Worktree Env Setup
meta-pytorch/attention-gym
Sets up an isolated per-worktree Python environment for attention-gym development using nightly PyTorch and the CI-mirroring uv flow.
Compare codegen output (.pto files and pass dumps) between origin/main and the current branch for a given test case.
Install Compare Codegen
$ npx skills add hw-native-sys/pypto --skill compare-codegen -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hw-native-sys/pypto compare-codegen --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/hw-native-sys/pypto.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/compare-codegen .claude/skills/compare-codegen && 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 "compare-codegen" agent skill from https://github.com/hw-native-sys/pypto/tree/main/.claude/skills/compare-codegen into .claude/skills/compare-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-codegen", 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/hw-native-sys/pypto/tree/main/.claude/skills/compare-codegenType 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 hw-native-sys/pypto --skill compare-codegen -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hw-native-sys/pypto compare-codegen --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hw-native-sys/pypto.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/compare-codegen .agents/skills/compare-codegen && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "compare-codegen" agent skill from https://github.com/hw-native-sys/pypto/tree/main/.claude/skills/compare-codegen into .agents/skills/compare-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-codegen", 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 hw-native-sys/pypto --skill compare-codegen -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hw-native-sys/pypto compare-codegen --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hw-native-sys/pypto.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/compare-codegen .cursor/skills/compare-codegen && 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 "compare-codegen" agent skill from https://github.com/hw-native-sys/pypto/tree/main/.claude/skills/compare-codegen into .cursor/skills/compare-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-codegen", 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/hw-native-sys/pypto.git --path .claude/skills/compare-codegen--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 hw-native-sys/pypto --skill compare-codegen -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hw-native-sys/pypto compare-codegen --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hw-native-sys/pypto.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/compare-codegen .gemini/skills/compare-codegen && 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 "compare-codegen" agent skill from https://github.com/hw-native-sys/pypto/tree/main/.claude/skills/compare-codegen into .gemini/skills/compare-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-codegen", 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 hw-native-sys/pypto compare-codegenInstalls 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 hw-native-sys/pypto --skill compare-codegen -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hw-native-sys/pypto.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/compare-codegen .github/skills/compare-codegen && 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 "compare-codegen" agent skill from https://github.com/hw-native-sys/pypto/tree/main/.claude/skills/compare-codegen into .github/skills/compare-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-codegen", 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 hw-native-sys/pypto --skill compare-codegen -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hw-native-sys/pypto compare-codegen --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hw-native-sys/pypto.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/compare-codegen .opencode/skills/compare-codegen && 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 "compare-codegen" agent skill from https://github.com/hw-native-sys/pypto/tree/main/.claude/skills/compare-codegen into .opencode/skills/compare-codegen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compare-codegen", 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
compare-codegen- GitHub stars
- 125
- Token cost
- ~1.4k tokens
- SKILL.md length
- 377 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Compare codegen output (.pto files and pass dumps) between origin/main and the current branch for a given test case.
- Works in 6 steps: Validate Inputs → Prepare Directories → Run on Current Branch → …
- The user asks to compare codegen output
- SKILL.md covers Prerequisites, Workflow, Cleanup and Troubleshooting
- Runs Python scripts from its folder; calls git, cmake and python
What it does
Compare Codegen is an agent skill from hw-native-sys/pypto. Compare codegen output (.pto files and pass dumps) between origin/main and the current branch for a given test case. Runs the test with --save-kernels and --dump-passes on both branches via git worktree, then diffs the results. Use when the user asks to compare codegen output, diff .pto files between branches, or check what changed in generated code.
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/diff_pto.py`).
It sits in Development, covering Project scaffolding, Git worktrees and Test generation. It works with Git and pytest. The repository describes itself as: A community-driven pypto implementation.
When your agent uses it
- The user asks to compare codegen output
- Diff .pto files between branches
- Check what changed in generated code
Example prompts
- “/compare-codegen”
Requirements
- Python 3
Workflow steps
6 steps, taken from the step headings in SKILL.md.
- Validate Inputs
- Prepare Directories
- Run on Current Branch
- Run on origin/main via git worktree
- Diff the Output
- Report Results
What it can do on your machine
Read from SKILL.md and the folder at commit 5f71449. 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
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
gitcmakepythonpytest
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Compare Codegen loads about 1.4k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 377 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); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 377 words (~1,367 tokens).
“Compare .pto files and pass dump output between origin/main and the current branch for a specific system test case.”
- name
- compare-codegen
Files
SKILL.md and 1 other file (scripts) in .claude/skills/compare-codegen of hw-native-sys/pypto.
- SKILL.md
- scripts/diff_pto.py
Open the folder on GitHubat commit 5f71449
Compare with similar skills
Compare Codegen 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 |
|---|---|---|---|---|---|---|
| Compare Codegen this skillhw-native-sys/pypto | 125 | — | ~1.4k | Automated safety check: Pass | Custom licence | |
| Worktree Env Setupmeta-pytorch/attention-gym | 1.3k | — | ~858 | Automated safety check: Pass | BSD-3-Clause | |
| Superset Project Setupsuperset-sh/superset | 15k | — | ~577 | Automated safety check: Notes | Custom licence | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Finishing A Development Branchfarm-fe/farm | 5.6k | 33 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Git Worktree Cleanuplobehub/lobehub | 83k | — | ~2.8k | Automated safety check: Pass | Custom licence |
Similar skills
Superset Project Setup
superset-sh/superset
Makes a repository Superset-ready by writing .superset/config.json with setup, teardown and run scripts, then proving it with a real throwaway workspace.
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Finishing A Development Branch
farm-fe/farm
A skill your agent uses when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for…
Git Worktree Cleanup
lobehub/lobehub
Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.
Skyvern Version Bump
Skyvern-AI/skyvern
Walks through a Skyvern open-source release bump: update the version, rebuild the Python and TypeScript SDKs with Fern, commit, and open a pull request.
More from hw-native-sys/pypto
Add Op
hw-native-sys/pypto
Add new operator definitions to PyPTO across all layers (C++, Python IR, Python DSL, tests, codegen, docs).
Code Review
hw-native-sys/pypto
Review code changes against PyPTO project standards before committing.
Testing
hw-native-sys/pypto
Verify testing coverage and run tests for PyPTO project. An agent skill from hw-native-sys/pypto.
Weekly Changelog
hw-native-sys/pypto
Generate a weekly changelog markdown file summarizing external API and feature changes from git commits in a date range.
Related
Categories
Questions about Compare Codegen
What does Compare Codegen do?
Compare codegen output (.pto files and pass dumps) between origin/main and the current branch for a given test case. Compare Codegen is an agent skill from hw-native-sys/pypto.pto files and pass dumps) between origin/main and the current branch for a given test case.
When should I use Compare Codegen?
Compare Codegen fits situations like: the user asks to compare codegen output; diff .pto files between branches; check what changed in generated code.
How do I install Compare Codegen in Claude Code?
Run `npx skills add hw-native-sys/pypto --skill compare-codegen -a claude-code`. Or copy the skill folder (.claude/skills/compare-codegen in hw-native-sys/pypto) into .claude/skills/compare-codegen in your project. Claude Code loads it when a task matches its description.
How do I install Compare Codegen in Codex?
Run `npx skills add hw-native-sys/pypto --skill compare-codegen -a codex`. Or copy the skill folder (.claude/skills/compare-codegen in hw-native-sys/pypto) into .agents/skills/compare-codegen in your project. Codex loads it when a task matches its description.
Can I use Compare Codegen 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 hw-native-sys/pypto --skill compare-codegen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compare-codegen, .gemini/skills/compare-codegen, .github/skills/compare-codegen and .opencode/skills/compare-codegen in your project.
What does Compare Codegen need to run?
Going by SKILL.md and its folder, Compare Codegen needs Python for the scripts in its folder and the command-line tools its instructions call (git, cmake, python and pytest). Our summary lists: Python 3.
Does Compare Codegen access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Compare Codegen 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Compare Codegen use?
Compare Codegen has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Compare Codegen use?
About 1.4k tokens (SKILL.md is roughly 5.5k 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 Compare Codegen?
Skills that share tags, products or a category with Compare Codegen: Worktree Env Setup (meta-pytorch/attention-gym, 1.3k stars), Superset Project Setup (superset-sh/superset, 15k stars), Finishing a Development Branch (obra/superpowers, 296k stars) and Finishing A Development Branch (farm-fe/farm, 5.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Compare Codegen?
hw-native-sys (a GitHub organization) maintains it in hw-native-sys/pypto, which has 125 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 30, 2026.
Source: hw-native-sys/pypto on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.