Skip to main content
PROMPT SPACE
T
Freedeveloper-toolsUniversal

truth-first

Eliminate hallucinations with an evidence-first verification framework for system state, configs, and file contents.

skill install https://www.promptspace.in/skills/truth-first

What it does

The Truth-First Verification skill enforces a rigorous, evidence-based workflow for AI agents. It prevents "hallucinated certainty" by requiring real-time verification of system states, configurations, and file contents before the agent is allowed to provide an answer. Instead of assuming a service is running or a config is correct, the agent must prove it using available diagnostic tools.

Why use this skill

Standard LLM prompts often lead to agents making assumptions based on outdated context or training data. This skill eliminates that risk by implementing a strict classification framework (Verified, Inferred, Unknown). It is essential for developers working in environments where accuracy is non-negotiable, such as infrastructure management, debugging complex deployments, or auditing configurations. It ensures every response is backed by specific command outputs or file citations.

Supported tools

  • Verification via ripgrep (rg) for targeted file searches.
  • System status checks (ls, stat, logs) for environment validation.
  • Connectivity and mount verification.
  • Configuration auditing through direct file reads and environment inspections.

The Output

The agent delivers a structured report listing every claim analyzed, its verification status, and the direct evidence (paths, log snippets, or command results) supporting the conclusion. If a state remains unknown, the agent provides the exact commands needed to find the answer.

Use cases

  • Validate active processes and service states before troubleshooting failures
  • Verify exact configuration parameters via live file inspections
  • Audit system discrepancies against real-time diagnostic snapshots
  • Prevent misinformation by grounding responses in verified file contents

Example

Prompt

"Verify my database connection settings and check if the production logs show any recent timeouts."

Output

### Verification Report
- DB Connection: Verified (Source: .env/logs)
- Nginx Config: Inferred (File exists, but syntax check skipped)
- Redis Status: Unknown (Command timeout)
[Evidence: 2023-10-27 14:02:11 DB_UP]
Next check: `systemctl status redis`

Known limitations

- Cannot verify states requiring root permissions if the shell is unprivileged. - Limited by the quality and freshness of available system logs. - High latency on deep file system scans (rg) in massive directories.

Frequently asked questions

This skill forces the agent to categorize every claim as Verified, Inferred, or Unknown by performing real-time checks on your system state and file contents before responding, ensuring the agent never "guesses" about your environment.
truth-first — AI Agent Skill | PromptSpace