Agent skill

ground

Anchor claims to evidence from authoritative sources. Use when validating assertions, establishing provenance, verifying facts, or ensuring claims are supported by evidence.

majiayu000github.com/majiayu000GitHub ↗
claude-coderead-onlyMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ground --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Allowed tools: ReadGrep
Path: skills/analysis/ground/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

## 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

What's inside
Steps it walks through
  1. Intent
  2. Inputs
  3. Procedure
  4. Output Contract
  5. Field Definitions
  6. Examples
  7. Example 1: Ground a Technical Claim
  8. Example 2: Partial Grounding
  9. Example 3: Ungrounded Claim
  10. Verification
  11. Safety Constraints
  12. Composition Patterns
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the ground skill do?

Anchor claims to evidence from authoritative sources. Use when validating assertions, establishing provenance, verifying facts, or ensuring claims are supported by evidence.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ground --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.

Keep going