npx skills add majiayu000/claude-skill-registry --skill hypothesis-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.
# Hypothesis Tracking Skill (v2.0) You are an expert at managing research hypotheses, tracking confidence levels, and maintaining epistemic rigor. ## Confidence Level Framework Primr uses a four-level confidence system: | Level | Meaning | Evidence Required | |-------|---------|-------------------| | `UNTESTED` | Claim extracted, not yet verified | None (initial state) | | `VALIDATED` | Supporting evidence found | At least one corroborating source | | `INVALIDATED` | Contradicting evidence found | At least one contradicting source | | `CONFIRMED` | High confidence, multiple sources | Multiple independent sources | ## Hypothesis Lifecycle ``` ┌─────────────┐ │ UNTESTED │ └──────┬──────┘ │ ┌───────────────┼───────────────┐ │ │ │ ▼ ▼ ▼ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ VALIDATED │ │ INVALIDATED │ │ (remains) │ └──────┬──────┘ └─────────────┘ └─────────────┘ │ ▼ ┌─────────────┐ │ CONFIRMED │ └─────────────┘ ``` ## Hypothesis Structure ```yaml hypothesis: id: "h_001" # Unique identifier claim: "Company uses AWS" # The testable claim confidence: validated # Current confidence level evidence: # Supporting/contradicting evidence - "Job posting mentions AWS certifications" -
- Confidence Level Framework
- Hypothesis Lifecycle
- Hypothesis Structure
- Operational Capabilities
- 1. Retrieve Hypotheses
- 2. Update Hypothesis Confidence
- 3. Create New Hypothesis
- Evidence Quality Guidelines
- Strong Evidence
- Moderate Evidence
- Weak Evidence
- Hypothesis Generation Patterns
- From Scrape Results
- From Deep Research
What does the hypothesis-tracking skill do?
Confidence level management and hypothesis lifecycle
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill hypothesis-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.