agentleFS
GoogleKnown publishergoogle/adk-samples/core/python/adk-voice-agent/sandbox/skills/approvals/SKILL.md

approvals

Skill11k starsChanged 45 days agoApache-2.0View on GitHub

What to do when a tool call is paused for the user's approval or declined (sending, inviting, deleting, posting, merging), and when you are resumed after one.

2 other projects use a version of this.

Adopted by

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Sep 13: 0 new projectsWeek of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 0 new projectsWeek of Nov 1: 0 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Most recently taken up by

Who's talking about google/adk-samples

The biggest 5 of 32 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 32

Talked about on GitHub, Bluesky, Hacker News and Stack Overflow (32 times).

On GitHub · 23

18 more on GitHub

On Bluesky · 4

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Stop immediately. Do not retry or work around the gate via another tool, CLI, curl, or API.

    line 12
  2. Distinctive:

    Approved: call the exact same tool with the exact same arguments once.

    line 17
  3. Distinctive:

    Declined: do not perform the action.

    line 18
  4. Distinctive:

    Prefer a draft (Gmail draft, Markdown file) unless the user explicitly asked to send, invite, post, or merge.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Approvals

Gated MCP calls that reach other people or delete data trigger request_permission on the voice_agent gateway, move the thread to awaiting_approval, and return "Paused for the user's approval of: …". Prepare everything first so the gated call comes last, then call the tool directly.

When a call is paused

  1. Stop immediately. Do not retry or work around the gate via another tool, CLI, curl, or API.
  2. End your turn with one sentence stating what is waiting for approval.

When resumed

  • Approved: call the exact same tool with the exact same arguments once. Changed arguments require a new approval.
  • Declined: do not perform the action; continue without it or explain what it blocks.

Guidelines

  • Prefer a draft (Gmail draft, Markdown file) unless the user explicitly asked to send, invite, post, or merge.
  • Shell commands denied by policy are final—do not bypass them; report what was blocked.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.