compozy

172 mods across 4 repositories, 2.9k stars between them.

git-rebase

49

compozy/compozy

Skill Claude CodeCodex

Intelligently handle git rebase operations and resolve merge conflicts while preserving features and maintaining code quality. Use when rebasing feature branches, resolving conflicts across commits, and ensuring clean linear history without losing changes. Don't use for merge-commit workflows, cherry-picking…

2.7k 2d ago A 64 tokens original MIT

golang-master

50

compozy/compozy

Skill Claude CodeCodex

Go engineering doctrine for writing and reviewing production Go — errors, concurrency, safety, types, tests, performance. Use when wrapping or matching errors, spawning goroutines or picking channel vs mutex vs atomic, propagating context and cancellation, designing interfaces or generics, naming and structuring…

2.7k 2d ago A 128 tokens original MIT

grill-me

51

compozy/compozy

Skill Claude CodeCodex

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

2.7k 2d ago A 49 tokens copy · 92% MIT

handoff

52

compozy/compozy

Skill Claude CodeCodex

Compact the current conversation into a handoff document for another agent to pick up.

2.7k 2d ago A 19 tokens copy · 88% MIT

herdr-orchestration

53

compozy/compozy

Skill Claude CodeCodex

Orchestrate Claude and Codex worker TUIs from a controller agent — one worker per named herdr tab, driven over the herdr socket CLI.

2.7k 2d ago A 37 tokens original MIT

humanizer

54

compozy/compozy

Skill Claude CodeCodex

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…

2.7k 2d ago A 111 tokens copy · 83% MIT

impeccable

55

compozy/compozy

Skill Claude CodeCodex

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…

2.7k 2d ago A 189 tokens copy · 95% MIT

improve-react

56

compozy/compozy

Skill Claude CodeCodex

Survey a whole React codebase as a senior React engineer, using React Doctor's scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to…

2.7k 2d ago B 125 tokens original MIT

lesson-learned

57

compozy/compozy

Skill Claude CodeCodex

Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to extract principles from recent work.

2.7k 2d ago A 64 tokens original MIT

mermaid-diagrams

58

compozy/compozy

Skill Claude CodeCodex

Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes…

2.7k 2d ago A 143 tokens original MIT

next-best-practices

59

compozy/compozy

Skill Claude CodeCodex

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling.

2.7k 2d ago A 38 tokens copy · 100% MIT

no-workarounds

60

compozy/compozy

Skill Claude CodeCodex

Fix problems at their root cause instead of patching symptoms. Use when debugging, fixing bugs, resolving test failures, planning a solution, or reviewing a change — especially where a fix would silence a signal (type assertion, lint suppression, swallowed error, timing hack, monkey patch) rather than repair its…

2.7k 2d ago A 76 tokens original MIT

adversarial-review

61

compozy/kb

Skill Claude CodeCodex

Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. Triggers: "adversarial review".

101 12d ago A 56 tokens copy · 89% MIT

compozy/kb

Skill Claude CodeCodex

Deep architectural audit focused on finding dead code, duplicated functionality, architectural anti-patterns, type confusion, and code smells. Use when user asks for architectural analysis, find dead code, identify duplication, or assess codebase health.

101 12d ago A 49 tokens original MIT

brainstorming

63

compozy/kb

Skill Claude CodeCodex

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

101 12d ago A 37 tokens copy · 100% MIT

compozy

64

compozy/kb

Skill Claude CodeCodex

Explains Compozy capabilities, CLI commands, core workflow skills, optional extension skills, configuration, artifact structure, reusable agents, and extensions. Use when the user asks how to use Compozy, what commands are available, how the workflow pipeline works, or how to configure a workspace. Do not use for…

101 12d ago A 79 tokens original MIT

cy-create-prd

65

compozy/kb

Skill Claude CodeCodex

Creates a Product Requirements Document through interactive brainstorming with parallel codebase and web research. Use when starting a new feature or product, building a PRD, or brainstorming requirements. Do not use for technical specifications, task breakdowns, or code implementation.

101 12d ago A 54 tokens original MIT

cy-create-tasks

66

compozy/kb

Skill Claude CodeCodex

Decomposes PRDs and TechSpecs into detailed, independently implementable task files with enrichment from codebase exploration. Use when a PRD or TechSpec exists and needs to be broken down into executable tasks, or when task files need enrichment with implementation context. Do not use for PRD creation, TechSpec…

101 12d ago A 74 tokens original MIT

cy-create-techspec

67

compozy/kb

Skill Claude CodeCodex

Creates a Technical Specification by translating PRD business requirements into implementation designs through interactive technical clarification. Use when a PRD exists and needs a technical plan, or when technical architecture decisions need documentation. Do not use for PRD creation, task breakdown, or direct code…

101 12d ago A 59 tokens original MIT

cy-execute-task

68

compozy/kb

Skill Claude CodeCodex

Executes one PRD task end-to-end using a provided task file, PRD directory, tracking file paths, and auto-commit mode. Use when a prompt includes a task specification that must be implemented, validated, and reflected in task tracking files. Do not use for PR review batches, generic coding tasks without a PRD task…

101 12d ago A 80 tokens original MIT

cy-final-verify

69

compozy/kb

Skill Claude CodeCodex

Enforces fresh verification evidence before any completion, fix, or passing claim, and before commits or PR creation. Use when an agent is about to report success, hand off work, or commit code. Do not use for early planning, brainstorming, or tasks that have not yet reached a concrete verification step.

101 12d ago A 66 tokens original MIT

cy-fix-reviews

70

compozy/kb

Skill Claude CodeCodex

Executes provider-agnostic PR review remediation using existing review round files under .compozy/tasks/ /reviews-NNN/. Use when resolving batched review issues, updating issue markdown files, implementing fixes, and verifying the result. Do not use for PRD task execution, review export/fetch, or generic coding tasks…

101 12d ago A 77 tokens original MIT

cy-review-round

71

compozy/kb

Skill Claude CodeCodex

Performs a comprehensive code review of a PRD implementation and generates a review round directory with issue files compatible with cy-fix-reviews. Use when reviewing implemented PRD tasks, creating a manual review round without an external provider, or performing a quality audit of code changes. Do not use for…

101 12d ago A 84 tokens original MIT

cy-workflow-memory

72

compozy/kb

Skill Claude CodeCodex

Maintains workflow-scoped task memory for Compozy runs using .compozy/tasks/ /memory/ files. Use when a task prompt provides workflow memory paths and requires the agent to read, update, compact, and promote durable context across PRD task executions. Do not use for PR review remediation, global user preferences, or…

101 12d ago A 80 tokens original MIT