New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Babysit PR

by ZenUml in ZenUml/web-sequence

Monitor and diagnose GitHub Actions checks on ZenUML web-sequence PRs, fixing code-caused CI failures when appropriate.

MITAuto-check passedTesting & QA

Install Babysit PR

skills CLI
$ npx skills add ZenUml/web-sequence --skill babysit-pr -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ZenUml/web-sequence babysit-pr --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ZenUml/web-sequence.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/babysit-pr .claude/skills/babysit-pr && rm -rf skills-src

Use ~/.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/

Facts

Skill name
babysit-pr
GitHub stars
150
Token cost
~871 tokens
SKILL.md length
297 words
Files
2
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Monitor and diagnose GitHub Actions checks on ZenUML web-sequence PRs, fixing code-caused CI failures when appropriate.

  • Works in 5 steps: Find The PR → Check Status → Diagnose Failures → …
  • The user says babysit PR
  • SKILL.md covers Scope, Step 1. Find The PR, Step 2. Check Status and Step 3. Diagnose Failures, plus 4 more sections
  • Calls gh, git and yarn

What it does

Babysit PR is an agent skill from ZenUml/web-sequence. Monitor and diagnose GitHub Actions checks on ZenUML web-sequence PRs, fixing code-caused CI failures when appropriate. Use when the user says "babysit PR", "check PR status", "fix CI", "why is CI red", "watch this PR", or a PR is blocked by build, release, Firebase deploy, artifact, lint, test, or runner failures.

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Testing & QA, covering Failing and flaky tests, Linting and formatting and Diagrams. It works with Firebase, GitHub Actions, pnpm and GitHub. The repository describes itself as: Realtime tool for generating sequence diagrams. The licence is MIT.

When your agent uses it

  • The user says babysit PR
  • Check PR status
  • A PR is blocked by build
  • Firebase deploy

Example prompts

  • “babysit PR”
  • “check PR status”
  • “fix CI”
  • “/babysit-pr”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Find The PR
  2. Check Status
  3. Diagnose Failures
  4. Fix Or Rerun
  5. Push And Watch

What it can do on your machine

Read from SKILL.md and the folder at commit e38bd91. 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

    Shell commands in SKILL.md call:

    • gh
    • git
    • yarn
    • pnpm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, git, yarn and pnpm, 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

Babysit PR loads about 871 tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 297 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~82
When it runs · the whole SKILL.md, loaded when a task matches
~871

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 ZenUml/web-sequence at commit e38bd91, republished under its MIT licence (© ZenUml). 297 words, ~871 tokens.

Download SKILL.mdSave it as .claude/skills/babysit-pr/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
babysit-pr
description
Monitor and diagnose GitHub Actions checks on ZenUML web-sequence PRs, fixing code-caused CI failures when appropriate. Use when the user says "babysit PR", "check PR status", "fix CI", "why is CI red", "watch this PR", or a PR is blocked by build, release, Firebase deploy, artifact, lint, test, or runner failures.

Babysit PR

Watch a web-sequence PR, diagnose failures, optionally fix code issues, and retry within a small budget.

Scope

  • Repository: ZenUml/web-sequence
  • Main PR workflow: Deploy to Stage
  • Base branch: master
  • Production workflow Deploy to Prod runs only when a GitHub release is published.

Step 1. Find The PR

Use the explicit PR number if provided. Otherwise infer from the current branch:

bash
gh pr view --json number,title,url,headRefName,state,isDraft,statusCheckRollup

If no PR exists, stop and tell the user to use submit-branch.

Step 2. Check Status

bash
gh pr checks <PR_NUMBER> --repo ZenUml/web-sequence
gh pr view <PR_NUMBER> --repo ZenUml/web-sequence --json statusCheckRollup,headRefName,isDraft

Treat required successful checks as green. If checks are pending, find the latest run and watch it:

bash
gh run list --repo ZenUml/web-sequence --branch <branch> --limit 5 --json databaseId,name,status,conclusion,event,createdAt
gh run watch <RUN_ID> --repo ZenUml/web-sequence

Step 3. Diagnose Failures

Pull failed logs:

bash
gh run view <RUN_ID> --repo ZenUml/web-sequence --log-failed

Classify the failure:

  • Build: Vite errors, missing imports, package resolution, pnpm build
  • Release packaging: pnpm release, gulp, extension artifact, zip creation
  • Firebase staging deploy: credentials, project config, deploy command, emulator/config mismatch
  • Functions config/deploy: failures under functions/
  • Test/lint: Jest, Playwright, ESLint
  • Dependency/install: pnpm lockfile or Node version issues
  • Runner/infra: network, cache, GitHub outage, transient Firebase error
  • Dependabot/secrets skip: staging deploy intentionally skipped for Dependabot actors

Step 4. Fix Or Rerun

Before editing:

bash
git fetch origin
git checkout <PR_BRANCH>
git pull --ff-only origin <PR_BRANCH>

Fix only failures with a local code cause. Do not patch around secrets, credentials, Firebase project access, or GitHub runner outages.

Suggested local checks by category:

  • Build: yarn build
  • Release: yarn build && yarn release
  • Jest: yarn test
  • Playwright: yarn test:e2e
  • Lint: yarn lint
  • CI parity for package manager issues: pnpm install && pnpm build

If a failure is clearly transient infra, rerun failed jobs:

bash
gh run rerun <RUN_ID> --repo ZenUml/web-sequence --failed

Step 5. Push And Watch

After a code fix:

bash
git add <specific-files>
git commit -m "fix: <ci failure summary>"
git push origin <PR_BRANCH>

Then watch the new run. Maximum retry budget: 3 total fix/rerun attempts. Re-diagnose from fresh logs after each attempt.

Safety Rules

  • Never force-push.
  • Never resolve merge conflicts automatically.
  • Never commit unrelated local changes.
  • Never treat Firebase secret/auth failures as code fixes.
  • If CI passes after rerun without code changes, report likely flakiness.

Report

text
PR #<number> Babysit Report
- Status: PASSED|FAILED after <n> attempts|PENDING
- Workflow/run: <url>
- Failures found: ...
- Fixes applied: ...
- Manual attention needed: ...

© ZenUml, MIT. 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 .claude/skills/babysit-pr of ZenUml/web-sequence.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit e38bd91

Compare with similar skills

Babysit PR 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.

Babysit PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Babysit PR this skillZenUml/web-sequence150—~871Automated safety check: PassMIT
Authoring CI WorkflowsPostHog/posthog40k—~12kAutomated safety check: PassCustom licence
Debugging CI FailuresPostHog/posthog40k—~5.8kAutomated safety check: PassCustom licence
GreptimeDB Fuzz CI Failure InvestigationGreptimeTeam/greptimedb6.7k—~4.4kAutomated safety check: PassApache-2.0
Analysing CI Failuresgolemcloud/golem1.5k—~862Automated safety check: PassCustom licence
Manor CI Triagemanor-os/manor-ai162—~533Automated safety check: PassCustom licence

Similar skills

  • Authoring CI Workflows

    PostHog/posthog

    Official

    A skill your agent uses when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under .github/ — new CI jobs, triggers, matrices, checkout/clone tuning, action…

    40k GitHub stars~12k tokensUpdated today
    DevelopmentAuto-check passed

  • Debugging CI Failures

    PostHog/posthog

    Official

    Debugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches, and answers broad CI-health questions ("is CI red?", "is master green today?", "what's broken right now?").

    40k GitHub stars~5.8k tokensUpdated today
    Testing & QAAuto-check passed

  • GreptimeDB Fuzz CI Failure Investigation

    GreptimeTeam/greptimedb

    Diagnoses a failed GreptimeDB fuzz CI job by pulling its GitHub Actions logs and fuzz artifacts, then matching the evidence to the local source code.

    6.7k GitHub stars~4.4k tokensUpdated today
    Testing & QAAuto-check passed

  • Analysing CI Failures

    golemcloud/golem

    Analysing GitHub Actions CI failures from a run URL. An agent skill from golemcloud/golem.

    1.5k GitHub stars~862 tokensUpdated today
    Testing & QAAuto-check passed

  • Manor CI Triage

    manor-os/manor-ai

    A skill your agent uses when Manor GitHub Actions, .github/workflows/ci.yml, OSS smoke/regression jobs, web source smoke, frontend build, lint, or public CI failure logs need diagnosis or repair.

    162 GitHub stars~533 tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed

  • CI Debug

    yonatangross/orchestkit

    Diagnose a failing CI run against an 11-pattern playbook. An agent skill from yonatangross/orchestkit.

    292 GitHub stars~2.7k tokensUpdated today
    DevOps & CloudAuto-check: notes

More from ZenUml/web-sequence

  • Land PR

    ZenUml/web-sequence

    Merge a green ZenUML web-sequence PR into master and verify staging CI after merge.

    150 GitHub stars~632 tokensUpdated 5 days ago
    Auto-check passed

  • Release App

    ZenUml/web-sequence

    Release ZenUML web-sequence to production (app.zenuml.com) by publishing a GitHub release, wait for deploy-prod CI + @smoke, then run a release-delta spot check (spot-check skill Step 5.5).

    150 GitHub stars~1.7k tokensUpdated 5 days ago
    Auto-check passed

  • Spot Check

    ZenUml/web-sequence

    Ad hoc, AI-driven verification of a specific behavior on ZenUML web-sequence — not a new checked-in E2E test.

    150 GitHub stars~1.7k tokensUpdated 5 days ago
    Auto-check passed

  • Submit Branch

    ZenUml/web-sequence

    Push the current ZenUML web-sequence branch, create or reuse a GitHub PR against master, then always run babysit-pr until CI is green or blocked.

    150 GitHub stars~765 tokensUpdated 5 days ago
    Auto-check passed

  • Validate Branch

    ZenUml/web-sequence

    Run local validation checks for ZenUML web-sequence before pushing, opening a PR, or merging.

    150 GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check passed

  • Ship Branch

    ZenUml/web-sequence

    Take the current ZenUML web-sequence branch from local validation through PR submission, green CI, and merge to master.

    150 GitHub stars~456 tokensUpdated 5 days ago
    Auto-check passed

Works with

Categories

Questions about Babysit PR

What does Babysit PR do?

Monitor and diagnose GitHub Actions checks on ZenUML web-sequence PRs, fixing code-caused CI failures when appropriate. Babysit PR is an agent skill from ZenUml/web-sequence. Monitor and diagnose GitHub Actions checks on ZenUML web-sequence PRs, fixing code-caused CI failures when appropriate.

When should I use Babysit PR?

Babysit PR fits situations like: the user says babysit PR; check PR status; A PR is blocked by build; firebase deploy.

How do I install Babysit PR in Claude Code?

Run `npx skills add ZenUml/web-sequence --skill babysit-pr -a claude-code`. Or copy the skill folder (.claude/skills/babysit-pr in ZenUml/web-sequence) into .claude/skills/babysit-pr in your project. Claude Code loads it when a task matches its description.

How do I install Babysit PR in Codex?

Run `npx skills add ZenUml/web-sequence --skill babysit-pr -a codex`. Or copy the skill folder (.claude/skills/babysit-pr in ZenUml/web-sequence) into .agents/skills/babysit-pr in your project. Codex loads it when a task matches its description.

Can I use Babysit PR 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 ZenUml/web-sequence --skill babysit-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/babysit-pr, .gemini/skills/babysit-pr, .github/skills/babysit-pr and .opencode/skills/babysit-pr in your project.

What does Babysit PR need to run?

Going by SKILL.md and its folder, Babysit PR needs the command-line tools its instructions call (gh, git, yarn and pnpm).

Does Babysit PR access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Babysit PR 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 Babysit PR use?

Babysit PR is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Babysit PR use?

About 871 tokens (SKILL.md is roughly 3.5k 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 Babysit PR?

Skills that share tags, products or a category with Babysit PR: Authoring CI Workflows (PostHog/posthog, 40k stars), Debugging CI Failures (PostHog/posthog, 40k stars), GreptimeDB Fuzz CI Failure Investigation (GreptimeTeam/greptimedb, 6.7k stars) and Analysing CI Failures (golemcloud/golem, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Babysit PR?

ZenUml (a GitHub organization) maintains it in ZenUml/web-sequence, which has 150 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 5, 2026.

Source: ZenUml/web-sequence on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.