sync-ai-context

Synchronize AI-critical repository documents against current project state and configuration.

Updated Aug 31, 2026
One-click install
npx skills add https://github.com/ahuaracab/test-genesis --skill sync-ai-context-ahuaracab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sync-ai-context
Source: https://github.com/ahuaracab/test-genesis/tree/main/.agents/skills/sync-ai-context
Command: npx skills add https://github.com/ahuaracab/test-genesis --skill sync-ai-context-ahuaracab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI-facing repository documents (README.md, AGENTS.md, CLAUDE.md, onboarding pages) drift out of sync with the actual project state as scripts, skills, aliases, and paths change, causing AI assistants to load stale or contradictory instructions. ## Core Features & Use Cases - Multi-document drift patching: Audits all AI-critical files using five discovery rules, then patches only verified drifted facts while preserving human prose and protected policy sections. - Cross-document consistency checks: Verifies that skill names, script names, environment URLs, and paths agree across every document before writing anything. - Security redaction protocol: Scans drafted content for credentials, production URLs, and shaped secrets (JWTs, PATs, AWS keys) before any write, with a user-visible redaction log. - Use Case: After renaming a skill or changing package.json scripts, run the sync to update README script tables, the AGENTS.md skills registry, and the onboarding HTML in one pass without rewriting stable rule sections. ## Quick Start Ask the AI to run sync-ai-context on this repository to detect and patch documentation drift across all AI-critical files.

Frequently Asked Questions about sync-ai-context

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

FAQPage Schema
How do I keep AGENTS.md and README.md in sync with my repository?

Run the sync-ai-context workflow, which audits all AI-critical documents, detects drifted facts like renamed scripts or skills, and patches them in place. It preserves human prose and stable rule sections while updating only verified drift.

What files does an AI context sync check for documentation drift?

The audit discovers root all-caps Markdown files, docs referenced by AGENTS.md or SKILL.md files, .context/ outputs, files with three or more inbound references, and standalone HTML docs. Each file gets a role tag that determines its sync behavior.

Does the sync rewrite CLAUDE.md or stable policy sections?

No. CLAUDE.md must remain an exact one-line shim importing AGENTS.md, and protected sections like Critical Rules and Behavioral Layer are preserved verbatim. Structural drift causes the sync to stop and report rather than rewrite.

How does the sync prevent leaking secrets into documentation?

A pre-write redaction protocol scans drafted content for credential patterns, production URLs, and shaped secrets like JWTs, GitHub PATs, and AWS keys. Matches are replaced with placeholders and surfaced in a redaction log before any file is written.

When should I not run the AI context sync?

Do not run it when the repository lacks the KATA test architecture; the sync stops and directs you to run project discovery first. It also cannot bootstrap a missing AGENTS.md, which must come from the boilerplate repository.