Best use case
enable-feedback-hooks is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Enable feedback capture hooks for the current project
Teams using enable-feedback-hooks 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/enable-feedback-hooks/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How enable-feedback-hooks Compares
| Feature / Agent | enable-feedback-hooks | 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?
Enable feedback capture hooks for the current project
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
# Enable Feedback Hooks
Opt-in the current project to capture feedback for Product Forge improvements.
## What This Does
When enabled, at the end of each Claude Code session:
1. **Haiku analyzes** the conversation for improvement opportunities
2. **Feedback is saved** to `~/.claude/learnings/` for later review
3. **No data leaves your machine** - feedback stays local until you sync
## Feedback Types Captured
- **Improvements** - Enhancements to existing skills, commands, or agents
- **Skill ideas** - New skills that could help others
- **Command ideas** - New commands that could be useful
- **Bug reports** - Issues with existing components
- **Patterns** - Reusable patterns from your project
## Enable for Current Project
Add the Stop hook to `.claude/settings.local.json`:
```bash
/enable-feedback-hooks
```
## Disable
Remove the hook from the current project:
```bash
/enable-feedback-hooks --disable
```
## How It Works
```
Session ends → Haiku analyzes → Saves to ~/.claude/learnings/
↓
Use /sync-feedback to review
```
## Privacy
- Feedback analysis happens locally via Haiku
- Feedback files stored only on your machine
- You review and choose what to submit via `/sync-feedback`
- Nothing is sent to Product Forge without your explicit action
## Execution Instructions
When the user runs this command:
### Enable Mode (default)
1. **Initialize learnings directory** if needed:
```bash
~/.claude/plugins/cache/product-forge-marketplace/scripts/hooks/init-learnings.sh
```
2. **Check if .claude directory exists**, create if needed:
```bash
mkdir -p .claude
```
3. **Read existing settings.local.json** or create empty structure:
```bash
# If exists, read it
cat .claude/settings.local.json 2>/dev/null || echo '{}'
```
4. **Add the Stop hook configuration**:
- Merge with existing hooks if any
- Write the following hook configuration:
```json
{
"hooks": {
"Stop": [
{
"hooks": [
{
"type": "prompt",
"prompt": "Analyze this session for Product Forge feedback. Identify:\n1. Improvements to existing skills/commands/agents\n2. New skill/command ideas\n3. Bug reports\n4. Reusable patterns\n\nRespond JSON: {\"feedback\": [{\"type\": \"improvement|skill-idea|command-idea|bug-report|pattern\", \"title\": \"...\", \"description\": \"...\", \"target\": \"plugin/component\"}]} or {\"feedback\": []}",
"timeout": 60
},
{
"type": "command",
"command": "python3 ~/.claude/plugins/cache/product-forge-marketplace/scripts/hooks/save-feedback.py",
"timeout": 10
}
]
}
]
}
}
```
5. **Confirm success**:
```
Feedback hooks enabled for this project.
At the end of each session, Haiku will analyze the conversation
for improvement opportunities and save them to ~/.claude/learnings/
Use /sync-feedback to review and submit feedback to Product Forge.
```
### Disable Mode (--disable)
1. **Read existing settings.local.json**:
```bash
cat .claude/settings.local.json
```
2. **Remove the Stop hook** while preserving other settings
3. **Write back the modified settings**
4. **Confirm**:
```
Feedback hooks disabled for this project.
Existing feedback in ~/.claude/learnings/ is preserved.
```
## Notes
- The hook configuration is stored in `.claude/settings.local.json` (not committed to git)
- Each project opts in independently
- Feedback is aggregated across all opted-in projects in `~/.claude/learnings/`Related Skills
sync-feedback
Review and sync captured feedback to Product Forge
zod
Zod schema validation patterns and type inference. Auto-loads when validating schemas, parsing data, validating forms, checking types at runtime, or using z.object/z.string/z.infer in TypeScript.
typescript-import-style
Merge-friendly import formatting (one-per-line, alphabetical). Auto-loads when writing TypeScript/JavaScript imports to minimize merge conflicts in parallel development. Enforces consistent grouping and sorting.
setup-mcp-auth
Configure authentication for an existing FastMCP server
fastmcp
FastMCP TypeScript framework patterns for MCP servers. Auto-loads when building MCP servers, creating tools/resources/prompts, implementing authentication, configuring transports, or working with FastMCP in TypeScript.
add-mcp-tool
Add a new tool to an existing FastMCP server with guided configuration
add-mcp-resource
Add a new resource or resource template to an existing FastMCP server
plan-with-team
Validate plan file ownership
privacy-compliance
GDPR, CCPA, and privacy compliance guidance for data protection. Use when handling personal data, implementing consent management, or ensuring regulatory compliance across jurisdictions.
oauth
OAuth 2.0 and OpenID Connect implementation patterns. Use when implementing authentication, authorization flows, or integrating with OAuth providers like Google, GitHub, or custom identity providers.
mcp-security
Use when securing MCP servers, preventing prompt injection, implementing authorization, validating user input, or building secure multi-agent pipelines. Provides 5-layer defense architecture patterns.
rag-cag-security
Security patterns for RAG and CAG systems with multi-tenant isolation. Use when building retrieval-augmented or cache-augmented generation systems that require tenant isolation, access control, and secure data handling.