Epistemic checkpoint
Skill aiskillstore/marketplace/skills/ancplua/epistemic-checkpoint
Force verification before answering questions involving versions, dates, status, or "current" state. Prevents hallucinations at the REASONING level by checking assertions.yaml and WebSearch before forming beliefs. Triggers on software versions, release status, dates, and package versions.From its SKILL.md
npx -y skills add aiskillstore/marketplace --skill epistemic-checkpointAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
SKILL.md
3.3 KB, 762 tokens by cl100k_base, as published. Nobody here has run it
Epistemic Checkpoint
Force verification before answering questions involving versions, dates, status, or "current" state.
Purpose
Prevents the ROOT CAUSE of hallucinations - not just blocking wrong output, but preventing wrong REASONING. Claude's training data is stale; this skill forces verification before forming beliefs.
Triggers
Activate this skill when the question involves ANY of:
- Software versions (.NET, Node, React, Python, etc.)
- Release status (preview, LTS, GA, RC, deprecated)
- "Current" or "latest" anything
- Dates that might be after training cutoff
- Package versions
- API deprecations
MANDATORY Protocol
Step 1: Recognize Uncertainty
Say to yourself: "My training data may be stale for: [topic]"
Step 2: Check Local Ground Truth
Read ${CLAUDE_PLUGIN_ROOT}/blackboard/assertions.yaml
Search for relevant entries
If found - use that value with high confidence.
Step 3: If Not in Assertions - WebSearch
WebSearch("[software] [version] release date site:official-docs")
WebSearch("[software] LTS release 2025")
Prefer official sources:
- microsoft.com/dotnet for .NET
- nodejs.org for Node
- python.org for Python
Step 4: State Verified Facts
Say: "Based on [source], [software] [version] is [status] as of [date]."
Step 5: THEN Proceed
Only now answer the actual question with the verified baseline.
Red Flag Thoughts (REJECT THESE)
| If you think... | Actually do... |
|---|---|
| "I'm pretty sure .NET 10 is..." | WebSearch to verify |
| "This is probably still preview" | Check assertions.yaml |
| "I remember this from training" | Training is stale, verify |
| "This is a simple factual question" | Simple facts are often WRONG |
| "The user said it's preview" | User might be wrong too, verify |
Anti-Pattern Examples
WRONG:
"If targeting .NET 10 preview, use C# 14 extension types..."
CORRECT:
"Let me verify .NET 10 status... [WebSearch] ...
.NET 10 is LTS (released November 2025), not preview.
Standard extension methods work fine."
WRONG:
"React 19 is still in beta, so..."
CORRECT:
"Checking React 19 status... [WebSearch] ...
React 19 was released December 2024 as stable.
Proceeding with React 19 stable patterns."
Common Danger Patterns
| Topic | Danger Pattern | Likely Truth |
|---|---|---|
| .NET | "preview", "not released" | .NET 10 LTS since Nov 2025 |
| React | "beta", "experimental" | React 19 stable since Dec 2024 |
| Node | "current" without version | Always specify exact version |
| Python | "3.x is latest" | Verify - 3.13+ exists |
Output Format
When this skill activates, structure your verification as:
Epistemic Checkpoint
Claim to verify: [what you were about to assume]
Source checked: [assertions.yaml / WebSearch / official docs]
Verified fact: [the actual truth]
Confidence: [high/medium/low]
Proceeding with verified baseline...
What ships with it: 1 file
18.6 KB alongside SKILL.md
- skill-report.json18.6 KB