# Ingest Feedback

> Use when user wants to ingest a development-skills feedback report and apply fixes, or runs /ingest-feedback. Challenges every suggestion against the Iron Rules before accepting; most friction points should SKIP. Expect a report path as argument.

- Skill: `concertonotes/ingest-feedback` (Agent Skill)
- Install (CLI): `npx skillmds@latest add concertonotes/ingest-feedback`
- Raw SKILL.md: https://api.skillmd.com/api/skills/concertonotes/ingest-feedback/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Docs & Writing
- Author: ConcertoNotes (https://skillmd.com/u/concertonotes)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/concertonotes/ingest-feedback

---


Ingest a development-skills feedback report. Challenge every suggestion against the Iron Rules before accepting. Report path: $ARGUMENTS

## Ground Rule: The Report Is Input, Not Truth

The report describes what happened, not what should change. Most friction is model behavior or edge cases. A change must EARN its place.

Iron Rules to apply here (canonical: `../../shared/iron-rules.md`):
- **Principle 3 — Simplicity by default.** Small improvement + ugly complexity = not worth it.
- **Principle 5 — All signal, zero noise.** Everything earns its place.

**Marginal improvement + added words/rules → SKIP.**

---

## Step 1: Read the Report

Extract friction points (Section 3), chain-of-thought (Section 2).

## Step 2: Read Current Plugin State

Read every file referenced in friction points. Understand current instruction, why it exists, what went wrong.

## Step 3: Gather Best Practices (targeted)

Research content relevant to friction points:
- Official Claude Code docs: https://code.claude.com/docs/en/overview
- `@~/Documents/ai/superpowers`
- `@~/Documents/ai/claude-code-best-practice`

## Step 4: Critical Evaluation — Friction Points

Write verdicts in `docs/reports/ingest-YYYY-MM-DD.md`.

| Verdict | Meaning | Burden |
|---------|---------|--------|
| **FIX** | Instruction is wrong, misleading, or causes repeated waste. Net simplification or correction. | HIGH |
| **SKIP** | Edge case, model behavior, already handled, or fix adds more complexity. | LOW (default) |
| **INVESTIGATE** | Insufficient information. | — |

### Mandatory Rejection Filters (ANY yes → SKIP)

1. Model ignored a clear instruction? → SKIP (compliance, not coverage)
2. Fix adds new rule/exception for a one-time event? → SKIP
3. Fix makes plugin longer with marginal improvement? → SKIP
4. Already covered by existing instructions? → SKIP
5. Would removing/shortening an instruction fix it better? → Only acceptable FIX direction

| # | Friction Point | Verdict | Rejection filter? | Reasoning |
|---|---------------|---------|-------------------|-----------|

## Step 5: Apply Changes

**FIX verdicts only.** Surgical edits:
- Prefer removing/shortening over adding
- If adding words, remove at least as many elsewhere (net-zero or negative)

## Step 6: Validate

Run `pre-commit run` (if `.py` touched: `ruff format .` + `ruff check . --fix`).

## Step 7: Summary

Report: FIX/SKIP/INVESTIGATE counts, files changed and why, report location.

**Expected: most friction points SKIP.** If >30% FIX, re-examine critical rigor.