odh-ai-helpers

Plugin odh-ai-helpers from marketplace opendatahub-skills in opendatahub-io/skills-registry. Commands read from the repo's manifest — 8 days ago.

Skills (72)

• coderabbit-review

  Use when you need to evaluate CodeRabbit PR comments and fix or reply

• unit-test-project-conformant

  Use this skill to write unit tests that strictly conform to the project's existing testing structure, patterns, and style by learning from similar tests before writing anything new.

• adr-review

  Review an Architectural Decision Record (ADR) using a team of six specialist reviewer subagents and produce a consolidated report as both PDF and PPTX slide deck. Use this skill whenever the user asks to review, critique, audit, or get feedback on an ADR, architecture decision, design doc, or RFC —

• doc-gap

  Use this skill to analyze context sufficiency for documentation generation. Reads workspace/context-package.json and produces workspace/gap-report.json with severity-rated gaps and a proceed/gather-more/stop recommendation.

• doc-gather

  Use when you need to gather context for a Jira ticket or PR. Resolves ticket metadata, clones relevant repos, collects candidate files, runs filtering pipeline, and produces workspace/context-package.json.

• doc-generate

  Use when you need to generate AsciiDoc documentation modules from gathered context. Reads context package and gap report, generates content, then self-validates with iterative correction (up to 3 retries). Produces generated files and workspace/generation-report.json.

• doc-pipeline

  Use this skill to orchestrate the full documentation pipeline. Sequences doc-gather, doc-gap, doc-validate, doc-review, and doc-generate skills based on the requested pipeline mode.

• doc-plan

  Use this skill to produce a STRAT-level documentation plan. Traverses a strategic initiative's child epics and stories to identify what documentation is needed, what type, and at what priority.

• doc-post

  Use this skill to post validation and review findings as comments on a GitHub PR or GitLab MR. Reads workspace findings files and formats them as inline or summary comments.

• doc-review

  Use this skill to perform adversarial review of AsciiDoc documentation against context sources. Checks factual accuracy, completeness, consistency, and hallucination. Produces workspace/review-findings.json.

• doc-validate

  Use when you need to validate AsciiDoc documentation for technical accuracy using Extract-Identify-Validate pattern. Runs Vale, asciidoctor, lychee, YAML syntax checks, and LLM-powered cross-reference validation. Produces workspace/validation-findings.json.

• learning-mode

  Hands-on mentoring: the agent scaffolds work, then pauses so the engineer writes small, meaningful code (roughly 5–15 lines) for practice. Use when the user enables learning mode, asks for guided mentoring, hands-on practice, collaborative coding, or teaching while building a feature. author: Andre

• aipcc-commit-suggest

  Generate AIPCC Commits style commit messages or summarize existing commits

• gist-upload

  Use this skill to upload a summary or plan from the current conversation as a GitHub Gist using the `gh` CLI.

• git-shallow-clone

  Use this skill to perform a shallow clone of a Git repository to a temporary location.

• github-actions-debugger

  Debug and monitor GitHub Actions workflow runs. Check run status, view failed job logs, and troubleshoot CI failures. Use this when the user needs to investigate GitHub Actions failures, inspect job output, or identify the root cause of a broken workflow run.

• github-sync-upstream

  Sync code from an upstream GitHub repository into a target fork (e.g., opendatahub-io midstream). Detects remotes from the current repo, or clones fresh if run from outside. Fetches upstream, merges into a sync branch, restores protected files, resolves conflicts, and opens a PR to the target GitHub

• gitlab-pipeline-debugger

  Debug and monitor GitLab CI/CD pipelines for merge requests. Check pipeline status, view job logs, and troubleshoot CI failures. Use this when the user needs to investigate GitLab CI pipeline issues, check job statuses, or view specific job logs.

• email-meeting-summary

  Use when the user wants to summarize a Google Meet meeting and send the summary by email. Reviews a Google Meet transcript for a specific meeting topic, then composes a Gmail draft summarizing decisions and action items for that topic. Prompts for meeting selection if not specified, and for topic se

• gmail-draft

  Use this skill to compose a Gmail draft from text content in the conversation. Accepts a body, recipient list, and subject — either from the user or from context — and creates a draft in the user's Gmail Drafts folder via gws. author: dhellman version: "1.0" tags: gmail, email, draft, google-workspa

• google-workspace

  Fetch and query data from Google Workspace using the gws CLI — Gmail, Calendar, Docs, Sheets, Slides, and Drive. Use this skill whenever the user mentions email, inbox, messages, calendar, meetings, schedule, agenda, Google Docs, spreadsheets, presentations, or Drive files. Trigger on phrases like "

• acli-setup-check

  Verify acli installation and authentication. Checks if acli is installed, authenticated to Jira, and can query projects. Use when troubleshooting acli issues or setting up acli for the first time.

• ai-bug-fix-triage

  Triage JIRA bugs against repository code to classify AI fixability. Use when reviewing a backlog of bugs to determine which ones an AI agent can fix.

• aipcc-cve-report

  Generate CVE remediation instructions for the user's target RHAI product release or content channel from Jira JQL, ticket keys or a ticket description. Verify fixed packages in the RHAI package index and a matching RHAI base image (RHAIBI), or prepare a focused AIPCC build-request prompt.

• jira-activity

  Summarize Jira ticket activity, including child tickets, to detect stale tickets in the backlog. Use when user asks to review one or more Jira tickets to determine if they are being worked on.

• jira-aipcc-create

  Create AIPCC-org Jira issues in the RHAI project. Infers summary, description, type, and component from conversation context, confirms with the user before creating. Use when the user wants to file a new AIPCC Jira issue.

• jira-sprint-summary

  Generate comprehensive sprint summaries by analyzing JIRA sprint data, including issue breakdown, progress metrics, and team performance insights.

• jira-upload-chat-log

  Use this skill to export and upload the current chat conversation as a markdown file attachment to a JIRA ticket for later review and documentation.

• jira-workitem-attach

  Upload file attachments to Jira tickets. Verifies file exists and uploads via Jira API. Use when user wants to attach files to tickets.

• jira-workitem-comment

  Add comments to Jira tickets using simple text or Jira markup (ADF JSON). Supports rich formatting with code blocks, lists, mentions, and links. Use when user wants to comment on a ticket.

• jira-workitem-search

  Search Jira tickets using JQL queries. Provides common query templates and flexible output formats. Use when user needs to find or filter tickets.

• jira-workitem-view

  Retrieve and display full details of a Jira ticket. Fetches all fields and formats them for conversation context. Use when user needs ticket information or wants to examine a ticket.

• pr-jira-linker

  Find and link Jira issues to PRs/MRs that are missing Jira references. Supports single PR/MR linking and batch audit of configured repos. Use when the user mentions "link PR to Jira", "scan PRs", "PR audit", "MR missing Jira", "link merge request", or wants to connect code changes to Jira for tracea

• triage-bug-readiness

  Use when assessing a Jira bug ticket for AI autofix readiness. Produces a structured JSON verdict (ready/needs_info/not_fixable) based on a three-gate rubric. Designed for CI pipeline use with the jira-triage orchestrator.

• konflux-application

  Manage Konflux application

• konflux-component

  Manage Konflux component

• konflux-sandbox-onboarding

  Guide AIPCC engineers through obtaining access to the shared Konflux sandbox, onboarding a user-selected GitHub repository or dummy project, and verifying pull-request and push pipelines. Use when an engineer wants a hands-on Konflux staging experiment; exclude production tenants and release configu

• ai-gateway-operator-manifest-update

  Update batch-gateway manifests in opendatahub-io/ai-gateway-operator when the pinned llm-d-batch-gateway-operator main commit changes.

• odh-llm-d-release

  Orchestrate the opendatahub-io release for all llm-d components in one cycle. Collects upstream(llm-d) versions, auto-discovers the release tracker issue, then spawns parallel sub-agents — one per component (release branch, Konflux onboarder workflow, PR validation, approve+merge, Quay image verify,

• maas-nightly-qe-impact

  Assess whether a Models-as-a-Service autofix change requires follow-up in opendatahub-tests or ods-ci nightly QE pipelines. Runs as a Jira autofix post_review extension for the Model as a Service component. Appends a Nightly QE Impact section to the PR description and writes informational findings.

• module-compliance

  Check an ODH module operator repository for contract violations against the platform onboarding guide. Validates PlatformObject status, CRD structure, Helm chart content, webhook ownership, metadata conventions, and reconciler chain ordering. Use during code review or after scaffolding a new module.

• module-migrate

  Read existing in-tree ODH operator component code and produce a step-by-step extraction checklist for migrating it to a standalone module. Analyzes controller logic, webhooks, RBAC, embedded manifests, and DSC field mappings. Use when extracting a component from the monolithic operator into its own

• module-scaffold

  Given a component name, generate a complete standalone ODH module operator repository. Produces Go module, CRD types implementing PlatformObject, controller skeleton with reconciler builder pattern, Helm chart, Makefile, CI config, singleton webhook, and AGENTS.md. Use when starting a new module fro

• python-full-deps

  Resolve the full install-time dependency tree for a Python package. Use when the user needs all transitive dependencies, full dependency list, or install requirements resolved for a specific Python version with environment markers.

• python-packaging-binary-audit

  Scan a Python package repository for compiled/binary files using Fromager-style detection and malcontent YARA analysis, then triage findings with deterministic rules and AI reasoning to produce a structured risk report section.

• python-packaging-bug-finder

  Use when you need to find known packaging bugs, fixes, and workarounds for Python projects by searching GitHub issues and analyzing their resolution status

• python-packaging-complexity

  Use this skill to analyze Python package build complexity by inspecting PyPI metadata. Evaluates compilation requirements, dependencies, distribution types, and provides recommendations for wheel building strategies.

• python-packaging-env-finder

  Use this skill to investigate environment variables that can be set when building Python wheels for a given project. Analyzes setup.py, CMake files, and other build configuration files to discover customizable build environment variables.

• python-packaging-git-audit

  Inspect recent git history of a Python package repository for suspicious commits touching supply-chain-sensitive files, then triage findings with AI reasoning to produce a structured risk report section.

• python-packaging-license-checker

  Use this skill to check whether a Python package license is compatible with redistribution

• python-packaging-license-finder

  Use this skill to deterministically find license information for Python packages by checking PyPI metadata first, then falling back to Git repository LICENSE files using shallow cloning.

• python-packaging-security-audit

  Use this skill to evaluate the security of a Python package repository by orchestrating static analysis, binary scanning, and git history inspection sub-skills in parallel, then combining their results into a unified security report with a risk rating.

• python-packaging-source-finder

  Use this skill to locate source code repositories for Python packages by analyzing PyPI metadata, project URLs, and code hosting platforms like GitHub, GitLab, and Bitbucket. Provides deterministic results with confidence levels.

• python-packaging-static-audit

  Run hexora static analysis on a Python package repository to detect suspicious code patterns, then triage findings with deterministic rules and AI reasoning to produce a structured risk report section.

• torchtalk-analyzer

  Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.

• torchtalk-setup

  Install and configure TorchTalk MCP server for PyTorch cross-language analysis

• torchtalk-trace

  Trace a PyTorch function's cross-language binding chain (Python -> C++ -> CUDA)

• non-redhat-rpms

  Use this skill to identify non-Red Hat RPM packages installed in container images or on the local machine. For containers, pulls images across multiple architectures and release tags; for local scans, inspects the host directly. Extracts RPM signing metadata and reports packages not signed with the

• rpm-examine

  Analyze RPM build.log failures

• oci-cve-checker

  Use this skill to compare CVE vulnerabilities between two OCI container images and generate reports showing fixed and new CVEs.

• security-alert

  Use this skill to filter a pre-fetched set of Hacker News stories down to those that report supply-chain security threats relevant to the Red Hat / RHEL ecosystem, Python (PyPI/pip), or JavaScript/TypeScript (npm/yarn/pnpm). Reads stories from stories.json in the workspace, performs semantic analysi

• create-delivery-postmortem

  Use when a release delay, missed deadline, or delivery incident needs a structured post-mortem. Facilitates context gathering, timeline synthesis, and interactive Five Whys root cause analysis. Produces an executive-ready document in HTML or Markdown. author: AIPCC version: "1.0" tags: - postmortem

• engineer-snapshot

  Generate an engineer activity snapshot showing active JIRA issues with days open, blocked work, upstream PRs awaiting review, recently merged PRs, and open action items from 1:1 notes. Requires a team config YAML file. Use when the user asks to review an engineer's status, check someone's workload,

• team-weekly-report

  Generate a weekly team status report combining JIRA and GitHub data. Fetches closed, open, stale, and blocked issues plus PR activity for each team member. Requires a team config YAML file with JIRA project, GitHub repos, and team member mappings. Use when the user asks for a weekly report, team sta

• vllm-backport-check-backported

  Check which candidate PRs have already been cherry-picked into the downstream branch. Use after classify-and-filter to mark already_backported on each PR. Fully deterministic — compares merge SHAs and PR titles. author: ZhanqiuHu version: "1.0" tags: vllm, backport, triage

• vllm-backport-cherry-pick

  Auto cherry-pick backport candidates and create a draft PR on the downstream repo. Use after scoring to attempt clean cherry-picks for ai-fixable candidates. The agent must still do semantic validation on the result. author: ZhanqiuHu version: "1.0" tags: vllm, backport, triage

• vllm-backport-classify

  Classify bugfix PRs by type (runtime_bug, platform_specific, unclear, not_bugfix) and filter by file existence at a release tag. Use after fetching raw PRs to produce a filtered candidate list. PRs marked "unclear" need agent review. author: ZhanqiuHu version: "1.0" tags: vllm, backport, triage

• vllm-backport-fetch-prs

  Fetch merged bugfix PRs from vllm-project/vllm within a date window. Use when starting a backport triage run to get raw PR data from GitHub. Outputs a JSON array of PR objects with labels, authors, and merge commits. author: ZhanqiuHu version: "1.0" tags: vllm, backport, triage

• vllm-backport-push-report

  Push a triage report to GitHub under a timestamped directory in reports/. Use after the agent writes the report markdown and has ranked.json ready. Outputs the report URL to stdout. author: ZhanqiuHu version: "1.0" tags: vllm, backport, triage

• vllm-backport-score-rank

  Score and rank backport candidates using a composite formula based on verdict, severity, scope, risk, and self-containedness. Use after the agent completes semantic analysis to produce a prioritized ranked list. author: ZhanqiuHu version: "1.0" tags: vllm, backport, triage

• vllm-compare-reqs

  Use this skill to compare vllm requirements files between versions

• vllm-slack-summary

  Use this skill to generate slack summaries of vLLM CI SIG Slack channel activity for the RHAIIS midstream release team

Similar plugins