groundlisted
Install: claude install-skill synaptiai/agent-capability-standard
## Intent
Verify that claims are supported by evidence from reliable sources. This is the foundation of the Grounded Agency principle - no assertion should be made without evidence anchors.
**Success criteria:**
- Claim evaluated against available evidence
- Evidence sources identified and referenced
- Grounding strength assessed (strong, moderate, weak, ungrounded)
- Evidence gaps explicitly documented
**Compatible schemas:**
- `schemas/output_schema.yaml`
## Inputs
| Parameter | Required | Type | Description |
|-----------|----------|------|-------------|
| `claim` | Yes | string | The claim or assertion to ground |
| `sources` | No | array | Evidence sources to check (files, URLs, commands) |
| `required_strength` | No | string | Minimum grounding level: weak, moderate, strong |
## Procedure
1) **Parse the claim**: Understand what is being asserted
- Identify the core assertion
- Note any implicit sub-claims
- Determine what evidence would support it
2) **Identify evidence sources**: Determine where to look
- Use provided sources if available
- Identify additional relevant sources
- Prioritize authoritative sources
3) **Search for evidence**: Look for supporting or contradicting data
- Read relevant files and documentation
- Execute commands to gather data
- Note both supporting and contradicting evidence
4) **Evaluate evidence quality**: Assess reliability of found evidence
- Consider source authority
- Check for recency and rele