skills/skill-sync/SKILL.md
Syncs skill metadata to AGENTS.md Auto-invoke sections. Trigger: After creating/modifying skills, regenerating Auto-invoke tables, or troubleshooting missing skills in AGENTS.md.
npx skillsauth add 333-333-333/agents skill-syncInstall 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.
Keeps AGENTS.md Auto-invoke sections in sync with skill metadata. When you create or modify a skill, run the sync script to automatically update all affected AGENTS.md files.
Each skill that should appear in Auto-invoke sections needs these fields in metadata:
metadata:
author: your-name
version: "1.0"
type: generic # generic | project | meta
scope: [root] # Which AGENTS.md files to update
auto_invoke: "When to invoke this skill" # Single action or list
The type field classifies skills: generic (reusable across projects), project (specific to this project), or meta (skills that manage the skills system itself). Meta skills are excluded from sync — they are managed manually in the Meta-Skills section.
Scopes are discovered dynamically based on your project structure:
| Scope | Updates |
|-------|---------|
| root | ./AGENTS.md (repository root) |
| <directory> | ./<directory>/AGENTS.md |
Examples:
scope: [root] updates ./AGENTS.mdscope: [frontend] updates ./frontend/AGENTS.mdscope: [root, backend, frontend] updates all threeSkills can target multiple scopes: scope: [root, api, ui]
Single action:
auto_invoke: "Creating new components"
Multiple actions:
auto_invoke:
- "Creating new components"
- "Refactoring component structure"
./skills/skill-sync/assets/sync.sh
skills/*/SKILL.md filesmetadata.scope and metadata.auto_invoke### Auto-invoke Skills section in each AGENTS.md# Sync all AGENTS.md files
./skills/skill-sync/assets/sync.sh
# Dry run (show what would change)
./skills/skill-sync/assets/sync.sh --dry-run
# Sync specific scope only
./skills/skill-sync/assets/sync.sh --scope frontend
# Run tests
./skills/skill-sync/assets/sync_test.sh
Given this skill metadata:
# skills/my-skill/SKILL.md
metadata:
author: dev
version: "1.0"
scope: [frontend]
auto_invoke: "Creating React components"
The sync script generates in frontend/AGENTS.md:
### Auto-invoke Skills
When performing these actions, ALWAYS invoke the corresponding skill FIRST:
| Action | Skill |
|--------|-------|
| Creating React components | `my-skill` |
metadata.scope exists and is validmetadata.auto_invoke exists./frontend/AGENTS.md)--dry-run to see what would be generatedThe scope references a directory that doesn't have an AGENTS.md file. Either:
metadata.scope to new/modified skillmetadata.auto_invoke with action description./skills/skill-sync/assets/sync.shtesting
Review Flutter components and screens for UX/UI compliance. Trigger: When user invokes /ux-review command or requests UX audit.
development
TypeScript strict patterns and best practices. Trigger: When implementing or refactoring TypeScript in .ts/.tsx (types, interfaces, generics, const maps, type guards, removing any, tightening unknown).
testing
Testing philosophy and strategy for every feature: test pyramid, mandatory levels per change type, completion checklist, and skill delegation. Trigger: When planning tests for a feature, reviewing test coverage, defining acceptance criteria, or asking what tests a change needs.
development
Terraform security practices: sensitive variables, secret management, state protection, .gitignore patterns, and CI/CD credential handling. Trigger: When handling secrets in Terraform, configuring state backends, reviewing .gitignore for Terraform, or setting up CI/CD pipelines for infrastructure.