# Common Feedback Reporter

> Pre-write audit for skill violations. Checks planned code against loaded skill anti-patterns before any file write. Use when writing Flutter/Dart code, editing SKILL.md files, or generating any code where project skills are active. Load as composite alongside other skills. When a violation is detected and Auto-fixed: YES, also load +common/common-learning-log to record the mistake.

- **Type:** Skill
- **Install:** `agentstack add skill-hoangnguyen0403-agent-skills-standard-common-feedback-reporter`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [HoangNguyen0403](https://agentstack.voostack.com/s/hoangnguyen0403)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [HoangNguyen0403](https://github.com/HoangNguyen0403)
- **Source:** https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/.agents/skills/common/common-feedback-reporter
- **Website:** https://www.npmjs.com/package/agent-skills-standard

## Install

```sh
agentstack add skill-hoangnguyen0403-agent-skills-standard-common-feedback-reporter
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Feedback Reporter

## **Priority: P0 - Auto-detect skill violations before file writes**

## 🚨 Checkpoint: Before File Writes

**Quick check before `write_to_file`, `replace_file_content`, `multi_replace_file_content`:**

1. **Check** - Any skills loaded for this file extension?
- NO → ✅ Proceed silently
- YES → Continue to step 2

2. **Audit** - planned code violate loaded skill rules?
- NO → ✅ Proceed silently — ** NOT submit feedback report**
- YES → Output violation block below, then fix immediately

## Detection Flow

```
Before file write?
├─ Check file extension → Identify loaded skills
├─ Review skill anti-patterns/rules
├─ Code matches anti-pattern?
│  ├─ YES → 🚨 VIOLATION → feedback command
│  └─ NO → ✅ Proceed
└─ No skills loaded → ✅ Proceed
```

## Examples (Quick Reference)

**Flutter**: `color: Colors.blue` → Rule: No hardcoded colors → Report + use theme

**React**: `class MyComponent extends...` → Rule: Use functions → Report + convert

**SKILL.md**: 105 lines → Rule: ≤100 lines max → Report + extract to references/

[More examples →](references/violation-examples.md)

## Violation Report Format

When violation detected, output this block before fixing:

```
🚨 SKILL VIOLATION DETECTED
Skill:        [skill-id]
File:         [relative/path/to/file.ext]:[line-range]
Rule:         [exact rule text from SKILL.md]
Violation:    [what planned code does — up to 5-line offending snippet]
Fix:          [corrected approach — up to 5-line corrected snippet]
Auto-fixed:   YES / NO
Root Cause:   [AMBIGUOUS_RULE | MISSING_COVERAGE | OUTDATED_GUIDANCE | COMPETING_RULES | PATTERN_MISMATCH]
User Intent:  [1 sentence: what the user was trying to achieve]
Skill Gap:    [1–2 sentences: what change to the SKILL.md would prevent this next time]
Co-skills:    [other active skill IDs, comma-separated, or 'none']
```

### Root Cause Guide

| Code                | When to use                                          |
| ------------------- | ---------------------------------------------------- |
| `AMBIGUOUS_RULE`    | Rule wording permits multiple interpretations        |
| `MISSING_COVERAGE`  | Common pattern not addressed anywhere in skill       |
| `OUTDATED_GUIDANCE` | Skill references deprecated API or framework version |
| `COMPETING_RULES`   | Two loaded skills gave contradictory guidance        |
| `PATTERN_MISMATCH`  | AI misread or misapplied anti-pattern definition     |

Then apply fix immediately — not wait for user confirmation.

## Pre-Completion Check

Before `notify_user` or task completion:

** I write code?** YES → ** I audit skills?** NO → Audit now

## Anti-Patterns

- **No "I'll check later"**: Check before writing, not after
- **No "minor change skip"**: Every write needs check
- **No "user waiting skip"**: 10-second check > pattern violation
- **No "clean-pass report"**: If no violation found, proceed silently — NOT submit report
- **No "shallow report"**: Always populate Root Cause, User Intent, and Skill Gap — these drive improvement

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [HoangNguyen0403](https://github.com/HoangNguyen0403)
- **Source:** [HoangNguyen0403/agent-skills-standard](https://github.com/HoangNguyen0403/agent-skills-standard)
- **License:** Apache-2.0
- **Homepage:** https://www.npmjs.com/package/agent-skills-standard

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-hoangnguyen0403-agent-skills-standard-common-feedback-reporter
- Seller: https://agentstack.voostack.com/s/hoangnguyen0403
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.