claudecodex

Universal

Platform-agnostic tools for making good software.

21 on GitHubby Kyle Hughesv1.11.0updated 3 days agoproductivity
/

Plugin universal from marketplace making-good-software in kylehughes/agent-plugins-for-making-good-software. Commands read from the repo's manifest — 3 days ago.

What it installs

Skills (11)

  • graders
  • brainstorming-design-specs

    Develop an implementation-ready design through research and dialogue. Use proactively when product scope, requirements, or engineering tradeoffs remain unresolved; skip specified changes ready to implement.

  • compiling-agent-goals

    Compile specs, plans, or issues into bounded agent goal contracts with acceptance evidence and stopping conditions. Use proactively when preparing a persistent-agent handoff; this authors the contract, not the implementation.

  • delivering-changes

    Carry a requested change through implementation, simplification, hardening, and required checks to a PR-ready handoff. Use proactively when the user delegates end-to-end delivery; preserve narrower requests and project checkpoints.

  • designing-documents

    Organize substantive documents for understanding, decisions, action, and lookup. Use when creating, revising, or reviewing document structure, explanations, onboarding, or findability; preserve constrained edits and useful existing structures.

  • hardening-changes

    Harden owned changes through scoped review and fixes. Use proactively when preparing a change set for a PR or when hardening is requested; read-only review belongs to reviewing-code.

  • reviewing-code

    Review code for concrete correctness, security, concurrency, and compatibility defects. Load for every requested review, including a short function, diff, PR, branch, or repository audit. Keep review-only requests read-only.

  • simplifying-code

    Simplify existing code while preserving behavior. Use proactively for requested cleanup, deduplication, local refactoring, or simplification review; preserve read-only review scope. Ordinary defect review belongs to reviewing-code.

  • verifying-invariants

    Assess whether invalid domain values or states can be constructed, decoded, mutated into, or reached. Use proactively for invariant assessments or enforcement-boundary changes; choose bounded evidence. Skip ordinary output tests and async-test timing.

  • writing-escalation-briefs

    Prepare a standalone expert brief with evidence a reader without repository access needs. Use proactively when debugging stalls or an escalation or expert handoff is requested; skip ordinary first-pass debugging and direct reviews.

  • writing-technical-prose

    Write, edit, review, and normalize developer documentation, API comments, READMEs, design docs, runbooks, and PR descriptions. Use proactively for technical prose that needs accurate claims, clear structure, or consistent voice.

Subagents (4)

  • code-reviewer

    Review structural design and architecture fit. Use PROACTIVELY when reviewing changes for pattern drift or misplaced responsibilities. Defer correctness defects, codified rules, and prose.

  • code-simplifier

    Find behavior-preserving simplifications and reuse in any language. Use PROACTIVELY after changes that add complexity, duplication, or redundant state. Defer correctness and architecture review; report without editing.

  • correctness-reviewer

    Review correctness, security, concurrency, compatibility, and performance defects. Use PROACTIVELY when assessing a diff, PR, or branch for merge readiness. Defer structural design, codified style, and prose.

  • technical-writing-auditor

    Audit developer documentation for accuracy, reader usefulness, structure, and voice. Use PROACTIVELY after docs or API-comment changes. Defer architecture and code defects; report without editing.

View source on GitHub

More from kylehughes/agent-plugins-for-making-good-software

All 2 plugins →

Apple Platform

claudecodex

Tools for making good software on Apple platforms.

20 skills · 4 agents

21

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain Universal?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins