hint-detection
Detect hints about unreleased AI research or capabilities from lab researcher communications. Use when analyzing tweets, posts, or interviews from people at major AI labs to identify signals about upcoming work.
npx skills add majiayu000/claude-skill-registry --skill hint-detection-rickoslyder-hypedelta-2 --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.
# Hint Detection Skill Lab researchers often hint at work before publication. This skill identifies these signals. ## Hint Patterns ### 1. Vague Progress Claims Language that implies results without specifics: - "We've been seeing interesting results with..." - "There's been a lot of progress on..." - "Things are moving faster than people think in..." ### 2. Deflection with Signal Answers that acknowledge something exists: - "I can't say much, but..." - "You'll see soon..." - "No comment ;)" - "That's a great question" (followed by non-answer) ### 3. Future Tense Confidence Certainty about unreleased capabilities: - "You'll see that..." - "This will become clear when..." - "The next generation will..." ### 4. Unusual Enthusiasm Disproportionate excitement about a topic: - Sudden interest in a specific area - Detailed knowledge about approaches not in their published work - Defending an approach more vigorously than expected ### 5. Specific Denials Sometimes denial calls attention: - "We're definitely NOT working on..." - "That's not what we're focused on" (when they clearly are) - Overly specific denials ### 6. Timeline Hints Suggestions about release timing: - "In the coming weeks
- Hint Patterns
- 1. Vague Progress Claims
- 2. Deflection with Signal
- 3. Future Tense Confidence
- 4. Unusual Enthusiasm
- 5. Specific Denials
- 6. Timeline Hints
- 7. Capability Hedging
- 8. Recruitment Signals
- Author Context
- Analysis Framework
- 1. Quote the relevant passage
- 2. Implied capability
- 3. Confidence level (0.0-1.0)
What does the hint-detection skill do?
Detect hints about unreleased AI research or capabilities from lab researcher communications. Use when analyzing tweets, posts, or interviews from people at major AI labs to identify signals about upcoming work.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill hint-detection-rickoslyder-hypedelta-2 --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.