$ loading_
Stage, commit, push, and open a GitHub pull request in one flow.
The material indicates a prompt-only skill that describes a Git/GitHub workflow and does not itself declare secrets, remote endpoints, or a standalone executable component. While it guides a host agent to perform git/gh actions that may push code to GitHub, its open-source nature and strong community adoption keep the overall risk low; the main consideration is what repository permissions the host environment actually grants.
The material states that the skill itself requires no environment variables or secrets; the README only expects an already authenticated GitHub CLI session in the host environment. Credential exposure risk mainly comes from the host's existing gh login state, not from the skill collecting, storing, or exfiltrating credentials itself.
The system checks indicate no standalone remote endpoint; the documented network activity is limited to git/gh interactions with GitHub repositories and pull requests, which is directly aligned with the stated purpose. There is no sign of sending data to unknown or unrelated third-party endpoints.
This item is marked as prompt-only and is not itself an executable binary or MCP service. Although the README instructs a host agent to run git and gh commands, this is an openly auditable workflow description with no evidence of unusual system privileges or covert execution beyond its stated code-submission flow.
The documented access scope is mainly the current Git repository contents, status, and PR template files for the stage/commit/push/PR workflow; it does not claim access to arbitrary system directories, browser data, or unrelated sensitive resources. The data touchpoints are broadly consistent with its stated purpose.
The source is the open-source openai/skills repository on GitHub, making the material auditable, and its roughly 22k stars provide a strong positive signal of community adoption. Although the license is not stated and maintenance status is unknown, those factors alone do not constitute a high-risk supply-chain red flag.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "yeet" skill from askskill: 1. Download https://raw.githubusercontent.com/openai/skills/main/skills/.curated/yeet/SKILL.md 2. Save it as ~/.claude/skills/yeet/SKILL.md 3. Reload skills and tell me it's ready
gh. Check gh --version. If missing, ask the user to install gh and stop.gh session. Run gh auth status. If not authenticated, ask the user to run gh auth login (and re-run gh auth status) before continuing.{description} when starting from main/master/default.{description} (terse).{description} summarizing the full diff.Before creating the PR, resolve the repository root and look for the active GitHub PR template from there:
repo_root="$(git rev-parse --show-toplevel)"
Template candidates, in order:
.github/pull_request_template.md.github/PULL_REQUEST_TEMPLATE.md*.md file under .github/pull_request_template/*.md file under .github/PULL_REQUEST_TEMPLATE/Use paths as emitted from the repository root, such as .github/pull_request_template.md, not ./.github/pull_request_template.md.
If exactly one template is found, read it before composing the final PR body and pass it to gh pr create with --template "$template".
If multiple template files are found, stop before PR creation and ask which template to use. If no template exists, use the fallback body shape in this skill.
git checkout -b "{description}"git status -sb then git add -A.git commit -m "{description}"git push -u origin $(git branch --show-current)gh pr view "$(git branch --show-current)" --json number,isDraft,urlGH_PROMPT_DISABLED=1 GIT_TERMINAL_PROMPT=0 gh pr create --draft --fill --template "$template" --head "$(git branch --show-current)"GH_PROMPT_DISABLED=1 GIT_TERMINAL_PROMPT=0 gh pr create --draft --fill --head "$(git branch --show-current)"--body-file or gh pr edit --body-file to avoid \n-escaped markdown.When updating a PR created earlier in the flow, infer the PR from the current branch when possible:
git branch --show-current
gh pr view "$(git branch --show-current)" --json number --jq '.number'
If this finds an existing PR, preserve its current review state. Never convert an existing ready-for-review PR back to draft as part of yeet; only new PRs created by this flow should start as draft.
Format: <type>(<scope>): <subject>
<scope> is optional. A scope consist of a noun describing a section of the codebase (component, service or subsytem).
feat: add hat wobble
^--^ ^------------^
| |
| +-> Summary in present tense.
|
+-------> Type: chore, docs, feat, fix, refactor, style, or test.
More Examples:
feat: (new feature for the user, not a new feature for build script)fix: (bug fix for the user, not a fix to a build script)docs: (changes to the documentation)style: (formatting, missing semi colons, etc; no production code change)refactor: (refactoring production code, eg. renaming a variable)test: (adding missing tests, refactoring tests; no production code change)…
Generate custom design system rules for your codebase and Figma-to-code workflow.
Turn code or page descriptions into full Figma screens using design systems.
Research across Notion sources and produce cited, structured briefs and reports.
Find official OpenAI docs with citations for model choice and prompt upgrades.
Inspect Sentry issues, events, and recent production error health read-only.
Map Figma design components to code components for consistent implementation.
Create commits for code changes with AI-generated messages matching repo style.
Finalize completed work by committing, pushing, and opening reviewed pull requests.
Create a pull request from the current session's code changes.
Create a draft pull request from the current session’s code changes.
Generate Fluid-style PR content, push branches, and open GitHub pull requests.
Connect AI to GitHub to manage repos, issues, PRs, and workflows.