Skip to content
Agentmart
Submit a tool

grounding

Evidence before opinion: when requirements or context are unclear, or advice is needed, verify primary sources before making a judgment.

Skill by DearCaat

IndexedMIT★ 4
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/dearcaat-grounding

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Evidence before opinion: when requirements or context are unclear, or advice is needed, verify primary sources before making a judgment. Do not use it for a normal execution of an already agreed plan.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/grounding

What's inside

Skill name
grounding
Description
Evidence before opinion: when requirements or context are unclear, or advice is needed, verify primary sources before making a judgment. Do not use it for a normal execution of an already agreed plan.
License
MIT
Instructions
16 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Grounding

Establish an evidence base before speaking: evidence before opinion.

## Method

- Do not reason from assumptions. Treat every load-bearing user claim and premise as something to check; label it confirmed, refuted, or untested, and state conflicts explicitly.
- Reuse evidence already read in this conversation and identify its source. Search only for gaps.
- Explore the environment and go directly to primary sources: original papers (DOI / arXiv), official documentation, or the author’s own writing. Do not rely on second-hand summaries.
- Cite each claim, distinguish peer-reviewed, preprint, and blog evidence, then give an evidence-backed recommendation and move to `/brainstorming` or `/grilling`.

## Completion criterion

Every recommendation and every judgment about a user premise points to a specific source; evidence already read in this conversation is a valid source and is named directly.

From DearCaat/research-foundation-skills, MIT.

More from DearCaat/research-foundation-skills

Signals

Stars
4
Forks
0
Open issues
0
Last commit (this folder)
Sep 2, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/DearCaat/research-foundation-skills
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from DearCaat

Cite this page

grounding skill. Agent Mart. https://agentmart.dev/skills/dearcaat-grounding (last updated 2026-10-24)