mrzhangguoguo

54 mods across 1 repository, 2 stars between them.

mrzhangguoguo/oh-my-workbuddy

Instructions file CodexOpenCode

Instructions for mrzhangguoguo/oh-my-workbuddy: You are running with oh my workbuddy (OMw), a coordination layer for WorkBuddy. This file is the top-level operating contract. Role prompts under agents/.md are narrower execution surfaces; they follow this file, not override it.

2 1mo ago A 484 tokens original MIT

UserPromptSubmit

05

mrzhangguoguo/oh-my-workbuddy

Hook

Runs when you submit a prompt, before the agent sees it, executing user-prompt-submit.mjs via node. From mrzhangguoguo/oh-my-workbuddy.

2 1mo ago A tokens not measured original MIT

PreToolUse

06

mrzhangguoguo/oh-my-workbuddy

Hook

Runs before the agent uses a tool for Bash, Agent and DeferExecuteTool tool calls, executing pre-tool-use.mjs via node (3 commands). From mrzhangguoguo/oh-my-workbuddy.

2 1mo ago A tokens not measured original MIT

Stop

07

mrzhangguoguo/oh-my-workbuddy

Hook

Runs when the agent finishes a response, executing stop.mjs via node. From mrzhangguoguo/oh-my-workbuddy.

2 1mo ago A tokens not measured original MIT

ai-slop-cleaner

08

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Run a regression-tests-first, smell-by-smell deslop/refactor workflow that preserves behavior and raises signal quality. Use when the user asks to "cleanup", "refactor", "deslop", or when follow-up code has duplicates, dead code, weak boundaries, or fallback-like slop.

2 1mo ago A 66 tokens original MIT

analyze

09

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference boundaries. Use when a user says "analyze", "investigate", "why does", "what's causing", or needs grounded cross-file explanation before any changes are proposed.

2 1mo ago A 65 tokens copy · 88% MIT

ask-claude

10

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Deprecated compatibility shim for Claude advisor requests. Use ask with the claude backend instead.

2 1mo ago A 24 tokens original MIT

ask-gemini

11

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Deprecated compatibility shim for Gemini advisor requests. Use ask with the gemini backend instead.

2 1mo ago A 24 tokens original MIT

ask

12

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Ask a locally installed external advisor CLI (Claude or Gemini) for focused questions, reviews, brainstorming, or second opinions, and capture a reusable artifact. Use when the user wants a Claude/Gemini second opinion, "ask claude", or "ask gemini".

2 1mo ago A 56 tokens original MIT

autopilot

13

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Strict autonomous delivery loop that runs deep-interview, ralplan, ultragoal, code-review, and ultraqa in order with automatic re-planning when gates are not clean. Use on "autopilot", "autonomous", "build me", "create me", "make me", "full auto", "handle it all", or "I want a/an…".

2 1mo ago A 80 tokens original MIT

autoresearch-goal

14

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Durable professor-critic research workflow bound to a tracked goal, with validation-gated completion. Use when a research mission needs ongoing goal-focused management plus professor/critic-style validation.

2 1mo ago A 41 tokens original MIT

autoresearch

15

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Stateful validator-gated research loop that keeps nudging until explicit validation evidence exists. Use when a research output is a bounded deliverable that must pass a script or professor-critic validator, not for ordinary pre-planning docs lookup.

2 1mo ago A 50 tokens original MIT

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Bounded best-practice research using official/upstream evidence first; produces a cited, reusable recommendation and a handoff to planning/execution.

2 1mo ago A 33 tokens original MIT

build-fix

17

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Deprecated shim — build failures are now handled inline by the active execution/debugging workflow; do not route here.

2 1mo ago A 25 tokens original MIT

cancel

18

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Abort the current WorkBuddy workflow — stop background agents/processes, clear in-progress tasks, and hand back control to the user.

2 1mo ago A 27 tokens original MIT

code-review

19

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Run a comprehensive, severity-rated code review for quality, security, and maintainability, with a deterministic merge-readiness verdict.

2 1mo ago A 27 tokens original MIT

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Configure session notifications (Discord/Telegram/Slack webhooks or custom commands) by writing a WorkBuddy-native notifications config file.

2 1mo ago A 28 tokens original MIT

deep-interview

21

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Socratic deep interview with mathematical ambiguity gating that turns vague ideas into execution-ready specifications before planning or implementation.

2 1mo ago A 24 tokens original MIT

deepsearch

22

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Deprecated shim — use the analyze skill for deep repository analysis or repo inspection tools (Read/Grep/Glob/Bash) for fast repo-local lookup.

2 1mo ago A 35 tokens original MIT

design

23

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Canonical repo-local DESIGN.md workflow for product, UI/UX, and frontend decision source of truth.

2 1mo ago A 21 tokens original MIT

doctor

24

mrzhangguoguo/oh-my-workbuddy

Skill Claude CodeCodex

Diagnose and fix oh-my-workbuddy skill installation issues — missing or duplicate skill roots, stale package versions, broken AGENTS.md/memory. Trigger "doctor", "fix skill install", "why is my skill missing", "diagnose skills".

2 1mo ago D 52 tokens original MIT