update-installed-skills

$npx mdskill add MoizIbnYousaf/Ai-Agent-Skills/update-installed-skills

Update installed skills to latest versions safely with dry-run checks.

  • Keeps installed skills current without breaking workflows or overwriting customizations.
  • Depends on npx ai-agent-skills CLI tool for listing, checking, and syncing.
  • Always runs dry-run before applying updates and reviews breaking changes.
  • Outputs structured JSON results for logging and applies updates after review.

SKILL.md

.github/skills/update-installed-skillsView on GitHub ↗
---
name: update-installed-skills
description: Use when syncing or updating previously installed skills to their latest version. Always dry-run updates before applying, and check for breaking changes.
category: workflow
version: 4.1.0
---

# Update Installed Skills

## Goal

Keep installed skills current without breaking the agent's workflow or silently overwriting local customizations.

## Guardrails

- Always use `--dry-run` before running a real update.
- Check what is currently installed before updating: `npx ai-agent-skills list --installed`.
- Never update all skills at once in production without reviewing the dry-run output.
- Use `--format json` to capture structured update results for logging.

## Workflow

1. List currently installed skills.

```bash
npx ai-agent-skills list --installed --format json --fields name
```

2. Check for available updates.

```bash
npx ai-agent-skills check
```

3. Dry-run the update.

```bash
npx ai-agent-skills sync <skill-name> --dry-run
```

4. Apply the update after reviewing.

```bash
npx ai-agent-skills sync <skill-name>
```

5. For bulk updates, review each skill's dry-run output.

```bash
npx ai-agent-skills sync --all --dry-run
```

## Gotchas

- Skills installed from GitHub will attempt a fresh clone during sync. If the upstream repo is gone, the update will fail gracefully.
- Manually edited SKILL.md files will be overwritten by sync. Back up customizations before syncing.
- The `check` command makes network requests to verify upstream sources. It may be slow or fail if sources are unreachable.

More from MoizIbnYousaf/Ai-Agent-Skills

SkillDescription
ask-questions-if-underspecifiedClarify requirements before implementing. Do not use automatically, only when invoked explicitly.
audit-library-healthUse when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.
backend-developmentBackend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database schemas, or backend system architecture.
browse-and-evaluateUse when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
build-workspace-docsUse when regenerating README.md and WORK_AREAS.md in a managed library workspace. Always dry-run first to preview changes.
code-documentationWriting effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.
curate-a-team-libraryUse when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful `whyHere` notes, and create a starter pack once the first pass is solid.
install-from-remote-libraryUse when installing skills from a shared ai-agent-skills library repo. Inspect with `--list` first, prefer `--collection`, and preview with `--dry-run` before installing.
llm-application-devBuilding applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
migrate-skills-between-librariesUse when moving skills between library workspaces or upgrading from a personal library to a team library. Export from one workspace, import into another.