This skill should be used when saving or restoring conversation sessions, managing session state, or resuming previous work. Triggers on questions about saving progress, restoring context, or continuing where left off. <example> Context: User is stepping away user: "Save this session, I'll continue later" </example> <example> Context: User returns to previous work user: "Restore my morning session" </example>
From psnnpx claudepluginhub aladac/claude-pluginsThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Optimizes cloud costs on AWS, Azure, GCP via rightsizing, tagging strategies, reserved instances, spot usage, and spending analysis. Use for expense reduction and governance.
Sessions use the memory system:
| Tool | Purpose |
|---|---|
mcp__plugin_psn_core__memory_store | Save session state |
mcp__plugin_psn_core__memory_recall | Find sessions by query |
mcp__plugin_psn_core__memory_search | List sessions by subject |
mcp__plugin_psn_core__memory_forget | Delete old sessions |
| Tool | Purpose |
|---|---|
Bash | Get git branch, working directory |
Read | Read recent files for context |
| Command | Purpose |
|---|---|
/session:save | Save current session |
/session:restore | Restore a session |
Skill(skill: "psn:memory") - Memory patternsSave and restore conversation sessions for seamless work continuity.
Sessions are stored in the memory system:
session.{name}~/.local/share/personality/main.db{
"name": "session-name",
"working_directory": "/path/to/project",
"timestamp": "2026-02-17T10:30:00Z",
"context": "Brief description of what was being worked on",
"open_files": ["src/main.rs", "README.md"],
"pending_tasks": [
"Implement pagination",
"Add tests for new endpoint"
],
"conversation_summary": "Working on API refactor, completed auth module",
"git_branch": "feature/pagination",
"notes": "User prefers verbose test output"
}
session-2026-02-17-1030api-refactor-feb17Subject: session.{name}
Content: JSON context object
Metadata: { timestamp, user, source: "claude-session" }
User: /session:save morning-work
Gathering session context...
- Working directory: ~/Projects/api
- Branch: feature/auth
- Recent files: src/auth.rs, tests/auth_test.rs
- Pending: Add refresh token support
Session 'morning-work' saved.
Restore with: /session:restore morning-work
session.{name}User: /session:restore morning-work
Restoring session 'morning-work'...
š Directory: ~/Projects/api
šæ Branch: feature/auth
š Context: Working on API refactor, completed auth module
Pending tasks:
- [ ] Add refresh token support
- [ ] Update API documentation
Continue where you left off?
Search for all sessions:
Query: "session" with subject filter "session.*"
Display as table:
| Name | Date | Project |
|---------------|------------|-------------|
| morning-work | 2026-02-17 | api |
| bug-fix-123 | 2026-02-16 | frontend |
| code-review | 2026-02-15 | shared-lib |
| Pattern | Use Case |
|---|---|
{task}-{date} | Task-based: auth-feb17 |
{project}-{feature} | Feature work: api-pagination |
{ticket} | Ticket tracking: JIRA-1234 |
{time} | Quick save: afternoon-session |
Delete old sessions:
mcp__plugin_psn_core__memory_forget(id: <session-memory-id>)
Recommended: Clean sessions older than 30 days unless pinned.
Sessions complement the memory system:
After restoring a session, relevant memories are automatically available through semantic search.