compozy/kb

101Stars on the repository
32Mods indexed here, across every type
12d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

adversarial-review

01

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

03

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

04

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

05

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

06

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

07

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

08

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

09

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

10

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

11

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

12

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

exa-web-search-free

13

compozy/kb

Skill Claude CodeCodex

Free AI search via Exa MCP. Web search for news/info, code search for docs/examples from GitHub/StackOverflow, company research for business intel. No API key needed.

101 12d ago B 42 tokens copy · 100% MIT

compozy/kb

Skill Claude CodeCodex

Profile-driven performance optimization with behavior proofs. Use when: optimize, slow, bottleneck, hotspot, profile, p95, latency, throughput, or algorithmic improvements.

101 12d ago A 41 tokens copy · 100% MIT

find-skills

15

compozy/kb

Skill Claude CodeCodex

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

101 12d ago A 67 tokens copy · 91% MIT

git-rebase

16

compozy/kb

Skill Claude CodeCodex

Resolve Git merge and rebase conflicts conservatively, preserving both sides' intent, staging only understood resolutions, and leaving a git-clean conflict state.

101 12d ago A 33 tokens original MIT

golang-pro

17

compozy/kb

Skill Claude CodeCodex

Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with generics, interfaces, and robust error handling. Use when building Go applications requiring concurrent programming…

101 12d ago A 95 tokens copy · 91% MIT

grilling

18

compozy/kb

Skill Claude CodeCodex

Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.

101 12d ago A 36 tokens copy · 100% MIT

handoff

19

compozy/kb

Skill Claude CodeCodex

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

101 12d ago A 19 tokens copy · 84% MIT

impl-peer-review

20

compozy/kb

Skill Claude CodeCodex

Runs an optional cross-LLM peer review of an implemented change (the diff) via compozy exec and requires the reviewer to write one scoped Markdown findings artifact for user-directed remediation. The reviewer runtime is configurable through --ide / --model / --reasoning (defaults claude / opus / xhigh) and the…

101 12d ago A 213 tokens original MIT

kb-yt-channel

21

compozy/kb

Skill Claude CodeCodex

Creates and maintains Knowledge Base topics from YouTube channels by scaffolding a yt-channels topic, bulk-ingesting transcripts through kb ingest channel, and validating/indexing the result. Use when turning a YouTube channel into a Karpathy KB topic. Do not use for single-video ingestion, general video summaries, or…

101 12d ago A 73 tokens original MIT

lesson-learned

22

compozy/kb

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.

101 12d ago A 64 tokens copy · 100% MIT

no-workarounds

23

compozy/kb

Skill Claude CodeCodex

Enforce root-cause fixes over workarounds, hacks, and symptom patches in all software engineering tasks. Use when debugging issues, fixing bugs, resolving test failures, planning solutions, making architectural decisions, or reviewing code changes. Activates gate functions that detect and reject common workaround…

101 12d ago A 92 tokens original MIT

compozy/kb

Skill Claude CodeCodex

Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.

101 12d ago A 54 tokens original MIT