compound-retrieve

Included with Lifetime

$97 forever

Use when starting debugging, planning features, encountering errors, making design decisions, or working in unfamiliar code. Searches past solutions and engineering principles captured by compound-capture to surface institutional knowledge and prevent repeated mistakes. Trigger phrases include "have we seen this before", "check knowledge", "search for solutions", "this looks familiar", "check if we've solved this", "any past experience with this", "before I start, check for existing solutions", or any time past experience might inform the current task. Not for capturing new solutions — use compound-capture for that.

Design

What this skill does

# Compound Retrieve

## Goal

Surface institutional knowledge from past solutions and engineering principles before starting work. Prevent repeated mistakes by searching YAML-frontmatter solution files captured by compound-capture.

## Dependencies

### Tools

- **`compound-knowledge:knowledge-researcher`** — Haiku-powered subagent that performs fast, parallel grep-based retrieval across solution files. Designed for speed (<30s).

### Connectors

- **Solutions directory** — Resolved via path resolution (see Context). Default: `{project_root}/knowledge/solutions/`
- **Cross-project registry** — `~/.claude/compound-knowledge-registry.md`. Enables searching other projects' knowledge bases when local results are thin.

## Context

### Path Resolution

Resolve the solutions directory before any operation. **First match wins:**

1. **Project-level override**: Read `{project_root}/.claude/compound-knowledge.local.md` — extract `solutions_path` value
2. **User-level override**: Read `~/.claude/compound-knowledge.local.md` — extract `solutions_path` value
3. **Default**: `{project_root}/knowledge/solutions/`

If the resolved directory does not exist:
> "Solutions directory not found at `{solutions_path}`. Run `/compound-knowledge:setup` to initialize it."

### When to Retrieve

- **Before non-trivial debugging**: "Let me check if we've seen this before..."
- **During planning phases**: "Checking for relevant past solutions..."
- **When encountering errors**: Search by symptom/error message
- **When working on a project**: Search by project name for all related solutions
- **Making design decisions**: Surface relevant principles and past architectural choices
- **Working in unfamiliar code**: Check for documented patterns and gotchas

## Process

### Step 0: Load Stored Feedback

Load any stored feedback preferences before starting:

```bash
python ${PLUGIN_ROOT}/scripts/feedback_manager.py compound-knowledge show-feedback
```

If feedback entries exist, apply them:
- **retrieval_depth** → adjust how many results are surfaced
- **general** → apply to result formatting and presentation

### Step 1: Resolve Solutions Path

Follow the Path Resolution algorithm from Context. Store as `{solutions_path}`.

### Step 2: Delegate to Knowledge Researcher

Spawn the subagent for fast parallel search:

```
Agent(
subagent_type="compound-knowledge:knowledge-researcher",
model="haiku",
prompt="Search for solutions related to: {task_description}. Project: {project_name}. Keywords: {extracted_keywords}. Solutions path: {solutions_path}. Registry path: ~/.claude/compound-knowledge-registry.md",
description="Search past solutions"
)
```

The researcher reads the registry to identify other knowledge bases for cross-project search when primary results are thin (<3 hits).

### Step 3: Interpret and Apply Results

The knowledge-researcher returns:
1. **Critical patterns** — always-relevant warnings from `critical-patterns.md`
2. **Relevant principles** — engineering wisdom that applies to the current task
3. **Ranked solutions** — scored by project, component, symptom, and tag relevance
4. **Cross-project results** — solutions from other registered knowledge bases
5. **Recommendations** — actionable suggestions based on found solutions

Surface the top results to the user and incorporate insights into your approach:

- If a **critical pattern** matches → warn the user prominently
- If a **principle** applies → reference it when making design decisions
- If a **past solution** matches → suggest the documented fix
- If **nothing found** → say so clearly, don't fabricate relevance

## Output

A concise summary of relevant past solutions and principles, presented to the user with:
- File paths for deeper reading
- Actionable recommendations based on findings
- Prominent warnings for any matching critical patterns

Files: 1

Size: 4.5 KB

Complexity: 18/100

Category: Design

Source: https://github.com/joshuaoliphant/claude-plugins/tree/main/ai_docs/experiments/compound-retrieve-workspace/skill-snapshot

Related in Design

contribute

Included

Local-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".

Designscripts

architectural-analysis

Included

User-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).

Designscripts

mcp

Included

Model 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.

Designscripts

react-native-skia

Included

Design, 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.

Designscripts

plaid

Included

Product 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".

Designscripts

nextjs-framer-motion-animations

Included

Adds 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.

Designscripts