Agent skill

To Quality PR

by gambitph in gambitph/Stackable

Quality-gated ship: run ensure-quality, then commit dirty gated work and open a triage PR whose body is the gate summary (LOWRISKMERGE / MEDIUMREVIEW / HIGHHOLD).

GPL-3.0Auto-check passedDevelopment

Install To Quality PR

skills CLI
$ npx skills add gambitph/Stackable --skill to-quality-pr -a claude-code

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

GitHub CLI
$ gh skill install gambitph/Stackable to-quality-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/gambitph/Stackable.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/to-quality-pr .claude/skills/to-quality-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
to-quality-pr
GitHub stars
350
Token cost
~953 tokens
SKILL.md length
464 words
Files
4
Skills in repo
18
Repo updated
First seen
Licence
GPL-3.0

At a glance

Quality-gated ship: run ensure-quality, then commit dirty gated work and open a triage PR whose body is the gate summary (LOWRISKMERGE / MEDIUMREVIEW / HIGHHOLD).

  • Works in 2 steps: Ensure quality → Ship
  • The user asks to to-quality-pr
  • SKILL.md covers When to run, Preconditions, Pipeline and Triage verdict (summary)
  • Calls gh

What it does

To Quality PR is an agent skill from gambitph/Stackable. Quality-gated ship: run ensure-quality, then commit dirty gated work and open a triage PR whose body is the gate summary (LOWRISKMERGE / MEDIUMREVIEW / HIGHHOLD). Guardrail against AI slop leaving the machine. Use when the user asks to to-quality-pr, quality PR, gate and PR, ship a PR, or open a PR after changes; after finishing substantive or AI-generated work when the next step is a pull request; prefer this over committing or opening a PR without a quality gate.

Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `agents/openai.yaml`, `reference/pr-body.md` and `reference/ship.md`).

It sits in Development, covering Pull requests and Quality gates. The repository describes itself as: Page Builder Blocks for WordPress. An Amazing Block Library for the new WordPress Block Editor (Gutenberg). The licence is GPL-3.0.

When your agent uses it

  • The user asks to to-quality-pr
  • Open a PR after changes
  • After finishing substantive
  • AI-generated work when the next step is a pull request

Example prompts

  • “/to-quality-pr”

Workflow steps

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

  1. Ensure quality
  2. Ship

What it can do on your machine

Read from SKILL.md and the folder at commit 5c13d80. 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

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

  • Network

    No URLs in SKILL.md. Its commands use gh, 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

To Quality PR loads about 953 tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 464 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~122
When it runs · the whole SKILL.md, loaded when a task matches
~953

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 gambitph/Stackable at commit 5c13d80, republished under its GPL-3.0 licence (© gambitph). 464 words, ~953 tokens.

Download SKILL.mdSave it as .claude/skills/to-quality-pr/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
to-quality-pr
description
Quality-gated ship: run ensure-quality, then commit dirty gated work and open a triage PR whose body is the gate summary (LOW_RISK_MERGE / MEDIUM_REVIEW / HIGH_HOLD). Guardrail against AI slop leaving the machine. Use when the user asks to to-quality-pr, quality PR, gate and PR, ship a PR, or open a PR after changes; after finishing substantive or AI-generated work when the next step is a pull request; prefer this over committing or opening a PR without a quality gate.

To quality PR

Ship guardrail: gate first, then PR. Runs ensure-quality to completion, then commits the gated worktree and opens a pull request whose description is the gate output in a triage-first format. Reviewers should decide merge-now vs inspect-first from the PR header alone.

Does not re-implement the gate. Anti-slop / review / test / docs / lint live only in ensure-quality.

Stages (order): ensure-quality → ship (branch → commit → push → PR). Load reference/ship.md and reference/pr-body.md only when ship runs.

When to run

Fire this skill when any of these hold:

  • The user asks for to-quality-pr / quality PR / gate and PR / ship a PR / open a PR after changes.
  • You finished substantive or AI-generated source changes and the natural next step is a pull request.
  • You would otherwise commit and open a PR without a quality gate.

Prefer ensure-quality alone when the user wants a local gate only (no commit, no PR). Skip auto-invoke for pure Q&A, exploration with no edits, or when the user said to keep iterating without shipping.

Preconditions

  1. Synthesize intent the same way ensure-quality requires - authoritative acceptance criteria for the gate.
  2. Confirm ship target. Record base branch (same default resolution as ensure-quality's fixed-point base) and whether the user named a PR title or branch.
  3. Dirty scope. Note that ship will include all work ensure-quality gated (committed-since-fixed-point plus unstaged/staged fixes the gate applied).

Completion: intent written; ship target named; then enter the pipeline.

Pipeline

Show full SKILL.md (230 more words)Show less
1. Ensure quality

Read and execute .cursor/skills/ensure-quality/SKILL.md fully for this worktree. Honor its HITL pauses; do not ship past unresolved ask-user findings. Capture its Summary fields verbatim for the PR body - do not invent a second risk score.

If Summary Ship readiness is blocked (or the gate aborts): stop. Leave the worktree dirty. Emit a short blocked report (intent, risk, remaining findings). Do not commit. Do not push. Do not open a PR.

If the gate reports ready with an empty diff (nothing to gate): stop and say so - no empty PR.

2. Ship

Only when ensure-quality ended Ship readiness: ready with a non-empty gated change set.

  1. Read reference/ship.md and follow it (branch, commit, push).
  2. Read reference/pr-body.md, map Summary → triage verdict + body, open the PR.
  3. Return the PR URL and the triage verdict to the user.

Completion: PR URL exists (or ship blocked with a concrete git/gh error); verdict stated; worktree clean relative to the pushed commit unless the user forbade commit.

Triage verdict (summary)

Derived in reference/pr-body.md from ensure-quality Risk (+ caution signal):

VerdictMeaning for reviewers
LOW_RISK_MERGESkim intent + diffstat; merge if CI green
MEDIUM_REVIEWRead Caution and linked hunks before merge
HIGH_HOLDDo not merge until Caution is checked; open as draft unless the user already approved shipping high risk

Empty Caution on Medium or High is a skill failure - rewrite before gh pr create.

© gambitph, GPL-3.0. 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 3 other files in .cursor/skills/to-quality-pr of gambitph/Stackable.

  • SKILL.md
  • agents/openai.yaml
  • reference/pr-body.md
  • reference/ship.md

Open the folder on GitHubat commit 5c13d80

Compare with similar skills

To Quality 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.

To Quality PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
To Quality PR this skillgambitph/Stackable350—~953Automated safety check: PassGPL-3.0
PlotJuggler Ship CheckPlotJuggler/PlotJuggler6.2k—~1.3kAutomated safety check: PassMPL-2.0
Pull Requestnoh-rs/nohrs156—~4.1kAutomated safety check: PassMIT
Compound Engineering Code ReviewEveryInc/compound-engineering-plugin25k—~2kAutomated safety check: PassMIT
Sonarcloud Reviewlucasvieirasilva/nx-plugins153—~2.7kAutomated safety check: NotesMIT
PR Preflight Checkliaohch3/claude-tap3.3k—~615Automated safety check: PassMIT

Similar skills

  • PlotJuggler Ship Check

    PlotJuggler/PlotJuggler

    Runs a gated finish-line checklist before committing a PlotJuggler PJ4 change: build proof, red-test triage, hooks, docs freshness and a diff self-review.

    6.2k GitHub stars~1.3k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Pull Request

    noh-rs/nohrs

    Take a change from working tree to a merge-ready pull request, then keep iterating until the CI checks and AI reviewers (CodeRabbit, cubic) all pass.

    156 GitHub stars~4.1k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Compound Engineering Code Review

    EveryInc/compound-engineering-plugin

    Runs a staged pull request or diff review using selected reviewer personas, checking the change against its stated intent and project standards before producing findings.

    25k GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Sonarcloud Review

    lucasvieirasilva/nx-plugins

    Fetches and triages SonarCloud findings (issues, security hotspots, quality gate) for the current pull request or branch of this repository via the SonarCloud Web API, summarizes them in a markdown…

    153 GitHub stars~2.7k tokensUpdated 10 days ago
    DevelopmentAuto-check: notes
  • PR Preflight Check

    liaohch3/claude-tap

    Runs a single merge-readiness check on a pull request: metadata, GitHub Actions status, local lint, format and test gates, and PR body rules, ending in READY or NOT_READY.

    3.3k GitHub stars~615 tokensUpdated 16 days ago
    DevelopmentAuto-check passed
  • Submit PR

    FutureTense/keymaster

    Procedure for preparing and submitting pull requests in keymaster, enforcing the required PR template (.github/PULLREQUESTTEMPLATE.md), checklist validation, and quality gates.

    349 GitHub stars~830 tokensUpdated yesterday
    DevelopmentAuto-check passed

More from gambitph/Stackable

All 18 skills in this repo
  • Wp Block Development

    gambitph/Stackable

    A skill your agent uses when developing WordPress (Gutenberg) blocks: block.json metadata, registerblocktype(frommetadata), attributes/serialization, supports, dynamic rendering…

    350 GitHub starsUsed in 4 repos~1.6k tokens
    Auto-check passed
  • Wp Block Themes

    gambitph/Stackable

    A skill your agent uses when developing WordPress block themes: theme.json (global settings/styles), templates and template parts, patterns, style variations, and Site Editor troubleshooting (style…

    350 GitHub starsUsed in 3 repos~985 tokens
    Auto-check passed
  • Wp Performance

    gambitph/Stackable

    A skill your agent uses when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers)…

    350 GitHub starsUsed in 3 repos~1.5k tokens
    Auto-check passed
  • Wp Plugin Development

    gambitph/Stackable

    A skill your agent uses when developing WordPress plugins: architecture and hooks, activation/deactivation/uninstall, admin UI and Settings API, data storage, cron/tasks, security…

    350 GitHub starsUsed in 3 repos~999 tokens
    Auto-check passed
  • Wp Project Triage

    gambitph/Stackable

    A skill your agent uses when you need a deterministic inspection of a WordPress repository (plugin/theme/block theme/WP core/Gutenberg/full site) including tooling/tests/version hints, and a…

    350 GitHub starsUsed in 4 repos~371 tokens
    Auto-check passed
  • A skill your agent uses when reviewing WordPress plugins for GPL compliance, checking license headers or compatibility, evaluating upsell/freemium/trialware patterns, validating plugin naming or…

    350 GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed

Questions about To Quality PR

What does To Quality PR do?

Quality-gated ship: run ensure-quality, then commit dirty gated work and open a triage PR whose body is the gate summary (LOWRISKMERGE / MEDIUMREVIEW / HIGHHOLD). To Quality PR is an agent skill from gambitph/Stackable. Quality-gated ship: run ensure-quality, then commit dirty gated work and open a triage PR whose body is the gate summary (LOWRISKMERGE / MEDIUMREVIEW / HIGHHOLD).

When should I use To Quality PR?

To Quality PR fits situations like: the user asks to to-quality-pr; open a PR after changes; after finishing substantive; AI-generated work when the next step is a pull request.

How do I install To Quality PR in Claude Code?

Run `npx skills add gambitph/Stackable --skill to-quality-pr -a claude-code`. Or copy the skill folder (.cursor/skills/to-quality-pr in gambitph/Stackable) into .claude/skills/to-quality-pr in your project. Claude Code loads it when a task matches its description.

How do I install To Quality PR in Codex?

Run `npx skills add gambitph/Stackable --skill to-quality-pr -a codex`. Or copy the skill folder (.cursor/skills/to-quality-pr in gambitph/Stackable) into .agents/skills/to-quality-pr in your project. Codex loads it when a task matches its description.

Can I use To Quality 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 gambitph/Stackable --skill to-quality-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/to-quality-pr, .gemini/skills/to-quality-pr, .github/skills/to-quality-pr and .opencode/skills/to-quality-pr in your project.

What does To Quality PR need to run?

Going by SKILL.md and its folder, To Quality PR needs the command-line tools its instructions call (gh).

Does To Quality PR access the network?

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

Is To Quality 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 To Quality PR use?

To Quality PR is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does To Quality PR use?

About 953 tokens (SKILL.md is roughly 3.8k 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 To Quality PR?

Skills that share tags, products or a category with To Quality PR: PlotJuggler Ship Check (PlotJuggler/PlotJuggler, 6.2k stars), Pull Request (noh-rs/nohrs, 156 stars), Compound Engineering Code Review (EveryInc/compound-engineering-plugin, 25k stars) and Sonarcloud Review (lucasvieirasilva/nx-plugins, 153 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains To Quality PR?

gambitph (a GitHub organization) maintains it in gambitph/Stackable, which has 350 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 7, 2026.

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