Async Feedback Loop
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.
Best use case
Async Feedback Loop is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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.
Teams using Async Feedback Loop should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/async-feedback-loop/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Async Feedback Loop Compares
| Feature / Agent | Async Feedback Loop | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 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
}
```Related Skills
feedback-observing
Read agent interaction logs across packs and detect operational patterns. Emits state-transition FeedbackEvents for degradation/recovery.
asynchronous-programming-preference
Favors the use of async and await for asynchronous programming in Python.
async-operations
Specifies the preferred syntax for asynchronous operations using async/await and onMount for component initialization. This results in cleaner and more readable asynchronous code.
async-repl-protocol
Async REPL Protocol
addressing-pr-feedback
Fetches, organizes, and addresses PR review comments from GitHub. Use when user asks to review PR comments, fix PR feedback, check what reviewers said, address review comments, or handle bot suggestions on a pull request. Triggers on "review PR", "fix comments", "PR feedback", "what did reviewers say", "address PR feedback", "check PR comments".
asyncredux-undo-redo
Implement undo/redo functionality using state observers. Covers recording state history with stateObserver, creating a RecoverStateAction, implementing undo for the full state or partial state, and managing history limits.
asyncredux-observers
Set up observers for debugging and monitoring. Covers implementing actionObservers for dispatch logging, stateObserver for state change tracking, combining observers with globalWrapError, and using observers for analytics.
asyncredux-nonreentrant-mixin
Add the NonReentrant mixin to prevent an action from dispatching while already in progress. Covers preventing duplicate form submissions, avoiding race conditions, and protecting long-running operations.
asyncredux-async-actions
Creates AsyncRedux (Flutter) asynchronous actions for API calls, database operations, and other async work.
asyncpg-detection
This skill should be used when the user asks to "detect asyncpg usage", "find asyncpg patterns", "scan for asyncpg imports", or "identify asyncpg database code in FastAPI projects". It automatically scans Python files to identify asyncpg imports, connection patterns, and query execution methods that need conversion to SQLAlchemy.
asyncio
Python asyncio - Modern concurrent programming with async/await, event loops, tasks, coroutines, primitives, aiohttp, and FastAPI async patterns
asyncapi-docs
AsyncAPI specification handling for event-driven API documentation. Parse, validate, and generate documentation for message-based APIs including Kafka, MQTT, WebSocket, and AMQP systems.