Scaffold Example
comet-ml/comet-examples
Scaffold a brand-new Comet example in this repo from the canonical template under templates/integration-example/.
Guidance for implementing neural network inference (like GPT-2) under extreme code size constraints.
Install Gpt2 Codegolf
$ npx skills add lazyFrogLOL/Harness_Engineering --skill gpt2-codegolf -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lazyFrogLOL/Harness_Engineering gpt2-codegolf --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/gpt2-codegolf .claude/skills/gpt2-codegolf && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "gpt2-codegolf" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/gpt2-codegolf into .claude/skills/gpt2-codegolf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt2-codegolf", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/gpt2-codegolfType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add lazyFrogLOL/Harness_Engineering --skill gpt2-codegolf -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lazyFrogLOL/Harness_Engineering gpt2-codegolf --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/gpt2-codegolf .agents/skills/gpt2-codegolf && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "gpt2-codegolf" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/gpt2-codegolf into .agents/skills/gpt2-codegolf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt2-codegolf", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lazyFrogLOL/Harness_Engineering --skill gpt2-codegolf -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lazyFrogLOL/Harness_Engineering gpt2-codegolf --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/gpt2-codegolf .cursor/skills/gpt2-codegolf && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "gpt2-codegolf" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/gpt2-codegolf into .cursor/skills/gpt2-codegolf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt2-codegolf", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/lazyFrogLOL/Harness_Engineering.git --path skills/gpt2-codegolf--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add lazyFrogLOL/Harness_Engineering --skill gpt2-codegolf -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lazyFrogLOL/Harness_Engineering gpt2-codegolf --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/gpt2-codegolf .gemini/skills/gpt2-codegolf && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "gpt2-codegolf" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/gpt2-codegolf into .gemini/skills/gpt2-codegolf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt2-codegolf", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install lazyFrogLOL/Harness_Engineering gpt2-codegolfInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add lazyFrogLOL/Harness_Engineering --skill gpt2-codegolf -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/gpt2-codegolf .github/skills/gpt2-codegolf && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "gpt2-codegolf" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/gpt2-codegolf into .github/skills/gpt2-codegolf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt2-codegolf", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add lazyFrogLOL/Harness_Engineering --skill gpt2-codegolf -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lazyFrogLOL/Harness_Engineering gpt2-codegolf --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lazyFrogLOL/Harness_Engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/gpt2-codegolf .opencode/skills/gpt2-codegolf && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "gpt2-codegolf" agent skill from https://github.com/lazyFrogLOL/Harness_Engineering/tree/master/skills/gpt2-codegolf into .opencode/skills/gpt2-codegolf/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt2-codegolf", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
gpt2-codegolf- GitHub stars
- 128
- Token cost
- ~1.8k tokens
- SKILL.md length
- 782 words
- Files
- 1
- Skills in repo
- 32
- Repo updated
- First seen
- Licence
- None found
At a glance
Guidance for implementing neural network inference (like GPT-2) under extreme code size constraints.
- Works in 11 steps: Assess Feasibility Before Coding → Clarify Requirements Immediately → Recognize Impossible Constraints → …
- Tasks that involve Deep learning
- SKILL.md covers Overview, Critical First Steps, Recommended Approach and Verification Strategies, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Gpt2 Codegolf is an agent skill from lazyFrogLOL/Harness_Engineering. Guidance for implementing neural network inference (like GPT-2) under extreme code size constraints. This skill should be used when tasks require implementing ML model inference in minimal code (code golf), parsing model checkpoints in constrained environments, or building transformer architectures in low-level languages like C with strict size limits.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Deep learning and Machine learning.
When your agent uses it
- Tasks that involve Deep learning
- Tasks that involve Machine learning
Example prompts
- “/gpt2-codegolf”
Workflow steps
11 steps, taken from the step headings in SKILL.md.
- Assess Feasibility Before Coding
- Clarify Requirements Immediately
- Recognize Impossible Constraints
- Design Before Implementation
- Incremental Implementation with Testing
- Size Optimization
- Underestimating Checkpoint Complexity
- Claiming Completion Prematurely
- Writing Incomplete Code
- Ignoring BPE Complexity
- Missing Error Handling
What it can do on your machine
Read from SKILL.md and the folder at commit cae3b25. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Gpt2 Codegolf loads about 1.8k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 782 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 782 words (~1,788 tokens).
“This skill provides guidance for implementing neural network inference under extreme code size constraints. Tasks in this category typically require implementing a complete ML model (such as GPT-2) in a minimal amount of code, often in low-level languages like C…”
- name
- gpt2-codegolf
Files
Just SKILL.md in skills/gpt2-codegolf of lazyFrogLOL/Harness_Engineering.
Open the folder on GitHubat commit cae3b25
Compare with similar skills
Gpt2 Codegolf next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Gpt2 Codegolf this skilllazyFrogLOL/Harness_Engineering | 128 | — | ~1.8k | Automated safety check: Pass | None | |
| Scaffold Examplecomet-ml/comet-examples | 175 | — | ~1k | Automated safety check: Pass | None | |
| Christopher ManningK-Dense-AI/mimeo | 282 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Ian GoodfellowK-Dense-AI/mimeo | 282 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Ilya SutskeverK-Dense-AI/mimeo | 282 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Databricks ML Trainingdatabricks/databricks-agent-skills | 345 | — | ~4.6k | Automated safety check: Pass | Custom licence |
Similar skills
Christopher Manning
K-Dense-AI/mimeo
Applies the reasoning, architectural principles, and AI philosophy of Christopher Manning (natural language processing expert, Stanford University, director of Stanford AI Lab).
Ian Goodfellow
K-Dense-AI/mimeo
A skill your agent uses when reasoning about generative AI, adversarial machine learning, neural network security, algorithmic fairness, or deep learning fundamentals.
Ilya Sutskever
K-Dense-AI/mimeo
Applies the reasoning style of Ilya Sutskever (deep learning pioneer, co-founder of OpenAI and Safe Superintelligence Inc.) to problems involving AI architecture, scaling laws, alignment, and…
- Official
Databricks ML Training
databricks/databricks-agent-skills
Train ML models on Databricks. An agent skill from databricks/databricks-agent-skills.
GPU Optimizer
Mathews-Tom/armory
GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile.
More from lazyFrogLOL/Harness_Engineering
All 32 skills in this repoDistribution Search
lazyFrogLOL/Harness_Engineering
Guidance for finding probability distributions that satisfy specific statistical constraints such as KL divergence targets, entropy requirements, or moment conditions.
Prove Plus Comm
lazyFrogLOL/Harness_Engineering
Guide for completing Coq proofs involving arithmetic properties like addition commutativity.
Raman Fitting
lazyFrogLOL/Harness_Engineering
This skill provides guidance for fitting peaks in Raman spectroscopy data, particularly for materials like graphene.
Chess Best Move
lazyFrogLOL/Harness_Engineering
Guide for analyzing chess positions from images and determining optimal moves.
Crack 7z Hash
lazyFrogLOL/Harness_Engineering
This skill provides guidance for cracking 7z archive password hashes.
Feal Linear Cryptanalysis
lazyFrogLOL/Harness_Engineering
This skill provides guidance for FEAL cipher linear cryptanalysis tasks.
Related
Categories
Questions about Gpt2 Codegolf
What does Gpt2 Codegolf do?
Guidance for implementing neural network inference (like GPT-2) under extreme code size constraints. Gpt2 Codegolf is an agent skill from lazyFrogLOL/Harness_Engineering. Guidance for implementing neural network inference (like GPT-2) under extreme code size constraints.
When should I use Gpt2 Codegolf?
Gpt2 Codegolf fits situations like: tasks that involve Deep learning; tasks that involve Machine learning.
How do I install Gpt2 Codegolf in Claude Code?
Run `npx skills add lazyFrogLOL/Harness_Engineering --skill gpt2-codegolf -a claude-code`. Or copy the skill folder (skills/gpt2-codegolf in lazyFrogLOL/Harness_Engineering) into .claude/skills/gpt2-codegolf in your project. Claude Code loads it when a task matches its description.
How do I install Gpt2 Codegolf in Codex?
Run `npx skills add lazyFrogLOL/Harness_Engineering --skill gpt2-codegolf -a codex`. Or copy the skill folder (skills/gpt2-codegolf in lazyFrogLOL/Harness_Engineering) into .agents/skills/gpt2-codegolf in your project. Codex loads it when a task matches its description.
Can I use Gpt2 Codegolf in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lazyFrogLOL/Harness_Engineering --skill gpt2-codegolf -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gpt2-codegolf, .gemini/skills/gpt2-codegolf, .github/skills/gpt2-codegolf and .opencode/skills/gpt2-codegolf in your project.
What does Gpt2 Codegolf need to run?
SKILL.md names no scripts, command-line tools or credentials: Gpt2 Codegolf is instructions for the agent only.
Does Gpt2 Codegolf access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Gpt2 Codegolf safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Gpt2 Codegolf use?
No licence was found for Gpt2 Codegolf or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Gpt2 Codegolf use?
About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Gpt2 Codegolf?
Skills that share tags, products or a category with Gpt2 Codegolf: Scaffold Example (comet-ml/comet-examples, 175 stars), Christopher Manning (K-Dense-AI/mimeo, 282 stars), Ian Goodfellow (K-Dense-AI/mimeo, 282 stars) and Ilya Sutskever (K-Dense-AI/mimeo, 282 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Gpt2 Codegolf?
lazyFrogLOL (a GitHub user) maintains it in lazyFrogLOL/Harness_Engineering, which has 128 GitHub stars. The repository holds 32 skills in this directory. The repository was last updated on May 18, 2026.
Source: lazyFrogLOL/Harness_Engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.