Don't Lie to Me

by asimons81

Don't Lie to Me is an AI Engineering skill for Claude Code, published by asimons81 in hermes-field-kit.

122 stars11 forkson asimons81/hermes-field-kitAdded 2026/08/11+1% in starsRepository updated 2026/08/10

View source on GitHub Download repo ZIP

agent-skillsai-agentshermes-agentopen-sourcepython

Install in seconds

Install Don't Lie to Me

Copy Don't Lie to Me into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/asimons81/hermes-field-kit/tree/main/skills/dont-lie-to-me ~/.claude/skills/dont-lie-to-me

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/asimons81/hermes-field-kit.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/dont-lie-to-me/SKILL.md in asimons81/hermes-field-kit
Installs to: ~/.claude/skills/dont-lie-to-me
Collection: One of 16 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Don't Lie to Me does

Use when the user explicitly wants evidence-disciplined answers that separate observed facts, sourced claims, user reports, inference, unknowns, and contradictions before making strong factual or completion claims.

Don't Lie to Me is cataloged under AI Engineering on DirSkills. Don't Lie to Me comes from a repository tagged agent-skills, ai-agents, hermes-agent, open-source and python.

Documentation

README

Excerpt

dont-lie-to-me

Overview

dont-lie-to-me is a claim-discipline layer for Hermes.

It exists for one recurring failure class: turning partial, missing, inferred, user-reported, or weak evidence into language that sounds verified.

The skill does not promise perfect truthfulness and does not make the model omniscient. It changes the process used before material claims are stated.

Core rule:

claim -> required evidence -> check -> state, qualify, or remove

Strong wording carries a stronger proof obligation. Missing evidence stays missing.

This skill governs claims about work. It does not reduce permissions already granted by the user, turn every task into a read-only audit, or require citations when citations are not otherwise needed.

When to Use

This is the opening of the README. Read the full README on GitHub.

Commands Don't Lie to Me provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/dont-lie-to-me

Frequently asked about Don't Lie to Me

What else does asimons81 publish alongside Don't Lie to Me?
Don't Lie to Me is one of 16 skills that DirSkills catalogs from asimons81/hermes-field-kit, the repository it ships in. Its siblings there include Hermes Environment Migration, Hermes Field Kit and Hermes Gateway Doctor. Each one is a separate skill with its own page in this directory, installs the same way Don't Lie to Me does, and is maintained by asimons81 in that same repository. The rest of the collection is listed on the asimons81/hermes-field-kit page.
How does Don't Lie to Me compare to other AI Engineering skills?
Don't Lie to Me ranks #2243 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Don't Lie to Me against them. Open each page to compare what they document and how they install.