xiaolai

xiaolai/echo-sleuth-for-claude

Agent

Use this agent when the user asks "what can we learn", "extract wisdom", "what worked well", "summarize lessons", "generate insights", "what should I remember", "what patterns do I use", "how do I usually work", "my common workflows", "what tools do I prefer", "analyze my habits", "show usage statistics", or wants…

xiaolai/echo-sleuth-for-claude

Agent

Use this agent when the user asks "what happened to this file", "history of file X", "who changed this and why", "when was this file last modified", "trace changes to X", or needs to understand the full history of a specific file across both conversation sessions and git commits. Examples.

xiaolai/echo-sleuth-for-claude

Agent

Use this agent when the user asks to deeply audit memory staleness, verify memory claims against current code, check if memories reference deleted files or functions, or wants content-aware memory verification beyond simple age-based scoring. Dispatched by /audit --deep.

xiaolai/echo-sleuth-for-claude

Agent

Use this agent when the user asks "how did I get here", "find sessions about X", "what happened yesterday", "why did we choose X", "what went wrong with Y", "find past decisions", "what errors did we hit", "what was the rationale", "what alternatives were considered", "avoid past failures", or needs to locate, search…

xiaolai/echo-sleuth-for-claude

Agent

Use this agent when the user asks "has the format changed", "check if scripts still work", "discover schema", "what record types exist", "validate our assumptions", "is anything new in .claude", "check compatibility", or needs to verify that echo-sleuth's parsing scripts are compatible with the current Claude Code…

xiaolai/echo-sleuth-for-claude

Command

Audit memory staleness — heuristic scan or deep content verification.

xiaolai/echo-sleuth-for-claude

Command

Global memory overview — staleness alerts, token costs, and stats across all projects.

xiaolai/echo-sleuth-for-claude

Command

Extract knowledge from a conversation session — decisions, corrections, patterns, and references.

xiaolai/echo-sleuth-for-claude

Command

Extract accumulated wisdom from past sessions.

xiaolai/echo-sleuth-for-claude

Command

Interactive memory cleanup — review and prune stale memories.

xiaolai/echo-sleuth-for-claude

Command

Search past conversations for a topic, decision, or mistake. Pass --lite for raw, no-synthesis output (works on standard tier; cheapest API path).

xiaolai/echo-sleuth-for-claude

Command

Summarize recent sessions.

xiaolai/echo-sleuth-for-claude

Command

Show chronological timeline of project work.

xiaolai/echo-sleuth-for-claude

Skill Claude CodeCodex

This skill should be used when the user asks to "learn from past sessions", "extract lessons", "find what worked", "identify patterns in my workflow", "what mistakes did I make", "what decisions were made", or wants to synthesize wisdom and actionable insights from conversation history.

xiaolai/echo-sleuth-for-claude

Skill Claude CodeCodex

This skill should be used when the user asks to "check git history", "trace code changes", "find when something was added", "correlate commits with sessions", "find hotspot files", or needs to mine git repository history for insights. Only applicable when the current project is a git repository.

xiaolai/echo-sleuth-for-claude

Skill Claude CodeCodex

This skill should be used when the user asks to "analyze conversation history", "parse JSONL files", "read past sessions", "search conversation logs", "find what happened in a session", or needs to work with Claude Code's .jsonl conversation format. It provides the canonical parsing infrastructure for echo-sleuth…

xiaolai/echo-sleuth-for-claude

Skill Claude CodeCodex

Use when auditing, extracting, pruning, or writing Claude Code memory files. Covers memory file format, MEMORY.md index conventions, staleness scoring, claim extraction heuristics, destination routing, mutation rules, and archive conventions.

xiaolai/mac-it-guy-pro

Plugin Claude Code

Plugin marketplace listing 1 plugin: mac-it-guy-pro.

xiaolai/mac-it-guy-pro

Plugin Claude Code

Personal IT guy for non-technical users — remembers your machine, guards every action, and leaves reusable tools behind.

xiaolai/mac-it-guy-pro

Instructions file CodexOpenCode

Instructions for xiaolai/mac-it-guy-pro, covering working conventions for this repo, privacy discipline when testing against a real machine, english only, verification before release and which matcher a new guard rule should use.

xiaolai/mac-it-guy-pro

Agent

Read-only evidence gatherer for IT tasks — runs the macOS diagnostic recipes (disk, memory, startup items, updates, backups, battery, SMART) and returns structured findings. Never changes anything. Use for checkups and for diagnosing user-described problems before any fix.

xiaolai/mac-it-guy-pro

Agent

Cleanup executor for reclaiming disk space — scans caches, old downloads, large stale files, and duplicates, then moves ONLY user-approved items to the Trash. Never uses rm, never empties the Trash, always dry-runs first. Use after the user has approved a cleanup plan.

xiaolai/mac-it-guy-pro

Agent

File organization executor — scans a folder (Downloads, Desktop, photos, PDFs), proposes a file-by-file destination plan, and after approval writes an undo manifest and executes the moves. Never deletes, never overwrites. Use for organize workflows.

xiaolai/mac-it-guy-pro

Agent

Builds toolbox micro-tools from a clarified chore specification — writes the script, plain-language README, and double-clickable wrapper under /ITGuy/toolbox/, tests the dry-run on real files, and registers the tool. Also handles tool upgrades (script → CLI → scheduled). Use for automate and toolbox-evolve workflows.