Agent skill

Check Gates

by openshift-eng in openshift-eng/ai-helpers

Repeatedly validate and fix a Jira implementation until tests, lint, builds, requirements, production readiness, and repository cleanliness all pass.

Apache-2.0Auto-check passedTesting & QA

Install Check Gates

skills CLI
$ npx skills add openshift-eng/ai-helpers --skill check-gates -a claude-code

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

GitHub CLI
$ gh skill install openshift-eng/ai-helpers check-gates --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/openshift-eng/ai-helpers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/openshift-developer/skills/check-gates .claude/skills/check-gates && 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
check-gates
GitHub stars
120
Token cost
~818 tokens
SKILL.md length
389 words
Files
1
Skills in repo
118
Repo updated
First seen
Licence
Apache-2.0

At a glance

Repeatedly validate and fix a Jira implementation until tests, lint, builds, requirements, production readiness, and repository cleanliness all pass.

  • Works in 6 steps: Resolve the Jira issue and build an… → Discover repository-prescribed… → Review the implementation for production… → …
  • A Jira implementation needs its final quality gate before delivery
  • SKILL.md covers Name, Synopsis, Success condition and Workflow, plus 2 more sections
  • Calls git; needs ISSUE_KEY

What it does

Check Gates is an agent skill from openshift-eng/ai-helpers. Repeatedly validate and fix a Jira implementation until tests, lint, builds, requirements, production readiness, and repository cleanliness all pass. Use when a Jira implementation needs its final quality gate before delivery.

Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Quality gates and Linting and formatting. It works with Jira and Git. The repository describes itself as: Developer productivity tools for Claude Code & other AI assistants. The licence is Apache-2.0.

When your agent uses it

  • A Jira implementation needs its final quality gate before delivery
  • Tasks that involve Quality gates
  • Tasks that involve Linting and formatting

Example prompts

  • “/check-gates”

Requirements

  • A credential in ISSUE_KEY

Workflow steps

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

  1. Resolve the Jira issue and build an explicit acceptance checklist from its description,
  2. Discover repository-prescribed validation commands from AGENTS.md, contributor
  3. Review the implementation for production readiness: error paths, upgrade and rollback
  4. For each failure
  5. Run git diff --check and inspect git status --short. Commit all in-scope source,
  6. Perform one final complete pass of the acceptance checklist and all applicable gates

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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, 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 these keys or tokens, usually read from environment variables:

    • ISSUE_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Check Gates loads about 818 tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 389 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~818

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). 389 words, ~818 tokens.

Download SKILL.mdSave it as .claude/skills/check-gates/SKILL.md (or your agent's skills folder).
name
check-gates
description
Repeatedly validate and fix a Jira implementation until tests, lint, builds, requirements, production readiness, and repository cleanliness all pass. Use when a Jira implementation needs its final quality gate before delivery.

Name

openshift-developer:check-gates

Synopsis

text
/openshift-developer:check-gates <ISSUE_KEY> [--ci]

Success condition

Do not report success until all of these are true for %ISSUE_KEY%:

  • Tests pass.
  • Linting and repository verification are clean.
  • Builds succeed.
  • Every implementation requirement is satisfied.
  • The changes are production-ready.
  • git status --short is empty.

If any gate fails, diagnose it, fix in-scope failures, and re-run every gate affected by the fix. Continue until the complete success condition holds. A previous successful run does not remain valid after another edit.

Workflow

  1. Resolve the Jira issue and build an explicit acceptance checklist from its description, acceptance criteria, reproduction details, and later clarifications. Inspect the current diff and commit history against that checklist.
  2. Discover repository-prescribed validation commands from AGENTS.md, contributor documentation, CI configuration, and the Makefile. At minimum, run applicable:
    • Unit and integration tests for changed behavior, followed by the repository test target when one exists.
    • Formatting, lint, generated-file, and verification targets.
    • Build targets covering affected binaries, images, or packages.
  3. Review the implementation for production readiness: error paths, upgrade and rollback behavior where relevant, concurrency/idempotency, security boundaries, observability, compatibility, tests, and documentation. Apply these checks proportionally to the change; do not invent unrelated work.
  4. For each failure:
    • Determine whether it is caused by the implementation, pre-existing, environmental, or outside the issue scope.
    • Fix implementation-caused and in-scope failures, using implement when substantive coding is needed.
    • Re-run the failed gate and any gate invalidated by the edit.
    • Never weaken a check, delete a legitimate test, or hide a failure to obtain a pass.
  5. Run git diff --check and inspect git status --short. Commit all in-scope source, test, documentation, and generated changes in logical conventional commits. Do not discard, overwrite, or commit unrelated user changes.
  6. Perform one final complete pass of the acceptance checklist and all applicable gates after the last commit. Confirm git status --short produces no output.
Show full SKILL.md (83 more words)Show less

Blocking conditions

The normal stopping condition is complete success. If an external dependency, unavailable required environment, contradictory acceptance criterion, or unrelated dirty worktree makes success impossible, do not claim the gates passed. Exhaust safe in-scope alternatives, then report the exact blocker and the remaining unsatisfied gates. Under --ci, do not prompt, push, create a PR, or mutate external systems.

Return value

Report each gate and its final command/evidence, the acceptance checklist result, final commit hashes, and confirmation that the working tree is clean.

© 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

Just SKILL.md in plugins/openshift-developer/skills/check-gates of openshift-eng/ai-helpers.

Open the folder on GitHubat commit a627176

Compare with similar skills

Check Gates 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.

Check Gates compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Check Gates this skillopenshift-eng/ai-helpers120—~818Automated safety check: PassApache-2.0
Quality Gatesandymai/brepjs114—~3.2kAutomated safety check: PassApache-2.0
Procoder Commit Gateazrtydxb/procoder211—~3.7kAutomated safety check: PassApache-2.0
Pre-Commit Check GateZeroDeng01/sublinkPro1.7k—~2.9kAutomated safety check: NotesMIT
Git PR Workflowandymai/brepjs114—~2.9kAutomated safety check: PassApache-2.0
Run Pre Gen ChecksGoogleCloudPlatform/magic-modules974—~492Automated safety check: PassCustom licence

Similar skills

  • Quality Gates

    andymai/brepjs

    This skill should be used when a local brepjs quality gate or npm run validate step fails and the specific rule's fix or escape hatch is needed — ESLint errors like "no-explicit-any" or "Direct .oc…

    114 GitHub stars~3.2k tokensUpdated today
    Testing & QAAuto-check passed
  • Procoder Commit Gate

    azrtydxb/procoder

    Applies Procoder's senior-developer discipline in a repository: run the commit gate, format through the binary and work through specs, plans and todos.

    211 GitHub stars~3.7k tokensUpdated 10 days ago
    DevelopmentAuto-check passed
  • Pre-Commit Check Gate

    ZeroDeng01/sublinkPro

    Blocking checklist that runs formatting, lint and test commands for changed Go and frontend files before any git add, commit or pull request.

    1.7k GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check: notes
  • Git PR Workflow

    andymai/brepjs

    This skill should be used when committing, pushing, branching, or merging in the brepjs repository — when a task involves "pre-commit hook failed" (which tier ran, how to bypass), "commit rejected…

    114 GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Run Pre Gen Checks

    GoogleCloudPlatform/magic-modules

    Run fast static checks that don't require generating downstreams, including git submodule verification, gofmt formatting, YAML linting, template validation (version-guard and unused-tmpl), mmv1 core…

    974 GitHub stars~492 tokensUpdated today
    Testing & QAAuto-check passed
  • Check

    av1155/houndarr

    Run Houndarr's full quality gate (ruff lint, ruff format check, mypy, bandit, pytest) and report results in a single table.

    292 GitHub stars~366 tokensUpdated 2 days ago
    Testing & QAAuto-check passed

More from openshift-eng/ai-helpers

All 118 skills in this repo
  • Investigate CI Reliability

    openshift-eng/ai-helpers

    Find and independently validate actionable reliability defects across OpenShift release jobs and presubmits, then export portable issue handoffs.

    120 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Address Review PR

    openshift-eng/ai-helpers

    Fetch and address all PR review comments — categorize by priority, make code changes, post replies, and push.

    120 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed
  • Categorize Activity Types

    openshift-eng/ai-helpers

    Categorize Jira issues into Red Hat Sankey Activity Type categories using MCP Jira tools.

    120 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • 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.

    120 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Must Gather Analyzer

    openshift-eng/ai-helpers

    Analyze OpenShift must-gather diagnostic data including cluster operators, pods, nodes, and network components.

    120 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed
  • 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

    120 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Check Gates

What does Check Gates do?

Repeatedly validate and fix a Jira implementation until tests, lint, builds, requirements, production readiness, and repository cleanliness all pass. Check Gates is an agent skill from openshift-eng/ai-helpers. Repeatedly validate and fix a Jira implementation until tests, lint, builds, requirements, production readiness, and repository cleanliness all pass.

When should I use Check Gates?

Check Gates fits situations like: A Jira implementation needs its final quality gate before delivery; tasks that involve Quality gates; tasks that involve Linting and formatting.

How do I install Check Gates in Claude Code?

Run `npx skills add openshift-eng/ai-helpers --skill check-gates -a claude-code`. Or copy the skill folder (plugins/openshift-developer/skills/check-gates in openshift-eng/ai-helpers) into .claude/skills/check-gates in your project. Claude Code loads it when a task matches its description.

How do I install Check Gates in Codex?

Run `npx skills add openshift-eng/ai-helpers --skill check-gates -a codex`. Or copy the skill folder (plugins/openshift-developer/skills/check-gates in openshift-eng/ai-helpers) into .agents/skills/check-gates in your project. Codex loads it when a task matches its description.

Can I use Check Gates 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 check-gates -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/check-gates, .gemini/skills/check-gates, .github/skills/check-gates and .opencode/skills/check-gates in your project.

What does Check Gates need to run?

Going by SKILL.md and its folder, Check Gates needs the command-line tools its instructions call (git) and credentials named ISSUE_KEY. Our summary lists: A credential in ISSUE_KEY.

Does Check Gates access the network?

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

Is Check Gates 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 Check Gates use?

Check Gates 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 Check Gates use?

About 818 tokens (SKILL.md is roughly 3.3k 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 Check Gates?

Skills that share tags, products or a category with Check Gates: Quality Gates (andymai/brepjs, 114 stars), Procoder Commit Gate (azrtydxb/procoder, 211 stars), Pre-Commit Check Gate (ZeroDeng01/sublinkPro, 1.7k stars) and Git PR Workflow (andymai/brepjs, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Check Gates?

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.