build-models agent skill by replicate
Packages and builds custom AI models with Cog for deployment on Replicate, including cog.yaml, predict.py, model inputs and outputs, and Docker images.
At a glance
| Publisher | Replicate Official |
|---|---|
| Repository | replicate/skills (7 listed skills) |
| Category | AI Agents and LLM Engineering |
| License | Apache-2.0 |
| Last commit | June 4, 2026 (repository) |
| SKILL.md | 365 lines, 1,478 words |
| Bundled files | 1 file |
| Quality score | 71/100 · C Passes all seven graded checks |
| Security scan | Not scanned |
| README badge | Get the listing badge and raise the score |
Before you install
Read from the skill's files at the directory's October 19, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.
- Bundled scripts: none.
- License: Apache-2.0, an open-source or open-content license.
Install build-models
The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.
npx skills add https://github.com/replicate/skills/tree/main/skills/build-modelstmp="$(mktemp -d)"
git clone --depth 1 https://github.com/replicate/skills.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"skills/build-models .claude/skills/
rm -rf "$tmp"python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
--repo replicate/skills \
--path skills/build-modelsreplicate/skills is third-party code. Read SKILL.md and any bundled scripts before you install it.
How the author describes it
Package and build custom AI models with Cog for deployment on Replicate. Use when creating a cog.yaml or predict.py, defining model inputs and outputs, loading model weights at setup time, building Docker images for ML models, serving locally with cog serve or cog predict, or porting a HuggingFace, GitHub, or ComfyUI model to run on Replicate. Trigger on phrases like "build a model", "package a model", "create a Cog model", "wrap a model", "containerize an AI model", "predict.py", "cog.yaml", "BasePredictor", or "Cog container", and when referencing cog.run, github.com/replicate/cog, or github.com/replicate/cog-examples. Covers GPU and CUDA setup, pget for fast weight downloads, async predictors with continuous batching, streaming outputs, and cold-boot optimization for image, video, audio, and LLM models. For pushing built models to Replicate, see publish-models. For running existing models, see run-models.
From the description field of SKILL.md. Agents read this line to decide when to load the skill.
Sections in SKILL.md
- Docs
- When to use this skill
- Prerequisites
- Project layout
- cog.yaml essentials
- predict.py essentials
- Loading weights fast
- 1. Bake weights into the image at build time
- 2. Pull from weights.replicate.delivery with pget
- 3. HuggingFace Hub with hftransfer
- Weight cache for user-supplied weights
- Multi-LoRA composition
- Cold-boot tricks
- Local development
- Building
- Training
Files in the skill folder
SKILL.md
Suede Skill Check: 71/100 · C
Report snapshot · · graded-v2
The rubric totals 100 points; published scores are capped at 99. Security scan: not scanned.
Source revision: 2f36e415965a. Report version cd65e6bff4c5. Badge URLs follow the latest listing; save the report to keep this version.
Download report · Request a fresh review
What to review next
- Recent maintenance: 3 of 9 points. 9 for a repository commit within 30 days of the snapshot; 6 within 90; 3 within 180; 1 within 365.
- Description length: 1 of 5 points. 5 for 150–600 characters; 3 for 100–900; 1 for 50–1,024.
- Boundary clause: 0 of 4 points. 4 when the description says when not to use the skill (“Not for …”, “Do not use …”, “Use … instead”).
Add declarations and bundled files when they describe the skill’s actual needs. Update the source, then request a fresh review with the changed commit or PR.
build-models passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.
See the checks and points
| Check | Result |
|---|---|
| Frontmatter parses and declares a name and a description | Pass |
| Name uses lowercase letters, digits and hyphens, 64 characters or fewer | Pass |
| Name matches the skill's folder name | Pass |
| Description is between 50 and 1,024 characters | Pass |
| Description says when an agent should use the skill | Pass |
| SKILL.md body is 500 lines or fewer | Pass |
| A license is declared in the frontmatter or the repository | Pass |
| Repository has a commit in the last 12 months | Pass |
| Score component | Points |
|---|---|
| Structural checks | 56 of 56 |
| Description length | 1 of 5 |
| Boundary clause | 0 of 4 |
| Example request | 3 of 3 |
| Instruction depth | 7 of 7 |
| Reference files | 0 of 3 |
| Bundled scripts | 0 of 2 |
| Recent maintenance | 3 of 9 |
| Curated-list citations | 1 of 7 |
| Tool permissions declared | 0 of 2 |
| Compatibility declared | 0 of 2 |
Show the listing and raise the score
build-models is listed with 71/100 · C. This badge links to its Suede listing. Skills scoring 80–99 add a numeric and a letter quality shield; the largest open points for build-models are recent maintenance (6), boundary clause (4) and description length (4). Send your repository and the points you want to raise, then request a fresh review after updating the skill.
[](https://skills.suedeai.ai/directory/replicate/skills/build-models/)<a href="https://skills.suedeai.ai/directory/replicate/skills/build-models/"><img src="https://skills.suedeai.ai/directory/badge.svg" alt="Suede Skills Directory: listed" height="20"></a>Where this skill is cited
replicate/skills appears in 1 curated list: heilcheng/awesome-agent-skills.