One-click install
npx skills add https://github.com/Cogni-AI-OU/cogni-ai-agent-skills --skill fact-writer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: fact-writer
Source: https://github.com/Cogni-AI-OU/cogni-ai-agent-skills/tree/main/fact-writer
Command: npx skills add https://github.com/Cogni-AI-OU/cogni-ai-agent-skills --skill fact-writer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents contradictory, unverifiable, or poorly organized project fact files by enforcing strict state rules, lexical ordering, and structured density.

Core Features & Use Cases

  • Verifiable Facts Only: Records objective, repo-grounded truths while rejecting subjective prose and unsupported claims.
  • Contradiction Transparency: Detects and eliminates silent overwrites by replacing conflicting facts rather than appending them.
  • Lexical Sorting & State Compression: Enforces strict alphabetical/natural ordering to preserve deterministic, high-density state representation.
  • Reversibility Focus: Keeps history in Git diffs rather than embedding obsolete states inside the fact store.

Quick Start

Load the fact-writer skill and update FACTS.md or FACTS.mmd only by replacing or inserting verifiable nodes in strict alphabetical order after fully reading the current file contents.

Frequently Asked Questions about fact-writer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I maintain contradiction-free project facts in documentation files?

Maintaining contradiction-free project facts requires enforcing strict ingestion and update rules that detect conflicting facts and replace them rather than appending duplicates. This ensures your canonical fact files remain verifiable and free of silent overwrites.

What is lexical sorting and state compression for project fact repositories?

Lexical sorting and state compression enforce strict alphabetical or natural ordering within fact files to preserve a deterministic, high-density state representation. This structured formatting approach keeps project facts organized and easily verifiable across updates.

How do I handle contradictions when updating architecture decision records?

Handling contradictions in architecture decision records requires explicit conflict handling via replacement instead of silent overwrites. You must perform full prior state verification before applying updates, ensuring conflicting facts are transparently replaced.

What's the best way to format canonical fact files for documentation governance?

Formatting canonical fact files for documentation governance requires structured dense formatting with deterministic alphabetical insertion. This approach preserves state compression and ensures facts remain objective, repo-grounded truths rather than subjective prose.

Why does my project facts file keep accumulating duplicate or conflicting entries?

Project facts files accumulate duplicate or conflicting entries when updates are appended without full prior state verification. Strict ingestion rules that enforce contradiction checking and explicit replacement of conflicting facts prevent this documentation drift.

Can I use state compression techniques for managing FACTS.md files in large repositories?

State compression techniques suit managing FACTS.md files in large repositories by enforcing strict alphabetical ordering and structured density. This approach keeps history in Git diffs rather than embedding obsolete states inside the fact store itself.