skills/context-review/SKILL.md
Scans the codebase and synchronizes `.context/` documentation with the actual state of the code. Use this at the start of any architect or design task when the context cache is stale (older than 5 days) or missing.
npx skillsauth add maestria-co/ai-playbook context-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Scan the current codebase and synchronize the .context/ documentation with the actual state of the code. This keeps architecture, domain, and standards docs accurate without human effort.
Invoke this skill at the start of any architect task when the cache is stale (>5 days old) or missing.
Run these checks before scanning. If either fails, abort the skill and proceed with the original task.
Check 1 — Verify codebase context
Look for .context/overview.md or .context/project-overview.md in the current working directory.
Check 2 — Check the cache
Read .context/cache/context_update.md.
last_executed is within the last 5 days → context is fresh. Abort skill.Work through each step in order. Read the current .context/ file, scan the relevant source, and update only what has changed. Do not rewrite sections that are hand-authored, opinion-based, or business-context.
overview.mdTarget: .context/overview.md (or project-overview.md)
*.csproj, package.json, etc.)## Current State (or equivalent):
.gitkeep placeholders.context/domains/Target: all *.md files in .context/domains/
entities.md — compare against actual entity classes in source:
Implemented vs Planned based on whether source files existglossary.md — add new terms introduced in code; update definitions if usage has evolved.context/architecture.mdTarget: all *.md files in .context/architecture.md
.context/standards.mdTarget: all *.md files in .context/standards.md
code-style.md — note new conventions observed in recently added codenaming-conventions.md — update if naming patterns have evolvederror-handling.md — update if error handling patterns have changedAfter completing all steps (or confirming nothing changed), write .context/cache/context_update.md. Create .context/cache/ if it does not exist.
---
last_executed: <ISO 8601 timestamp — e.g., 2026-03-07T15:09:00Z>
triggered_by: architect-agent
---
## Summary
- **Reviewed:** `overview.md`, `domains/`, `architecture.md`, `standards.md`
- **Changes made:** yes / no
- **Files updated:**
- [list files that were changed, or "none"]
.context/ — never touch source code during this skill.gitkeep in source dirs), update Current State to reflect that but make no other changesdevelopment
Writes and runs a test suite for a piece of code, covering happy path, edge cases, error cases, and security cases. Use when: implementation is complete and needs test coverage, a bug needs a reproduction test and fix validation, or code needs coverage before a refactor. Do not use when: the code under test is not yet implemented, or the spec is still unclear.
testing
Use when creating a new skill, editing an existing skill, or helping a user author a skill for this system. Covers structure, discoverability, quality, and discipline hardening.
development
Evidence-based verification process to run before marking any task complete. Use this skill every time you're about to report that work is done — for features, bug fixes, refactoring, or any code change. This catches the most common failure mode: declaring "done" without proof. If you're finishing up and about to tell the user the task is complete, run this checklist first.
development
Teaches agents how to discover, select, and invoke skills from the skill library. Use this skill whenever you're uncertain which skill applies to a task, when composing multiple skills for complex work, or when you need to understand what skills are available. This is your go-to when facing an ambiguous task and need to figure out the right approach before diving into implementation.