This skill should be used when the user asks "how did we solve this before", "what was the decision about X", "have we done this before", "what do you remember about", "check your memory", or when searching for past context, previous decisions, or historical information about the project.
/plugin marketplace add SyntesseraAI/local-recall/plugin install local-recall@syntesseraai-local-recallThis skill inherits all available tools. When active, it can use any tool Claude has access to.
This skill provides guidance for searching local-recall memories to find relevant historical context.
Invoke this skill when:
Episodic memories contain facts, decisions, and observations from past sessions:
Use the episodic_search tool with a natural language query:
episodic_search(query: "authentication implementation decision")
Thinking memories contain reasoning patterns - how problems were analyzed and solved:
Use the thinking_search tool:
thinking_search(query: "debugging race condition in async code")
scope: "file:path/to/file" for file-specific memoriesglobal memories apply everywhere; file: or area: scoped memories are context-specificWhen learning something important that should be remembered:
episodic_create(
subject: "Brief description of the memory",
keywords: ["relevant", "searchable", "terms"],
applies_to: "global", // or "file:path" or "area:name"
content: "Detailed content in markdown"
)
Good candidates for new memories:
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.