playbooks

home / skills / sounder25 / google-antigravity-skills-library / 10_async_feedback

10_async_feedback skill

/10_async_feedback

This skill enables mid-task course correction by monitoring FEEDBACK.md and applying user guidance without restarting.

npx playbooks add skill sounder25/google-antigravity-skills-library --skill 10_async_feedback

Review the files below or copy the command above to add this skill to your agents.

Files (4)
SKILL.md
1.2 KB
---
name: Async Feedback Loop
description: Enables mid-stream course correction by monitoring a FEEDBACK.md file for user interventions. Allows the agent to incorporate new instructions without restarting the task.
version: 1.0.0
author: Antigravity Skills Library
created: 2026-01-16
leverage_score: 5/5
---

# SKILL-010: Async Feedback Loop

## Overview

Long-running tasks often drift. This skill provides a mechanism for the user to inject guidance via a `FEEDBACK.md` file. The agent checks this file and pivots immediately if new instructions are found.

## Trigger Phrases

- `check feedback`
- `read instructions`
- `get user input`

## Inputs

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `--file` | string | No | `FEEDBACK.md` | The feedback channel file |
| `--acknowledge` | switch | No | False | Mark feedback as read (append timestamp) |

## Outputs

1. Console: "New feedback found: ..." or "No new feedback."
2. File Update: Appends "Read by Agent at <time>" if acknowledged.

## Implementation

See `check_feedback.ps1`.

## Integration

```powershell
# In a loop:
.\skills\10_async_feedback\check_feedback.ps1 -Acknowledge
if ($LASTEXITCODE -eq 0) {
    # Pivot strategy
}
```

Overview

This skill enables mid-stream course correction for long-running automation by monitoring a FEEDBACK.md file for user interventions. It lets the agent detect new instructions without restarting the task and optionally acknowledge them. The implementation is in PowerShell and is designed for deterministic, safe pivots during execution.

How this skill works

The agent runs a PowerShell check_feedback script periodically or on demand to inspect the FEEDBACK.md feedback channel for new content. When it detects new instructions, it prints a console message and can append a timestamped acknowledgment to mark the feedback as read. The script returns a success exit code when new feedback is found so caller logic can pivot strategy immediately.

When to use it

  • Long-running jobs that may need user guidance mid-execution
  • Automated deployments or build pipelines requiring occasional manual input
  • Multi-step data processing where upstream decisions can change outcomes
  • Agents that must remain non-blocking but responsive to operator edits
  • Situations requiring auditable confirmation that feedback was consumed

Best practices

  • Keep FEEDBACK.md concise and timestamped so changes are easy to detect
  • Run the check periodically at sensible intervals to balance responsiveness and overhead
  • Use the acknowledge switch to append a read receipt and avoid duplicate handling
  • Treat feedback as authoritative for decision pivots, but validate any critical values before applying
  • Combine with safety gates like pre-action guards to prevent unsafe immediate pivots

Example use cases

  • A CI pipeline that adjusts test selection mid-run after a stakeholder notes flaky tests
  • A data migration that pauses for operator instructions if schema ambiguities are reported
  • An infrastructure provisioning job that switches regions when an incident is annotated in FEEDBACK.md
  • A long-running analysis where domain experts can inject corrected parameters without restarting

FAQ

What file does the agent monitor?

By default it monitors FEEDBACK.md, but the script accepts a --file parameter to override the path.

How do I prevent reprocessing the same feedback?

Use the acknowledge switch to append a timestamped "Read by Agent" line, or implement your own marker strategy in the feedback file.