Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Measures uncertainty, surprise, and information content using Shannon entropy. Use when asked 'how much information does this actually contain', 'how uncertain is this source', 'is this result surprising', 'what should I update on', 'where is the real information in this dataset', or when you need to distinguish high-information from low-information inputs.
Separates meaningful signal from background noise. Use when asked to 'find the signal', 'cut through the noise', 'what actually matters here', 'what's driving the variation', 'is this data telling us something real', or when a source is overwhelming and it's unclear what's relevant.
Entry point for the investigation toolkit. Routes to the right investigation skill based on what you're trying to establish. Use when you say 'investigate', 'verify this', 'check this claim', 'where does this come from', 'is this true', 'trace the source', 'stress-test this belief', 'what's the evidence', 'could something else explain this', or want to know whether something you've heard is actually true.
Breaks a complex claim into its smallest independently verifiable parts, classifies each sub-claim, and identifies which parts carry the most logical load. Use when a claim feels too big to verify as a unit — 'what exactly is this claiming', 'break this down', 'what are the hidden assumptions in this statement', 'this seems like multiple claims at once', 'what would I need to verify to believe this'.
Generates the best alternative explanations for the same observations. Use when you have a claim or explanation and want to know whether something else could explain the evidence just as well — 'could there be another explanation', 'what else could cause this', 'am I sure this isn't something else', 'steel-man the alternative', 'what would a skeptic say', 'rival hypotheses'.
Evaluates the quality, strength, and completeness of evidence for a claim. Covers evidence type hierarchy, sample quality, methodological soundness, conflicts of interest, and what's notably absent. Use when you want to know how good the evidence is — 'is this evidence strong', 'evaluate the research', 'how solid is this', 'is this just one study', 'what kind of evidence supports this', 'what's missing from the evidence'.
Traces a claim back to its origin: who first made it, what evidence it rested on, and how it has been distorted in transmission. Use when you've heard something and want to know where it actually came from — 'where does this claim come from', 'who first said this', 'I've heard that X is true', 'trace the source', 'is this just a rumor', 'how did this become conventional wisdom'.
Verifies a claim across genuinely independent sources, distinguishing amplification from true corroboration. Use when you want to know if multiple sources actually confirm something — 'can I verify this from multiple angles', 'do independent sources agree', 'is this confirmed by more than one source', 'are these sources actually independent', 'how well-corroborated is this claim'.
Tracks how meanings shift over time or across groups — concept creep, definition drift, and what it costs when words change. Use when you say 'this word doesn't mean what it used to', 'people are using this term differently now', 'this definition has been captured', 'concept creep', 'the word has been weaponised', 'we need to define our terms', or when a key term is contested or means different things to different audiences.
Entry point for the network analysis toolkit. Routes to the right network skill based on your situation. Use when you say 'network', 'who's connected to whom', 'how does this spread', 'who are the key players', 'why did this go viral', 'network effects', 'tipping point', 'weak ties', 'bridges between groups', or want network thinking applied without knowing which specific tool fits.