, a model won't converge, or a replication fails - before adjusting anything
How do I install it?
Run `npx skills add K-Dense-AI/science-superpowers --skill investigating-anomalous-results --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From K-Dense-AI/science-superpowers, a repository with 280 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.