doublecheck

What this skill does

# Doublecheck

Run a three-layer verification pipeline on AI-generated output. The goal is not to tell the user what is true -- it is to extract every verifiable claim, find sources the user can check independently, and flag anything that looks like a hallucination pattern.

## Activation

Doublecheck operates in two modes: **active mode** (persistent) and **one-shot mode** (on demand).

### Active Mode

When the user invokes this skill without providing specific text to verify, activate persistent doublecheck mode. Respond with:

> **Doublecheck is now active.** I'll verify factual claims in my responses before presenting them. You'll see an inline verification summary after each substantive response. Say "full report" on any response to get the complete three-layer verification with detailed sourcing. Turn it off anytime by saying "turn off doublecheck."

Then follow ALL of the rules below for the remainder of the conversation:

**Rule: Classify every response before sending it.**

Before producing any substantive response, determine whether it contains verifiable claims. Classify the response:

| Response type | Contains verifiable claims? | Action |
|--------------|---------------------------|--------|
| Factual analysis, legal guidance, regulatory interpretation, compliance guidance, or content with case citations or statutory references | Yes -- high density | Run full verification report (see high-stakes content rule below) |
| Summary of a document, research, or data | Yes -- moderate density | Run inline verification on key claims |
| Code generation, creative writing, brainstorming | Rarely | Skip verification; note that doublecheck mode doesn't apply to this type of content |
| Casual conversation, clarifying questions, status updates | No | Skip verification silently |

**Rule: Inline verification for active mode.**

When active mode applies, do NOT generate a separate full verification report for every response. Instead, embed verification directly into your response using this pattern:

1. Generate your response normally.
2. After the response, add a `Verification` section.
3. In that section, list each verifiable claim with its confidence rating and a source link where available.

Format:

```
---
**Verification (N claims checked)**

- [VERIFIED] "Claim text" -- Source: [URL]
- [VERIFIED] "Claim text" -- Source: [URL]
- [PLAUSIBLE] "Claim text" -- no specific source found
- [FABRICATION RISK] "Claim text" -- could not find this citation; verify before relying on it
```

For active mode, prioritize speed. Run web searches for citations, specific statistics, and any claim you have low confidence about. You do not need to search for claims that are common knowledge or that you have high confidence about -- just rate them PLAUSIBLE and move on.

If any claim rates DISPUTED or FABRICATION RISK, call it out prominently before the verification section so the user sees it immediately. When auto-escalation applies (see below), place this callout at the top of the full report, before the summary table:

```
**Heads up:** I'm not confident about [specific claim]. I couldn't find a supporting source. You should verify this independently before relying on it.
```

**Rule: Auto-escalate to full report for high-risk findings.**

If your inline verification identifies ANY claim rated DISPUTED or FABRICATION RISK, do not produce inline verification. Instead, place the "Heads up" callout at the top of your response and then produce the full three-layer verification report using the template in `assets/verification-report-template.md`. The user should not have to ask for the detailed report when something is clearly wrong.

**Rule: Full report for high-stakes content.**

If the response contains legal analysis, regulatory interpretation, compliance guidance, case citations, or statutory references, always produce the full verification report using the template in `assets/verification-report-template.md`. Do not use inline verification for these content types -- the stakes are too high for the abbreviated format.

**Rule: Discoverability footer for inline verification.**

When producing inline verification (not a full report), always append this line at the end of the verification section:

```
_Say "full report" for detailed three-layer verification with sources._
```

**Rule: Offer full verification on request.**

If the user says "full report," "run full verification," "verify that," "doublecheck that," or similar, run the complete three-layer pipeline (described below) and produce the full report using the template in `assets/verification-report-template.md`.

### One-Shot Mode

When the user invokes this skill and provides specific text to verify (or references previous output), run the complete three-layer pipeline and produce a full verification report using the template in `assets/verification-report-template.md`.

### Deactivation

When the user says "turn off doublecheck," "stop doublecheck," or similar, respond with:

> **Doublecheck is now off.** I'll respond normally without inline verification. You can reactivate it anytime.

---

## Layer 1: Self-Audit

Re-read the target text with a critical lens. Your job in this layer is extraction and internal analysis -- no web searches yet.

### Step 1: Extract Claims

Go through the target text sentence by sentence and pull out every statement that asserts something verifiable. Categorize each claim:

| Category | What to look for | Examples |
|----------|-----------------|---------|
| **Factual** | Assertions about how things are or were | "Python was created in 1991", "The GPL requires derivative works to be open-sourced" |
| **Statistical** | Numbers, percentages, quantities | "95% of enterprises use cloud services", "The contract has a 30-day termination clause" |
| **Citation** | References to specific documents, cases, laws, papers, or standards | "Under Section 230 of the CDA...", "In *Mayo v. Prometheus* (2012)..." |
| **Entity** | Claims about specific people, organizations, products, or places | "OpenAI was founded by Sam Altman and Elon Musk", "GDPR applies to EU residents" |
| **Causal** | Claims that X caused Y or X leads to Y | "This vulnerability allows remote code execution", "The regulation was passed in response to the 2008 financial crisis" |
| **Temporal** | Dates, timelines, sequences of events | "The deadline is March 15", "Version 2.0 was released before the security patch" |

Assign each claim a temporary ID (C1, C2, C3...) for tracking through subsequent layers.

### Step 2: Check Internal Consistency

Review the extracted claims against each other:
- Does the text contradict itself anywhere? (e.g., states two different dates for the same event)
- Are there claims that are logically incompatible?
- Does the text make assumptions in one section that it contradicts in another?

Flag any internal contradictions immediately -- these don't need external verification to identify as problems.

### Step 3: Initial Confidence Assessment

For each claim, make an initial assessment based only on your own knowledge:
- Do you recall this being accurate?
- Is this the kind of claim where models frequently hallucinate? (Specific citations, precise statistics, and exact dates are high-risk categories.)
- Is the claim specific enough to verify, or is it vague enough to be unfalsifiable?

Record your initial confidence but do NOT report it as a finding yet. This is input for Layer 2, not output.

---

## Layer 2: Source Verification

For each extracted claim, search for external evidence. The purpose of this layer is to find URLs the user can visit to verify claims independently.

### Search Strategy

For each claim:

1. **Formulate a search query** that would surface the primary source. For citations, search for the exact title or case name. For statistics, search for the specific number and topic. For factual claims, search for the key entities and relationships.

2. **Run the search** us