context-maintenance

Maintain project context documentation including architecture, standards, and progress tracking.

Updated Jun 25, 2026
One-click install
npx skills add https://github.com/oriddd/ai-toolkit --skill context-maintenance-oriddd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: context-maintenance
Source: https://github.com/oriddd/ai-toolkit/tree/main/copilot/public/skills/context-maintenance
Command: npx skills add https://github.com/oriddd/ai-toolkit --skill context-maintenance-oriddd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Project documentation drifts out of date as features ship, architecture evolves, and dependencies change, leaving AI assistants and team members working from stale context. This Skill provides a structured process for keeping the context/ documentation folder current. ## Core Features & Use Cases - Update Triggers: Defines exactly which context files to update when adding features, changing architecture, swapping dependencies, or completing sprints. - Diagram & Changelog Maintenance: Covers Mermaid-based C4 diagrams (system context, component, domain flow) and append-only CHANGELOG management with release procedures. - Use Case: After adding a Redis caching layer, follow the skill's checklist to update project-overview.md, architecture.md, component-diagram.md, library-docs.md, build-plan.md, progress-tracker.md, and CHANGELOG.md in one pass. ## Quick Start Ask the AI to apply the context-maintenance skill and update all context documentation after adding a new feature to the project.

Frequently Asked Questions about context-maintenance

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

FAQPage Schema
How do I keep project documentation up to date for AI assistants?

Maintain a context/ folder with files like architecture.md, code-standards.md, and progress-tracker.md, then update them whenever features, architecture, or dependencies change. Reference these files explicitly when prompting AI assistants so they work from current project knowledge.

What files should I update when adding a new feature?

Update project-overview.md with the feature, architecture.md with new components, code-standards.md if new patterns were introduced, progress-tracker.md for milestones, relevant Mermaid diagrams, and CHANGELOG.md under the Unreleased section.

How do I maintain Mermaid diagrams in Markdown documentation?

GitHub and GitLab render Mermaid natively in Markdown files, so no generation step is needed. For static images, install @mermaid-js/mermaid-cli and run mmdc to convert the Markdown file into a PNG.

How should a CHANGELOG be maintained during releases?

Keep the CHANGELOG append-only with new entries under an Unreleased section at the top. At release time, rename Unreleased to the version number with a date, then add a fresh empty Unreleased section above it.

How can I validate that context documentation is still accurate?

Run markdown-link-check on all context files to catch broken links, validate Mermaid syntax with mermaid-cli, and review Last Updated dates. Good documentation is under three months old with current metrics and valid cross-references.