How do I install the Cog Review skill?

Run npx skillmds@latest add replicate/cog-review in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Cog Review skill do?

Cog architecture and cross-cutting review guidelines It is listed under Coding & Dev Tools on SkillMD.

Is Cog Review safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Cog Review?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Cog Review free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Cog Review?

replicate (@replicate) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Cog Review by replicate — Agent Skill

Name: Cog Review
Author: replicate

File contents

Cog architecture review guidelines

Cog packages ML models into production-ready containers. Use this skill for changes that cross language boundaries or touch core architecture.

Component overview

CLI (Go): cmd/cog/ and pkg/ -- builds, runs, and deploys models
Python SDK: python/cog/ -- predictor interface, types, HTTP/queue server
Coglet (Rust): crates/ -- prediction server inside containers (HTTP, worker management, IPC)

Key design patterns

Wheel resolution: The CLI discovers SDK and coglet wheels from dist/ at Docker build time. Wheels are NOT embedded in the binary. Changes to build artifacts need to account for this.

Dockerfile generation: pkg/dockerfile/ generates Dockerfiles from cog.yaml config. Template injection and escaping matter here.

Config parsing: pkg/config/config.go parses cog.yaml. Schema is at pkg/config/data/config_schema_v1.0.json. Changes must keep schema and Go code in sync.

Two-process coglet: Parent process (HTTP server + orchestrator) and child worker process (Python predictor execution) communicate via IPC. Changes to the IPC protocol affect both Rust and Python code.

Compatibility matrix: CUDA/PyTorch/TensorFlow compatibility is managed in tools/compatgen/. Framework version changes have wide blast radius.

Cross-cutting concerns

VERSION.txt is the single source of truth for versioning. Cargo.toml must match.
Changes to python/cog/base_predictor.py affect all downstream model authors.
Changes to docs/ require running mise run docs:llm to regenerate docs/llms.txt.
CLI reference docs are auto-generated -- changes to cmd/ or pkg/cli/ require mise run docs:cli.
Integration tests in integration-tests/ use Go's testscript and need a built cog binary.

What to watch for

Breaking changes to the predictor interface or cog.yaml schema
Docker build changes that affect layer caching or build time
IPC protocol changes without updating both Rust and Python sides
Version bumps that miss one of the places VERSION.txt needs to match
New ML framework versions without compatibility testing

---name: cog-reviewdescription: Cog architecture and cross-cutting review guidelines---## Cog architecture review guidelinesCog packages ML models into production-ready containers. Use this skill forchanges that cross language boundaries or touch core architecture.### Component overview- **CLI** (Go): `cmd/cog/` and `pkg/` -- builds, runs, and deploys models- **Python SDK**: `python/cog/` -- predictor interface, types, HTTP/queue server- **Coglet** (Rust): `crates/` -- prediction server inside containers (HTTP, worker management, IPC)### Key design patterns**Wheel resolution**: The CLI discovers SDK and coglet wheels from `dist/` atDocker build time. Wheels are NOT embedded in the binary. Changes to buildartifacts need to account for this.**Dockerfile generation**: `pkg/dockerfile/` generates Dockerfiles from `cog.yaml`config. Template injection and escaping matter here.**Config parsing**: `pkg/config/config.go` parses `cog.yaml`. Schema is at`pkg/config/data/config_schema_v1.0.json`. Changes must keep schema and Gocode in sync.**Two-process coglet**: Parent process (HTTP server + orchestrator) and childworker process (Python predictor execution) communicate via IPC. Changes tothe IPC protocol affect both Rust and Python code.**Compatibility matrix**: CUDA/PyTorch/TensorFlow compatibility is managed in`tools/compatgen/`. Framework version changes have wide blast radius.### Cross-cutting concerns- **VERSION.txt** is the single source of truth for versioning. `Cargo.toml` must match.- Changes to `python/cog/base_predictor.py` affect all downstream model authors.- Changes to `docs/` require running `mise run docs:llm` to regenerate `docs/llms.txt`.- CLI reference docs are auto-generated -- changes to `cmd/` or `pkg/cli/` require `mise run docs:cli`.- Integration tests in `integration-tests/` use Go's testscript and need a built cog binary.### What to watch for- Breaking changes to the predictor interface or cog.yaml schema- Docker build changes that affect layer caching or build time- IPC protocol changes without updating both Rust and Python sides- Version bumps that miss one of the places VERSION.txt needs to match- New ML framework versions without compatibility testing

Frequently asked questions

Cog Review