Skip to content
Development
Skill

/update

Pull the latest flagrare skills from GitHub. Use when the user says 'update skills', 'refresh skills', 'pull latest skills', 'update flagrare', or 'sync skills'.

From plugin
flagrare-agent-skills
1134 skills
Install
$ npx -y skills add Flagrare/agent-skills --skill update --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/update

Context preview

The summary Claude sees to decide when to auto-load this skill.

Pull the latest flagrare skills from GitHub. Use when the user says 'update skills', 'refresh skills', 'pull latest skills', 'update flagrare', or 'sync skills'.

SKILL.md

update.SKILL.md
name: update
description: "Pull the latest flagrare skills from GitHub. Use when the user says 'update skills', 'refresh skills', 'pull latest skills', 'update flagrare', or 'sync skills'."

Update

Pull the latest version of all flagrare skills from the remote repository.

When to Use

  • User says "update skills", "refresh skills", "pull latest skills", "update flagrare", "sync skills"
  • User wants to get the newest version of a skill after a known push

Procedure

Run the canonical update script directly from GitHub. This guarantees the script logic is current even if this skill's text has been cached from an older release:

bash <(curl -sL https://raw.githubusercontent.com/Flagrare/agent-skills/main/update.sh)

**Run it with the agent sandbox disabled.** The script rewrites `~/.claude/plugins/`, which sandboxes normally deny writes to. Sandboxed, the `claude plugin marketplace update` call fails, the script falls through to its re-clone branch, and you get a wall of `rm: Operation not permitted` instead of an update. In Claude Code, pass `dangerouslyDisableSandbox: true` on the Bash call rather than running it once to watch it fail.

After running, tell the user:

> Skills updated from GitHub. Run `/reload-plugins` or restart Claude Code to apply.

Ships withflagrare-agent-skills

Thirty-three skills that wrap around your development cycle in Claude Code. They turn tickets into ATDD plans, smoke-test features against a running app or service, hunt down bugs with runtime evidence, guard commits against doc drift, run seven-axis code

Get the whole plugin
Stats
11
Stars
2
Forks
Active
Maintenance
JavaScript
Language
23h ago
Last commit
4mo ago
Created

Repo: Flagrare/agent-skills

Other skills on flagrare-agent-skills.