/suggest

description: "Experimental: Analyze activity and suggest memories to save"
argument-hint: "[--auto]"

/nemp:suggest

> Experimental: suggestions depend on an available activity log. Review proposed memories by default; `--auto` explicitly opts into saving without individual review. Activity frequency is not evidence that an inferred fact is true.

Intelligently suggest memories to save based on your recent work patterns.

Usage

/nemp:suggest            # Analyze and show suggestions interactively
/nemp:suggest --auto     # Automatically save all suggestions

Instructions

You are an intelligent pattern analyzer. Examine the user's recent activity and suggest valuable memories to save.

Step 1: Read Activity Log

Read the activity log from `.nemp/activity.log` or `.nemp-pro/activity.log`.

If no activity log exists:

No Activity Log Found

Enable activity capture to get personalized suggestions:
  /nemp:auto-capture on

Or manually add memories:
  /nemp:save <key> <value>
  /nemp:init              # Auto-detect project stack

Step 2: Parse and Analyze Patterns

Analyze the activity log entries to identify patterns:

**Pattern Detection Categories:**

| Category | Detection Method | Suggestion Type | |----------|------------------|-----------------| | **Hot Files** | Files edited 3+ times | `important-files` | | **Core Modules** | Directories with most activity | `project-structure` | | **Workflow Commands** | Repeated bash commands (git, npm, test) | `dev-workflow` | | **Stack Signals** | File extensions + paths | `stack-hints` | | **Testing Patterns** | Test commands + test file edits | `testing-workflow` | | **Build Patterns** | Build/deploy commands | `build-workflow` | | **New Dependencies** | npm/yarn/pnpm install commands | `new-packages` |

**Analysis Rules:**

FOR EACH activity entry:
  - Track file paths → count modifications per file
  - Track directories → identify hot zones (e.g., src/auth/, src/api/)
  - Track commands → identify workflow patterns
  - Track file types → detect stack usage
  - Track install commands → detect new dependencies (Rule 2)

THRESHOLDS:
  - File modified 3+ times → IMPORTANT FILE
  - Directory has 5+ file edits → CORE MODULE
  - Command run 3+ times → WORKFLOW PATTERN
  - Same file type in multiple edits → STACK SIGNAL
  - Any npm/yarn/pnpm/bun install → NEW DEPENDENCY (always suggest)

Step 3: Smart Memory Drafting

For each suggestion, auto-generate a memory value that is concise, actionable, and useful for future sessions.

**Drafting Rules:**

1. **Be Specific** - Include actual file paths, command names, package versions 2. **Be Concise** - Keep under 200 characters when possible 3. **Be Actionable** - Write in a way that helps future Claude sessions 4. **Include Context** - Add brief explanations for non-obvious items

**Memory Value Templates:**

| Suggestion Type | Template | Example | |-----------------|----------|---------| | `important-files` | `Core files: {file1} ({purpose}), {file2} ({purpose})` | `Core files: src/auth/login.ts (auth logic), src/api/users.ts (user CRUD)` | | `core-modules` | `Architecture: {dir1}/ ({purpose}), {dir2}/ ({purpose})` | `Architecture: src/auth/ (authentication), src/api/ (REST endpoints)` | | `dev-workflow` | `Dev: {cmd1}, Test: {cmd2}, Build: {cmd3}` | `Dev: npm run dev, Test: npm test, Build: npm run build` | | `testing-approach` | `Tests: {runner} in {location}, run with {command}` | `Tests: vitest in src/__tests__/, run with npm test` | | `deploy-process` | `Deploy: {build_cmd} then {deploy_method}` | `Deploy: npm run build then vercel --prod` | | `new-packages` | `Added: {pkg1} ({desc}), {pkg2} ({desc})` | `Added: zod (validation), react-query (data fetching)` |

**Example Drafts:**

DETECTED: File src/auth/login.ts edited 7 times
DRAFTED:  "Core auth file handling user login, token generation, and session creation"

DETECTED: npm install zod @tanstack/react-query
DRAFTED:  "Added zod (schema validation) and @tanstack/react-query (server state management)"

DETECTED: Commands npm test (5x), npm run dev (8x), git commit (4x)
DRAFTED:  "Workflow: dev server with 'npm run dev', test with 'npm test', commit frequently"

DETECTED: Directory src/components/ has 12 file edits
DRAFTED:  "UI components in src/components/ - Button, Modal, Form, Layout are most active"

**Intelligent Inference:**

When drafting, infer purpose from file/directory names:

| Pattern | Inferred Purpose | |---------|------------------| | `*/auth/*`, `*/login*`, `*/session*` | Authentication | | `*/api/*`, `*/routes/*`, `*/endpoints/*` | API layer | | `*/components/*`, `*/ui/*` | UI components | | `*/hooks/*` | Custom React hooks | | `*/utils/*`, `*/helpers/*`, `*/lib/*` | Utilities | | `*/store/*`, `*/state/*` | State management | | `*/types/*`, `*.d.ts` | Type definitions | | `*/tests/*`, `*/__tests__/*`, `*.test.*` | Testing | | `*/middleware/*` | Request middleware | | `*/services/*` | Business logic | | `*/models/*`, `*/entities/*` | Data models | | `*/config/*`, `*.config.*` | Configuration |

**Quality Checks:**

Before finalizing a drafted memory:

CHECK 1: Is it under 200 characters? (Prefer concise)
CHECK 2: Does it contain specific names? (No vague references)
CHECK 3: Would it help a new session understand the project? (Useful)
CHECK 4: Is it different from existing memories? (No duplicates)

If a draft is too long, summarize:

BEFORE: "The authentication system uses src/auth/login.ts for handling user
        login requests, src/auth/register.ts for new user registration,
        src/auth/logout.ts for session termination, and src/middleware/auth.ts
        for protecting routes"

AFTER:  "Auth: login.ts (login), register.ts (signup), logout.ts (signout),
        middleware/auth.ts (route protection)"

Step 4: Generate Suggestions

Based on analysis and smart drafting, create memory suggestions:

**Suggestion Types:**

1. **Important Files**