produce-feedback
Use when user wants to produce a factual chronicle of development-skills plugin interactions in the current conversation for later ingestion, or runs /produce-feedback. Pure record, no judgment.
Best use case
produce-feedback is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when user wants to produce a factual chronicle of development-skills plugin interactions in the current conversation for later ingestion, or runs /produce-feedback. Pure record, no judgment.
Teams using produce-feedback 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/produce-feedback/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How produce-feedback Compares
| Feature / Agent | produce-feedback | 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?
Use when user wants to produce a factual chronicle of development-skills plugin interactions in the current conversation for later ingestion, or runs /produce-feedback. Pure record, no judgment.
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
Produce a factual chronicle of development-skills plugin interactions in this conversation. Pure record, no judgment.
Write to `docs/reports/development-skills-feedback-YYYY-MM-DD.md`. Self-contained.
## Section 1: Project Context (short)
Language, size, test count, framework. Task performed. Why plugin was involved.
## Section 2: Full Chain-of-Thought Dump
EXHAUSTIVE chronological dump of every plugin interaction. Every skill trigger, phase read, gate evaluation, routing decision, agent spawn, tool call, verification run, deviation, problem.
Each step:
1. **Plugin instruction:** Quote the specific instruction from the specific file
2. **Agent action:** Tool called, parameters, result
3. **Agent reasoning:** Why it followed or deviated
4. **Outcome:** What happened
```
Step 3: core-dev/SKILL.md Step 1: "Run: bash scripts/find-plan.sh active"
- Action: Glob("**/find-plan.sh") → no results. grep fallback → found plan.
- Reasoning: Script not found. Used fallback.
- Outcome: Active plan found. 3 tool calls.
```
## Section 3: Friction Point Summary
| # | Step | Plugin file + instruction | What happened | Tool calls |
|---|------|--------------------------|---------------|------------|
## Section 4: Proposed Behavioral Evals
One eval per friction point:
```json
{
"name": "kebab-case-name",
"category": "category",
"tests_change": "which friction point",
"prompt": "user prompt",
"expected_output": "what model should do",
"assertions": [{"name": "x", "type": "behavioral", "check": "what", "pass_criteria": "criteria"}]
}
```
Verify Section 2 covers every interaction, then report location.Related Skills
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.
using-development-skills
Use when starting any conversation - establishes how the development-skills plugin works and how to invoke its components on each platform (Claude Code, Codex). Read first.
update-reqs
Use when user wants to update requirements.in with latest PyPI versions while preserving version patterns
update-reqs-dev
Use when user wants to update requirements-dev.in with latest PyPI versions while preserving version patterns
update-precommit
Use when user wants to update .pre-commit-config.yaml hooks to their latest versions from GitHub
typescript-dev
TypeScript development. Use for TypeScript, Node.js, Express, Fastify, Zod, vitest, jest. Backend, CLI, libraries only — no frontend frameworks.
swift-dev
Swift development. Use for Swift, SwiftUI, UIKit, Vapor, SPM, XCTest, Combine.
staff-review
Use when user wants a code review, deep code review, or staff-level code review of a local branch, repo, directory, or file. Use when user says code review, deep code review, review this branch, review the branch X, review my code, staff review, review locally, or /staff-review.
roast-my-code
Use when user wants a brutally honest code roast, quality critique, or AI-readiness audit. Use when user says roast, roast my code, critique my code, tear apart my code, review quality, or AI-readiness check. Supports --fix flag to auto-fix CRITICAL and HIGH issues via core-dev workflow.
resolve-merge
Use when the user asks to resolve merge conflicts, fix a failed merge, rebase conflict, or run /resolve-merge. Use when git status shows UU/AA/DD conflicts, when there are <<<<<<< conflict markers, when git merge or git pull failed with CONFLICT, or when numbered docs/plans need renumbering after merge. Triggers on: merge conflict, conflict markers, both modified, git merge failed, rebase conflict, resolve conflicts.
python-dev
Python development. Use for Python, FastAPI, Pydantic, asyncpg, pytest, pandas, SQLAlchemy.
java-dev
Java development. Use for Java, Spring Boot, Maven, Gradle, JPA, Hibernate.