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

Backport

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

A skill your agent uses when someone asks to backport or cherry-pick a PR to release branches of an openshift/ repository.

Apache-2.0Auto-check passed

Install Backport

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

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

GitHub CLI
$ gh skill install openshift-eng/ai-helpers backport --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/backport .claude/skills/backport && 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
backport
GitHub stars
120
Token cost
~819 tokens
SKILL.md length
381 words
Files
1
Skills in repo
118
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when someone asks to backport or cherry-pick a PR to release branches of an openshift/ repository.

  • Works in 4 steps: One bug per release. The fix's OCPBUGS… → One PR per branch, cherry-picked from… → Merge needs, per Tide on release… → …
  • Someone asks to backport
  • SKILL.md covers Name, Synopsis, What the process is (so you… and Steps, plus 1 more section
  • Calls git

What it does

Backport is an agent skill from openshift-eng/ai-helpers. Use when someone asks to backport or cherry-pick a PR to release branches of an openshift/ repository. Drives the full OpenShift backport flow — Jira clone chain, one cherry-pick PR per branch, chain progression — using the deterministic ocpbackport tools.

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 works with Jira and GitHub. 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

  • Someone asks to backport
  • Cherry-pick a PR to release branches of an openshift/ repository

Example prompts

  • “/backport”

Workflow steps

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

  1. One bug per release. The fix's OCPBUGS bug is cloned once per target
  2. One PR per branch, cherry-picked from the parent PR's commits with
  3. Merge needs, per Tide on release branches: lgtm, approved,
  4. A multi-branch request is a set: all PRs open together (when the

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 no API keys, tokens, secrets or passwords.

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

Context cost

Backport loads about 819 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 381 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~819

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). 381 words, ~819 tokens.

Download SKILL.mdSave it as .claude/skills/backport/SKILL.md (or your agent's skills folder).
name
backport
description
Use when someone asks to backport or cherry-pick a PR to release branches of an openshift/* repository. Drives the full OpenShift backport flow — Jira clone chain, one cherry-pick PR per branch, chain progression — using the deterministic ocp_backport_* tools.

Name

openshift-developer:backport

Synopsis

text
/openshift-developer:backport <PR> <branches...>

OpenShift backport (coordinator playbook)

Use when someone asks to backport or cherry-pick a PR to release-* branches of a github.com/openshift/* repository, in Slack or in a GitHub mention on the PR.

What the process is (so you can explain it)

  1. One bug per release. The fix's OCPBUGS bug is cloned once per target branch; each clone is blocked by the clone for the next-newer branch (Blocks links), so a release-4.20 PR is only valid once the release-4.21 bug is VERIFIED. The jira-lifecycle-plugin validates PRs against this chain and labels them jira/valid-bug / jira/invalid-bug.
  2. One PR per branch, cherry-picked from the parent PR's commits with git cherry-pick -x, titled [release-4.20] OCPBUGS-<clone>: …, body starting This is an automated cherry-pick of #N.
  3. Merge needs, per Tide on release branches: lgtm, approved, jira/valid-bug, backport-risk-assessed (a z-stream approver's risk sign-off) and verified (QE or a collaborator's /verified by). The bot never applies any of these.
  4. A multi-branch request is a set: all PRs open together (when the parent merges, or immediately if asked), never chained one-after-another.
Show full SKILL.md (204 more words)Show less

Steps

  1. ocp_backport_plan(pr, branches) — blockers stop you; a chain gap means offering the completed branch list. Show the summary; confirm (Slack reply / GitHub comment).
  2. priv_ocp_backport_ensure_clones(host, repo, pr_number, branches) — the Jira chain. Report created vs reused clones. Parent not merged → wait for the merge turn.
  3. Per branch, newest first, one pod (rws_pod_create named after the campaign): ocp_backport_brief → rws_new_agent → rws_goal_task running /openshift-developer:cherry-pick with the brief → on success priv_scm_ensure_fork + priv_scm_create_change_request with the brief's title/body unchanged → ocp_backport_record_pr. Conflicts park the branch (report_progress(kind="concern"), tell the requester which files).
  4. Then monitor: PR-activity turns (reviews, CI) and [BACKPORT UPDATE] turns from the watcher. ocp_backport_status gives each branch's next_action; ocp_zstream_approvers(repo) names who can sign off.

Exceptions you recognize, humans decide

  • jlp-no-clone on the bug, a disallowed security level, a non-bug project in the title, red-hat-storage/DFBUGS: the plan blocks; explain.
  • Code that no longer exists in master: the campaign can start from the newest affected branch; newer releases still get "presence" bugs.
  • Releases that already contain the fix: clones still exist for QE to verify; moving them to ON_QA is a human ask you may relay only when told.
  • Maintenance / EOL / EUS releases: the plan's lifecycle phase warning is the cue to point at engineering management + PM (or Sustaining Engineering).

© 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/backport of openshift-eng/ai-helpers.

Open the folder on GitHubat commit a627176

Compare with similar skills

Backport 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.

Backport compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Backport this skillopenshift-eng/ai-helpers120—~819Automated safety check: PassApache-2.0
YugabyteDB Issue Creatoryugabyte/yugabyte-db11k—~2kAutomated safety check: PassCustom licence
Connect Apps with ComposioComposioHQ/awesome-claude-skills77k3 repos~557Automated safety check: PassNone
Link Ticket To SessionJayantDevkar/claude-code-karma329—~1.8kAutomated safety check: NotesApache-2.0
Octo LoopMininglamp-OSS/octo-cli918—~2.3kAutomated safety check: PassApache-2.0
Opendocsioteverythin/OpenDocs233—~746Automated safety check: NotesMIT

Similar skills

  • YugabyteDB Issue Creator

    yugabyte/yugabyte-db

    Creates a GitHub issue or JIRA ticket for a YugabyteDB change or bug, after scrubbing customer data, secrets and unreleased details from anything public.

    11k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed

  • Connect Apps with Composio

    ComposioHQ/awesome-claude-skills

    Connects an agent to 1000+ external apps through the Composio Tool Router plugin, so it can actually send emails, create issues and post messages instead of only drafting them.

    77k GitHub starsUsed in 3 repos~557 tokens
    Productivity & AutomationAuto-check passed

  • Link Ticket To Session

    JayantDevkar/claude-code-karma

    Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma.

    329 GitHub stars~1.8k tokensUpdated 9 days ago
    DevelopmentAuto-check: notes

  • Octo Loop

    Mininglamp-OSS/octo-cli

    A skill your agent uses when operating the Octo Loop control plane through the octo-cli loop commands: reading or writing Fleet tasks, comments, metadata, projects, and labels; dispatching work to…

    918 GitHub stars~2.3k tokensUpdated 9 days ago
    Backend & APIsAuto-check passed

  • Opendocs

    ioteverythin/OpenDocs

    Generates multi-format documentation (Word, PDF, PPTX, Markdown blog post, JIRA ticket, FAQ, changelog, LaTeX, social snippet, architecture diagram) from a GitHub README, npm package, local Markdown…

    233 GitHub stars~746 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check: notes

  • Issue Triage Loop

    cobusgreyling/loop-engineering

    Scans open GitHub issues and discussions, flags duplicates, scores priority and proposes labels into issue-triage-state.md without ever labeling or closing.

    11k GitHub stars~522 tokensUpdated today
    DevelopmentAuto-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

Questions about Backport

What does Backport do?

A skill your agent uses when someone asks to backport or cherry-pick a PR to release branches of an openshift/ repository. Backport is an agent skill from openshift-eng/ai-helpers. Use when someone asks to backport or cherry-pick a PR to release branches of an openshift/ repository.

When should I use Backport?

Backport fits situations like: someone asks to backport; cherry-pick a PR to release branches of an openshift/ repository.

How do I install Backport in Claude Code?

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

How do I install Backport in Codex?

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

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

What does Backport need to run?

Going by SKILL.md and its folder, Backport needs the command-line tools its instructions call (git).

Does Backport 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 Backport 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 Backport use?

Backport 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 Backport use?

About 819 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 Backport?

Skills that share tags, products or a category with Backport: YugabyteDB Issue Creator (yugabyte/yugabyte-db, 11k stars), Connect Apps with Composio (ComposioHQ/awesome-claude-skills, 77k stars), Link Ticket To Session (JayantDevkar/claude-code-karma, 329 stars) and Octo Loop (Mininglamp-OSS/octo-cli, 918 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Backport?

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.