PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Upload screenshots or images to GitHub and get back embeddable URLs for PR comments and issues.
Apache-2.0Auto-check passed
Install Upload Screenshot
$ npx skills add openshift-eng/ai-helpers --skill upload-screenshot -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openshift-eng/ai-helpers upload-screenshot --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/openshift-eng/ai-helpers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/github/skills/upload-screenshot .claude/skills/upload-screenshot && 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 "upload-screenshot" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/github/skills/upload-screenshot into .claude/skills/upload-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "upload-screenshot", 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/openshift-eng/ai-helpers/tree/main/plugins/github/skills/upload-screenshotType 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 openshift-eng/ai-helpers --skill upload-screenshot -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openshift-eng/ai-helpers upload-screenshot --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/github/skills/upload-screenshot .agents/skills/upload-screenshot && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "upload-screenshot" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/github/skills/upload-screenshot into .agents/skills/upload-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "upload-screenshot", 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 openshift-eng/ai-helpers --skill upload-screenshot -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openshift-eng/ai-helpers upload-screenshot --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/github/skills/upload-screenshot .cursor/skills/upload-screenshot && 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 "upload-screenshot" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/github/skills/upload-screenshot into .cursor/skills/upload-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "upload-screenshot", 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/openshift-eng/ai-helpers.git --path plugins/github/skills/upload-screenshot--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 openshift-eng/ai-helpers --skill upload-screenshot -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openshift-eng/ai-helpers upload-screenshot --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/github/skills/upload-screenshot .gemini/skills/upload-screenshot && 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 "upload-screenshot" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/github/skills/upload-screenshot into .gemini/skills/upload-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "upload-screenshot", 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 openshift-eng/ai-helpers upload-screenshotInstalls 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 openshift-eng/ai-helpers --skill upload-screenshot -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/github/skills/upload-screenshot .github/skills/upload-screenshot && 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 "upload-screenshot" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/github/skills/upload-screenshot into .github/skills/upload-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "upload-screenshot", 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 openshift-eng/ai-helpers --skill upload-screenshot -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install openshift-eng/ai-helpers upload-screenshot --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openshift-eng/ai-helpers.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/github/skills/upload-screenshot .opencode/skills/upload-screenshot && 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 "upload-screenshot" agent skill from https://github.com/openshift-eng/ai-helpers/tree/main/plugins/github/skills/upload-screenshot into .opencode/skills/upload-screenshot/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "upload-screenshot", 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
upload-screenshot- GitHub stars
- 120
- Token cost
- ~1.3k tokens
- SKILL.md length
- 504 words
- Files
- 2
- Skills in repo
- 118
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Upload screenshots or images to GitHub and get back embeddable URLs for PR comments and issues.
- Works in 2 steps: gh CLI: Authenticated with gh auth login → Repository write access: The gh token…
- SKILL.md covers When to Use This Skill, Prerequisites, Implementation and How It Works, plus 4 more sections
- Runs Shell scripts from its folder; calls gh, bash and jq; reaches github.com; needs GITHUB_TOKEN and GH_FORK_TOKEN
What it does
Upload Screenshot is an agent skill from openshift-eng/ai-helpers. Upload screenshots or images to GitHub and get back embeddable URLs for PR comments and issues. Use this when you have taken a screenshot, captured a UI change, or have any image file that needs to be shared in a GitHub PR or issue.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `upload_screenshot.sh`).
It works with GitHub. The repository describes itself as: Developer productivity tools for Claude Code & other AI assistants. The licence is Apache-2.0.
Example prompts
- “/upload-screenshot”
Requirements
- A Bash shell
- A credential in GITHUB_TOKEN
- A credential in GH_FORK_TOKEN
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- gh CLI: Authenticated with gh auth login
- Repository write access: The gh token must have permission to create releases on the target repo
What it can do on your machine
Read from SKILL.md and the folder at commit a627176. 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 script files (Shell), which the agent can run.
Shell commands in SKILL.md call:
ghbashjq
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
github.com
Also links to:
docs.github.comcli.github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
GITHUB_TOKENGH_FORK_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Upload Screenshot loads about 1.3k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 504 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
The full file from openshift-eng/ai-helpers at commit a627176, republished under its Apache-2.0 licence (© openshift-eng). 504 words, ~1,305 tokens.
Download SKILL.mdSave it as
.claude/skills/upload-screenshot/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- upload-screenshot
- description
- Upload screenshots or images to GitHub and get back embeddable URLs for PR comments and issues. Use this when you have taken a screenshot, captured a UI change, or have any image file that needs to be shared in a GitHub PR or issue.
Upload Screenshot
Upload images to GitHub via release assets and get back stable, embeddable URLs. This is the recommended way to share screenshots of frontend changes, UI diffs, or any visual artifacts in PR comments and issue descriptions.
Important: Always upload to the fork repo, not upstream, to avoid polluting upstream releases.
When to Use This Skill
Use this skill when you:
- Have taken a screenshot of a frontend/UI change and need to show it in a PR
- Need to attach visual evidence (error screenshots, UI comparisons) to a GitHub issue or PR comment
- Want to embed an image in any GitHub markdown context (PR description, comment, issue)
- Are working in an agentic workflow and need to share visual output
Prerequisites
ghCLI: Authenticated withgh auth login- Repository write access: The
ghtoken must have permission to create releases on the target repo
Implementation
Upload a screenshot
bash "${CLAUDE_PLUGIN_ROOT}/skills/upload-screenshot/upload_screenshot.sh" \
--file /path/to/screenshot.png \
--repo owner/fork-repoUpload with a custom title
bash "${CLAUDE_PLUGIN_ROOT}/skills/upload-screenshot/upload_screenshot.sh" \
--file /path/to/screenshot.png \
--repo owner/fork-repo \
--title "Login page after dark mode changes"Parameters
| Parameter | Required | Description |
|---|---|---|
--file | Yes | Path to the image file (png, jpg, gif, svg, webp) |
--repo | No | Target GitHub repository in owner/repo format (defaults to $FORK_REPO env var) |
--title | No | Alt text for the image (defaults to filename) |
--token-file | No | Path to a file containing a GitHub token to use for auth |
When --token-file is provided, the token is loaded into GITHUB_TOKEN for the duration of the script. This is useful in CI where the default GITHUB_TOKEN may not have write access to the target repo.
Environment variable defaults: If --repo is not provided, the script uses $FORK_REPO. If no explicit token is provided via --token-file, the script uses $GH_FORK_TOKEN when available. This means in CI environments where these env vars are set, you can call the script with just --file and it will upload to the correct fork with the right credentials.
Output
JSON on stdout:
{
"url": "https://github.com/owner/fork-repo/releases/download/screenshot-1719100000-a1b2c3d4/screenshot.png",
"markdown": "",
"tag": "screenshot-1719100000-a1b2c3d4",
"repo": "owner/fork-repo"
}Show full SKILL.md (201 more words)Show less
Embedding in a PR comment
After uploading, use the markdown field directly in a gh pr comment:
result=$(bash "${CLAUDE_PLUGIN_ROOT}/skills/upload-screenshot/upload_screenshot.sh" \
--file /tmp/screenshot.png --repo owner/fork-repo --title "UI change")
markdown=$(echo "$result" | jq -r '.markdown')
gh pr comment 123 --repo owner/upstream-repo --body "## Screenshot
$markdown"How It Works
- Creates a GitHub prerelease with a unique tag (
screenshot-<timestamp>-<random>) - Attaches the image file as a release asset
- Extracts the
browser_download_urlfrom the GitHub API - Returns the URL in both raw and markdown-formatted forms
The release is marked as a prerelease and tagged with a screenshot- prefix for easy identification and cleanup.
Cleanup
Screenshot releases accumulate over time. To clean up old uploads:
# Delete a specific screenshot release
gh release delete screenshot-1719100000-a1b2c3d4 --yes --cleanup-tag --repo owner/fork-repo
# Delete all screenshot releases older than 30 days
gh api "repos/owner/fork-repo/releases" --paginate --jq \
'.[] | select(.tag_name | startswith("screenshot-")) | select(.prerelease) | .tag_name' | \
while read -r tag; do
gh release delete "$tag" --yes --cleanup-tag --repo owner/fork-repo
doneLimitations
- URLs are only accessible as long as the release exists
- For private repos, viewers must have repo access to see the images
- GitHub release asset size limit is 2 GB per file
- Creates one release per upload (use cleanup to manage volume)
Error Handling
| Error | Cause | Resolution |
|---|---|---|
Missing required arguments | --file or --repo not provided | Provide both required arguments |
File not found | Image path doesn't exist | Check the file path |
Failed to create release | Auth or permission issue | Run gh auth login or check repo access |
Failed to retrieve asset URL | Release created but asset missing | Retry; the release is auto-cleaned on failure |
See Also
- GitHub Releases API: https://docs.github.com/en/rest/releases
gh release createdocs: https://cli.github.com/manual/gh_release_create
© openshift-eng, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in plugins/github/skills/upload-screenshot of openshift-eng/ai-helpers.
- SKILL.md
- upload_screenshot.sh
Open the folder on GitHubat commit a627176
Compare with similar skills
Upload Screenshot 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 |
|---|---|---|---|---|---|---|
| Upload Screenshot this skillopenshift-eng/ai-helpers | 120 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Diagnosing Superpowers Sessionsobra/superpowers | 296k | 3 repos | ~1.7k | Automated safety check: Pass | MIT | |
| GitHub Deep Researchbytedance/deer-flow | 83k | 5 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Greplooponyx-dot-app/onyx | 32k | 4 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Update V8 Versionopeninterpreter/openinterpreter | 69k | 2 repos | ~845 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Diagnosing Superpowers Sessions
obra/superpowers
Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.
GitHub Deep Research
bytedance/deer-flow
Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
Update V8 Version
openinterpreter/openinterpreter
Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.
Last30days
mvanhorn/last30days-skill
Research what people actually say about any topic in the last 30 days.
More from openshift-eng/ai-helpers
All 118 skills in this repoInvestigate CI Reliability
openshift-eng/ai-helpers
Find and independently validate actionable reliability defects across OpenShift release jobs and presubmits, then export portable issue handoffs.
Address Review PR
openshift-eng/ai-helpers
Fetch and address all PR review comments — categorize by priority, make code changes, post replies, and push.
Categorize Activity Types
openshift-eng/ai-helpers
Categorize Jira issues into Red Hat Sankey Activity Type categories using MCP Jira tools.
Has Review Work
openshift-eng/ai-helpers
Decide whether a GitHub PR has unanswered authorized review comments or new required CI failures worth a follow-up agent.
Must Gather Analyzer
openshift-eng/ai-helpers
Analyze OpenShift must-gather diagnostic data including cluster operators, pods, nodes, and network components.
Payload Autodl JSON
openshift-eng/ai-helpers
Schema for the autodl JSON data file produced by payload-analysis for database ingestion — you must use this skill whenever generating the autodl JSON file
Related
Works with
Questions about Upload Screenshot
What does Upload Screenshot do?
Upload screenshots or images to GitHub and get back embeddable URLs for PR comments and issues. Upload Screenshot is an agent skill from openshift-eng/ai-helpers. Upload screenshots or images to GitHub and get back embeddable URLs for PR comments and issues.
How do I install Upload Screenshot in Claude Code?
Run `npx skills add openshift-eng/ai-helpers --skill upload-screenshot -a claude-code`. Or copy the skill folder (plugins/github/skills/upload-screenshot in openshift-eng/ai-helpers) into .claude/skills/upload-screenshot in your project. Claude Code loads it when a task matches its description.
How do I install Upload Screenshot in Codex?
Run `npx skills add openshift-eng/ai-helpers --skill upload-screenshot -a codex`. Or copy the skill folder (plugins/github/skills/upload-screenshot in openshift-eng/ai-helpers) into .agents/skills/upload-screenshot in your project. Codex loads it when a task matches its description.
Can I use Upload Screenshot 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 openshift-eng/ai-helpers --skill upload-screenshot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/upload-screenshot, .gemini/skills/upload-screenshot, .github/skills/upload-screenshot and .opencode/skills/upload-screenshot in your project.
What does Upload Screenshot need to run?
Going by SKILL.md and its folder, Upload Screenshot needs a shell for the scripts in its folder, the command-line tools its instructions call (gh, bash and jq) and credentials named GITHUB_TOKEN and GH_FORK_TOKEN. Our summary lists: A Bash shell; A credential in GITHUB_TOKEN; A credential in GH_FORK_TOKEN.
Does Upload Screenshot access the network?
SKILL.md names 3 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: docs.github.com and cli.github.com. This is read from the text; nothing was executed.
Is Upload Screenshot 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 Upload Screenshot use?
Upload Screenshot is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Upload Screenshot use?
About 1.3k tokens (SKILL.md is roughly 5.2k 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 Upload Screenshot?
Skills that share tags, products or a category with Upload Screenshot: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Diagnosing Superpowers Sessions (obra/superpowers, 296k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars) and Greploop (onyx-dot-app/onyx, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Upload Screenshot?
openshift-eng (a GitHub organization) maintains it in openshift-eng/ai-helpers, which has 120 GitHub stars. The repository holds 118 skills in this directory. The repository was last updated on October 6, 2026.
Source: openshift-eng/ai-helpers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.