spot-ai-mistakes
Learn to recognize where and how AI tends to go wrong — the specific failure patterns — so you catch its mistakes on sight instead of getting burned by confident errors. Use when asked how do I know when AI is wrong, what are AI's common mistakes, how do I catch AI errors, or where does AI mess up. Produces the failure patterns most relevant to how you use AI (hallucinated facts, fake citations, outdated info, sycophancy, math slips, missed nuance), the tells that give each away, a quick check for the ones that would hurt you, and a calibrated trust level — so you develop the instinct to catch
Profile →npx skills add mohitagw15856/pm-claude-skills --skill spot-ai-mistakes --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.
# Spot AI Mistakes AI fails in patterned, learnable ways — it invents citations, states outdated facts with total confidence, agrees with whatever you imply, and fumbles arithmetic while sounding certain. Once you know the patterns and their tells, you catch most errors on sight. This maps the failure modes most relevant to how *you* use AI, the signs that give each away, and a fast check for the ones that would actually hurt — building the instinct so confident-wrong stops catching you off guard. ## What This Skill Produces - **The failure patterns that matter for you** — the specific ways AI goes wrong in your use (hallucinated facts, fabricated citations/quotes, outdated info, sycophancy, arithmetic slips, false precision, missed nuance, confident guessing) - **The tells for each** — the signals that give a mistake away (suspiciously specific sources, confidence on recent/niche topics, agreeing too readily, round-number math) - **A fast check for the dangerous ones** — a quick way to catch the errors that would actually cost you, without over-checking everything - **A calibrated trust level** — where AI is reliable for your uses and where it isn't, so trust is earned per-domain
- What This Skill Produces
- Required Inputs
- Framework: Know The Patterns, Read The Tells
- Output Format
- AI mistake-spotting: for [how you use it]
- Quality Checks
- Anti-Patterns
- Example Trigger Phrases
What does the spot-ai-mistakes skill do?
Learn to recognize where and how AI tends to go wrong — the specific failure patterns — so you catch its mistakes on sight instead of getting burned by confident errors. Use when asked how do I know when AI is wrong, what are AI's common mistakes, how do I catch AI errors, or where does AI mess up. Produces the failure patterns most relevant to how you use AI (hallucinated facts, fake citations, outdated info, sycophancy, math slips, missed nuance), the tells that give each away, a quick check for the ones that would hurt you, and a calibrated trust level — so you develop the instinct to catch
How do I install it?
Run `npx skills add mohitagw15856/pm-claude-skills --skill spot-ai-mistakes --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 mohitagw15856/pm-claude-skills, a repository with 1,277 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.