feedback
Save autoloop experiment feedback proactively. MUST trigger when the user corrects loop design ("don't use that metric", "always include this gate", "wrong quality gate") or confirms good output. Also trigger on explicit requests: "save this feedback", "show my feedback", "clear feedback", "loop preferences", "autoloop settings", "consolidate feedback", "bake in my preferences". Feedback loaded automatically when designing new experiment loops.
What this skill does
# Autoloop Feedback Manager
Persist feedback about experiment loop design across sessions. Stored feedback is automatically
loaded when autoloop designs new loops, ensuring design preferences carry forward.
## Actions
### Save Feedback
When the user provides feedback on loop design or execution, save it:
```bash
echo '{"category": "<category>", "feedback": "<what the user said>", "context": "<optional context>"}' | \
python ${CLAUDE_PLUGIN_ROOT}/scripts/feedback_manager.py autoloop save-feedback
```
**Categories**: loop_design, metrics, quality_gates, runner_script, time_budget, change_strategy, general
**Examples**:
- "Always include type checking as a gate" → `{"category": "quality_gates", "feedback": "Include mypy type checking as a quality gate in all Python autoloops"}`
- "Don't use coverage as a primary metric" → `{"category": "metrics", "feedback": "Avoid test coverage as primary metric — it leads to low-value tests. Use as secondary only"}`
- "Keep time budgets under 2 minutes" → `{"category": "time_budget", "feedback": "Prefer experiments that complete in under 2 minutes for faster iteration"}`
- "The runner script should always log to stderr" → `{"category": "runner_script", "feedback": "Runner scripts should redirect verbose output to stderr, keep stdout for METRIC lines only"}`
- "Be more conservative with changes" → `{"category": "change_strategy", "feedback": "Prefer small, focused changes per iteration over ambitious rewrites"}`
### Show Feedback
Display all stored feedback:
```bash
python ${CLAUDE_PLUGIN_ROOT}/scripts/feedback_manager.py autoloop show-feedback
```
Present as a readable list grouped by category.
### Clear Feedback
Clear all feedback or feedback for a specific category:
```bash
# Clear all
python ${CLAUDE_PLUGIN_ROOT}/scripts/feedback_manager.py autoloop clear-feedback
# Clear only metrics feedback
python ${CLAUDE_PLUGIN_ROOT}/scripts/feedback_manager.py autoloop clear-feedback metrics
```
### Consolidate Feedback
Graduate stable feedback into the actual SKILL.md files, making corrections permanent. This is a
Claude-driven operation — no script needed.
**When to consolidate**: When the user says "update the plugin based on feedback", "consolidate feedback",
"bake in my preferences", or "graduate feedback into the skill".
**Process**:
1. Load all stored feedback:
```bash
python ${CLAUDE_PLUGIN_ROOT}/scripts/feedback_manager.py autoloop show-feedback
```
2. Read the target SKILL.md file:
- `${CLAUDE_PLUGIN_ROOT}/skills/autoloop/SKILL.md`
3. For each feedback entry, determine if it should be consolidated:
- **Consolidate**: Universal preferences, repeated corrections, style rules that always apply
- **Keep as runtime feedback**: Situational preferences, context-dependent corrections, temporary focus areas
4. Present a consolidation plan to the user:
```
## Consolidation Plan
**Will bake into SKILL.md** (permanent):
- [feedback] → edit [file]: [what will change]
**Will keep as runtime feedback** (situational):
- [feedback] → reason: [why it stays runtime]
Proceed?
```
5. On approval:
- Edit the target SKILL.md files using the Edit tool
- Clear only the graduated feedback entries:
```bash
python ${CLAUDE_PLUGIN_ROOT}/scripts/feedback_manager.py autoloop clear-feedback <category>
```
- Keep non-graduated entries untouched
6. Report what changed and what remains as runtime feedback.
## How Feedback is Used
When autoloop designs a new experiment loop, it loads all feedback entries and applies them:
- **loop_design** feedback → adjusts overall loop structure and iteration strategy
- **metrics** feedback → guides metric selection and direction (minimize/maximize)
- **quality_gates** feedback → ensures preferred gates are included or excluded
- **runner_script** feedback → adjusts runner script generation (logging, output format)
- **time_budget** feedback → calibrates experiment duration and timeout settings
- **change_strategy** feedback → shapes the allowed change types in program.md
- **general** feedback → applied to all aspects of loop design
This ensures the user never has to repeat the same design preference twice.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.