prediction-tracking
Track and evaluate AI predictions over time to assess accuracy. Use when reviewing past predictions to determine if they came true, failed, or remain uncertain.
Profile →npx skills add majiayu000/claude-skill-registry --skill prediction-tracking --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.
# Prediction Tracking Skill Track predictions made by AI researchers and critics, evaluate their accuracy over time. ## Prediction Recording When recording a new prediction, capture: ### Required Fields - **text**: The prediction as stated - **author**: Who made it - **madeAt**: When it was made - **timeframe**: When they expect it to happen - **topic**: What area of AI - **confidence**: How confident they seemed ### Optional Fields - **sourceUrl**: Where the prediction was made - **targetDate**: Specific date if mentioned - **conditions**: Any caveats or conditions - **metrics**: How to measure success ## Evaluation Status When evaluating predictions, assign one of: ### `verified` Clearly came true as stated. - The predicted capability/event occurred - Within the stated timeframe - Substantially as described ### `falsified` Clearly did not come true. - Timeframe passed without occurrence - Contradictory evidence emerged - Author retracted or modified claim ### `partially-verified` Partially accurate. - Some aspects came true, others didn't - Capability exists but weaker than claimed - Timeframe was off but direction correct ### `too-early` Not enough time has passed. - Still withi
- Prediction Recording
- Required Fields
- Optional Fields
- Evaluation Status
- verified
- falsified
- partially-verified
- too-early
- unfalsifiable
- ambiguous
- Evaluation Process
- 1. Restate the prediction
- 2. Identify timeframe
- 3. Gather evidence
What does the prediction-tracking skill do?
Track and evaluate AI predictions over time to assess accuracy. Use when reviewing past predictions to determine if they came true, failed, or remain uncertain.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill prediction-tracking --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 majiayu000/claude-skill-registry, a repository with 534 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.