Agent skill

Kei PR Ready

by rhoopr in rhoopr/kei

Validate a kei branch before review without publishing or changing it.

MITAuto-check passedDevOps & Cloud

Install Kei PR Ready

skills CLI
$ npx skills add rhoopr/kei --skill kei-pr-ready -a claude-code

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

GitHub CLI
$ gh skill install rhoopr/kei kei-pr-ready --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/rhoopr/kei.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/kei-pr-ready .claude/skills/kei-pr-ready && 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
kei-pr-ready
GitHub stars
156
Token cost
~1.2k tokens
SKILL.md length
609 words
Files
2
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Validate a kei branch before review without publishing or changing it.

  • Works in 5 steps: Read repository-root AGENTS.md, then the… → Run just agent-status. → Resolve the remote default branch,… → …
  • Asked whether a kei change is PR-ready
  • SKILL.md covers Preflight, Classify impact, Validate and Review and report
  • Calls just

What it does

Kei PR Ready is an agent skill from rhoopr/kei. Validate a kei branch before review without publishing or changing it. Use when asked whether a kei change is PR-ready, to run the repository gate, to check review readiness, to validate a branch or diff, or to identify missing tests, consumers, documentation, safety evidence, or user-flow checks before PR preparation.

Its SKILL.md is about 1.2k 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 DevOps & Cloud, covering UX design. It works with Docker and Rust. The repository describes itself as: Fast, parallel backups for cloud-hosted photos and videos - one-time exports, local mirrors, and unattended Docker runs. The licence is MIT.

When your agent uses it

  • Asked whether a kei change is PR-ready
  • Run the repository gate
  • Check review readiness
  • Validate a branch

Example prompts

  • “/kei-pr-ready”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read repository-root AGENTS.md, then the relevant sections of
  2. Run just agent-status.
  3. Resolve the remote default branch, falling back to origin/main, then run
  4. Record the exact base, merge base, and head. Inspect committed, staged,
  5. Create a coverage ledger for every changed (status, path) entry, including

What it can do on your machine

Read from SKILL.md and the folder at commit 5cffa73. 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:

    • just

    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

Kei PR Ready loads about 1.2k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 609 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 rhoopr/kei at commit 5cffa73, republished under its MIT licence (© rhoopr). 609 words, ~1,224 tokens.

Download SKILL.mdSave it as .claude/skills/kei-pr-ready/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
kei-pr-ready
description
Validate a kei branch before review without publishing or changing it. Use when asked whether a kei change is PR-ready, to run the repository gate, to check review readiness, to validate a branch or diff, or to identify missing tests, consumers, documentation, safety evidence, or user-flow checks before PR preparation.

Validate a kei branch

Produce an evidence-backed readiness verdict. Keep the pass read-only unless the user separately asks to fix a failure. Do not commit, push, open a pull request, or change GitHub state.

Preflight

  1. Read repository-root AGENTS.md, then the relevant sections of CONTRIBUTING.md, docs/architecture.md, and tests/README.md.
  2. Run just agent-status.
  3. Resolve the remote default branch, falling back to origin/main, then run just review-scope BASE=<resolved-base>.
  4. Record the exact base, merge base, and head. Inspect committed, staged, unstaged, and untracked changes. Return a not-ready verdict if unrelated work prevents an attributable review.
  5. Create a coverage ledger for every changed (status, path) entry, including tests, docs, workflows, deletions, and renames. Mark each entry reviewed or skipped with a concrete reason. Keep unchanged callers and invariant owners in a separate context list. Never silently omit a changed entry.

Classify impact

Map every changed behavior to the owner and direct consumers in docs/architecture.md. Apply each matching row in its change-impact checklist. At minimum, classify:

  • provider identity, enumeration, checkpoint, or retry behavior
  • SQLite schema, query, durable key, sentinel, or serialization
  • file, path, publication, import, or metadata behavior
  • CLI, configuration, machine output, service, or documentation
  • tests, scripts, workflows, packaging, or release behavior

Trace shared types and literal consumers with rg. Identify the applicable safety-contract IDs and focused scenario slices. Do not treat the round-trip gate or a passing unit test as proof that all consumers were traced.

For file or path behavior, list every alternate byte-landing and downloaded-state finalization route, including normal download, local path reconciliation, import/adoption, pending recovery, explicit repair, and metadata rewrite where applicable. Compare each reached route against checksum, no-overwrite publication, metadata, fsync, durable state, retry, checkpoint, and root-confinement invariants. A normal-download test does not prove another route.

Record review depth by behavior and lens. Use separate coverage-ledger rows for correctness, safety, liveness, performance, and user-visible metadata when they apply. Do not label a complete owner or module "fully inspected" when the review covered only one lens, such as scale.

Show full SKILL.md (278 more words)Show less

Validate

  1. Run the smallest matching focused test or just test scenario NAME.
  2. Apply the contribution testing rules, including the changed command and its consumers for CLI or user-flow work.
  3. Apply the state-transition proof requirements. Report the required evidence or a concrete reason the proof does not apply.
  4. For schema, primary-key, sentinel, durable-key, or serialization changes, search every old literal and prove migration and round-trip behavior.
  5. Run just gate.
  6. Investigate every failure. Use bounded output and just agent-failure-summary when a retained full-test log is relevant.

Treat gate, CI, and full-test results as proof only when the record shows that the run stayed on one head and that head matches the reviewed head. Label results from the same branch at another head as STALE and results from another branch as OTHER BRANCH.

Do not run live tests unless the changed behavior requires them. Follow tests/README.md, run live suites single-threaded, and preserve rate-limit and shared-session constraints.

Review and report

Self-review the complete end-state diff for unrelated scope, missed consumers, weak evidence, accidental API changes, unnecessary abstractions, and stale documentation.

Report:

  • base, head, and reviewed diff scope
  • merge base and validation provenance
  • changed-file coverage ledger and separate context-file list
  • impact classification, owners, safety contracts, and scenario slices
  • behavior-specific review depth for correctness, safety, liveness, performance, and user-visible metadata
  • state-transition proof or a concrete reason it does not apply
  • exact validation commands and results
  • unresolved failures, skipped checks, risks, and missing evidence
  • final verdict: ready or not ready

Never report ready when a required check failed, was skipped without a documented reason, could not be attributed to the reviewed head, or any changed file is unaccounted for.

© rhoopr, 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 .agents/skills/kei-pr-ready of rhoopr/kei.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 5cffa73

Compare with similar skills

Kei PR Ready 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.

Kei PR Ready compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kei PR Ready this skillrhoopr/kei156—~1.2kAutomated safety check: PassMIT
GreptimeDB Dev Docker ImageGreptimeTeam/greptimedb6.7k—~4kAutomated safety check: NotesApache-2.0
GitHub Actions CreatorFNOSP/FlyNarwhal5091 repos~2.4kAutomated safety check: PassAGPL-3.0
Gui Automationam-will/gooey-pi943—~1.4kAutomated safety check: PassMIT
Fungienbop/fungi132—~2.9kAutomated safety check: PassApache-2.0
Tsk Configdtormoen/tsk-tsk171—~2.8kAutomated safety check: NotesMIT

Similar skills

  • GreptimeDB Dev Docker Image

    GreptimeTeam/greptimedb

    Packages a locally built GreptimeDB debug binary into a development-only Docker image for local-cluster testing, with an optional push to a dev registry.

    6.7k GitHub stars~4k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • GitHub Actions Creator

    FNOSP/FlyNarwhal

    A skill your agent uses when the user wants to create, generate, or set up a GitHub Actions workflow.

    509 GitHub starsUsed in 1 repo~2.4k tokens
    DevOps & CloudAuto-check passed
  • Gui Automation

    am-will/gooey-pi

    A skill your agent uses when you need to visually interact with a GUI — test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end…

    943 GitHub stars~1.4k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • Fungi

    enbop/fungi

    Install, configure, and operate the Fungi CLI across devices.

    132 GitHub stars~2.9k tokensUpdated 7 days ago
    DevOps & CloudAuto-check passed
  • Tsk Config

    dtormoen/tsk-tsk

    A skill your agent uses when the user wants to set up or configure tsk Docker container images, customize their tsk.toml for Docker builds, configure stack/agent/project layers, or troubleshoot tsk…

    171 GitHub stars~2.8k tokensUpdated 2 mo ago
    DevOps & CloudAuto-check: notes
  • Vuio

    vuiodev/vuio

    Browse, search and cast a VuIO media library, build playlists, and control DLNA, Chromecast and AirPlay devices on the local network.

    172 GitHub stars~1.3k tokensUpdated 17 days ago
    DevOps & CloudAuto-check passed

Works with

Questions about Kei PR Ready

What does Kei PR Ready do?

Validate a kei branch before review without publishing or changing it. Kei PR Ready is an agent skill from rhoopr/kei. Validate a kei branch before review without publishing or changing it.

When should I use Kei PR Ready?

Kei PR Ready fits situations like: asked whether a kei change is PR-ready; run the repository gate; check review readiness; validate a branch.

How do I install Kei PR Ready in Claude Code?

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

How do I install Kei PR Ready in Codex?

Run `npx skills add rhoopr/kei --skill kei-pr-ready -a codex`. Or copy the skill folder (.agents/skills/kei-pr-ready in rhoopr/kei) into .agents/skills/kei-pr-ready in your project. Codex loads it when a task matches its description.

Can I use Kei PR Ready 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 rhoopr/kei --skill kei-pr-ready -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kei-pr-ready, .gemini/skills/kei-pr-ready, .github/skills/kei-pr-ready and .opencode/skills/kei-pr-ready in your project.

What does Kei PR Ready need to run?

Going by SKILL.md and its folder, Kei PR Ready needs the command-line tools its instructions call (just).

Does Kei PR Ready 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 Kei PR Ready 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 Kei PR Ready use?

Kei PR Ready 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 Kei PR Ready use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 Kei PR Ready?

Skills that share tags, products or a category with Kei PR Ready: GreptimeDB Dev Docker Image (GreptimeTeam/greptimedb, 6.7k stars), GitHub Actions Creator (FNOSP/FlyNarwhal, 509 stars), Gui Automation (am-will/gooey-pi, 943 stars) and Fungi (enbop/fungi, 132 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kei PR Ready?

rhoopr (a GitHub user) maintains it in rhoopr/kei, which has 156 GitHub stars. The repository was last updated on October 11, 2026.

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