Netcracker/qubership-ai-packages

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Author an Architecture Decision Record. Use whenever the user wants to capture, write, or draft an architecture or system-design decision — "write an ADR", "document this decision", "add a decision record", "we decided to use X, record it" — even when they don't say "ADR" but describe a choice worth tracking (a…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Use when a user explicitly asks to review a GitHub pull request or GitLab merge request.

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Set up Renovate so dependency-update PRs merge themselves once CI passes. Use when enabling automerge in renovate.json, deciding which GitHub status checks to mark as required so a green PR means the tests actually ran, or adding a CI-gate job that folds several test jobs into one required check.

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

French technical-prose conventions for software documentation, README files, UI strings, error messages, logs, code comments, PR descriptions, changelog entries, and French localization. Use when writing, editing, translating, or reviewing French software-facing prose. Defaults to fr-FR, supports fr-CA mode, and…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before writing, editing, or reviewing a doc comment or inline comment in Go: the comment on a new or changed function, method, type, or package, a method that implements an interface, a //go:, //nolint, or +kubebuilder line, a regression test that names the old defect, a subtest name or a failure message, a CRD…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before writing, editing, or reviewing a doc comment or inline comment in Java, Kotlin, Groovy, or Scala: a Javadoc for a new or changed method or class, a @throws or @param for behavior that just changed, the comment on a test just added, a regression test that names the old defect, an override that departs from…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before writing, editing, or reviewing a doc comment or inline comment in JavaScript or TypeScript: a TSDoc block on an exported declaration, a @param type in a checked .js file, the it string of a test just added, a regression test that names the old defect, a method that overrides a base class or implements an…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Turn a meeting recording or transcript into a structured report through multi-axis analysis. Trigger when the user hands you a call transcript, a meeting recording, or diarized conversation text (Speaker 1 / Speaker 2, timecodes) and asks to "analyze the meeting", "break down the call", "summarize the call", "what did…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before writing, editing, or reviewing a docstring or inline comment in Python: the docstring on a new or changed function or class, a Raises: or Yields: section for behavior that just changed, a docstring that ships as --help text or an OpenAPI description, a doctest the test run executes, the docstring on a test…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Prepare a pull request that adds Qubership baseline agent support to a repository: install qubership-essentials, run apm install for repository-declared harnesses, commit generated agent assets, and configure generated-file attributes and Super-Linter exclusions.

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Audit or fix a Netcracker or Qubership GitHub repository for required files, workflows, Grand Report, APM Essentials, coverage, topics, and repository settings.

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Russian style guidance for developer-facing text of any length — README and docs, code comments, docstrings, commit messages, PR descriptions, changelog entries, UI strings (buttons, labels, placeholders, tooltips), error and log messages, and localisation files (.po, .properties, JSON i18n). Use whenever the task…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before writing, editing, or reviewing a doc comment or inline comment in Rust: the comment on a new or changed function, type, trait, or module, a # Errors or # Panics section for behavior that just changed, a # Safety section on an unsafe fn, a // SAFETY: comment beside an unsafe block, a doc example the build…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Triage failing checks on dependency-update PRs (Renovate or Dependabot) and drive them back to green: classify each failure, fix the clear ones, ask about the rest. Use only when the user asks to triage, fix, or sweep failing checks on dependency-update PRs — pass a PR number for one PR, or none to process every open…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex needs its repo

Use when the user asks to create, add, regenerate, or extend a repository-specific troubleshooting skill for the current checkout, a repository under repos/, or another named repository. This skill authors a skill; it does not diagnose a live incident.

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before writing the commit message, the pull request title and description, or the changelog or release-note entry for a change, including at the end of a coding task ("fix the bug", "implement the feature", "prepare the PR"): load it when the code is done and before git commit. Also load to rewrite, review, or…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before writing or editing a documentation page in a repository: a README, a reference or options page, a feature page, a how-to, a tutorial, a troubleshooting page, a migration guide. Inside a coding task, load it as soon as the change adds, renames, or removes an option, a property, a flag, an environment…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

English prose conventions for written deliverables: documentation, README files, javadoc and code comments, commit messages, PR descriptions and review replies, design docs, and choice of English identifier names (methods, variables, classes, files). Covers em-dash usage, hyphen stacking, sentence structure…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Use at the end of a coding task, in a fresh subagent, when the code, tests, and comments are written and before the commit is final: "run the final review", "final-review this change", "check the change before I commit". Reviews one change against a fixed form: every doc comment added or changed, and every comment…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before writing, editing, or reviewing a test in any language, and at the end of a coding task that changed behavior ("fix the bug"): the change owes tests, and this skill decides which. Also load when asked whether a change is tested enough, at which level a test belongs, why a test is flaky, whether a test could…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before writing or reviewing a report of a problem someone else has to act on: a bug report or issue in any tracker (GitHub, GitLab, Jira, a team's own backlog) or on a mailing list, a feature or change request, a question when you are not sure it is a defect, a vendor support ticket, a comment on an existing…

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

A method for preparing a short spoken update about a team's work for a town hall. It turns slides, notes, task exports, drafts, or agent conversations into a brief for managers and nearby team leads.

Netcracker/qubership-ai-packages

Skill Claude CodeCodex

Load before deciding what to ask a system whose behavior you must learn by querying it, not by reading its code: a legacy service you are porting or rewriting, a vendor jar or third-party API without source, another team's undocumented service, a stand that answers a parity or golden suite, an executable spec checked…