richardwu

10 mods across 1 repository, 2 stars between them.

analyze-feedback

01

richardwu/agent-skills

Skill Claude CodeCodex

Skill "analyze-feedback" from richardwu/agent-skills, covering analyze feedback, how to think, response structure, underlying need and why the explicit request may be insufficient or misleading.

2 1mo ago A 0 tokens

babysit

02

richardwu/agent-skills

Skill Claude CodeCodex

Fix issues on the current PR: address bot (eg Claude Code, CodeRabbit, or custom GHA) review comments and fix failing CI checks. Use when asked to fix PR, fix review comments, fix CI, or fix checks. Triggers on: fix pr, fix review, fix ci, fix checks, fix failing checks.

2 1mo ago B 72 tokens

explain-repo

03

richardwu/agent-skills

Skill Claude CodeCodex

Explain a code repository at three levels of depth. Use when asked to explain a repo, summarize how a codebase is built, create an architecture walkthrough, onboard someone to a project, produce component interaction diagrams, or make a developer/coding agent "dangerous enough" to contribute meaningfully.

2 1mo ago A 64 tokens

multi-agent-review

04

richardwu/agent-skills

Skill Claude CodeCodex

Multi-agent code review using 3 parallel subagents (Claude, GPT, Gemini) to review branch changes against origin/main. Validates findings against actual diffs and posts consolidated report to GitHub PR. Use before opening a PR, when wanting multiple AI perspectives on code changes, or for large changesets that might…

2 1mo ago A 103 tokens

multi-review-claude

05

richardwu/agent-skills

Agent

Architecture and design focused code reviewer. Evaluates how changes fit into the larger system, identifies structural issues, coupling problems, and missed abstractions.

2 1mo ago A 35 tokens

multi-review-gemini

06

richardwu/agent-skills

Agent

Security, performance, and production readiness focused code reviewer. Checks for vulnerabilities, performance regressions, test coverage gaps, and operational concerns.

2 1mo ago A 33 tokens

multi-review-gpt

07

richardwu/agent-skills

Agent

Correctness and edge case focused code reviewer. Hunts for bugs, logic errors, race conditions, and failure modes that pass tests but break in production.

2 1mo ago A 35 tokens

prd

08

richardwu/agent-skills

Skill Claude CodeCodex

Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

2 1mo ago A 60 tokens

ralph

09

richardwu/agent-skills

Skill Claude CodeCodex

Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.

2 1mo ago A 64 tokens

review-prd

10

richardwu/agent-skills

Skill Claude CodeCodex

Review and verify that a Ralph PRD's user stories have been implemented correctly. Reads prd.json, steps through each user story's acceptance criteria, runs tests, checks code, and uses browser verification. Produces a pass/gap/untestable summary. Triggers on: review prd, verify prd, check ralph requirements, review…

2 1mo ago A 89 tokens