autofix-resolveUse when orchestrating a Jira ticket fix end-to-end. Dispatches to implement and review prompt agents in a loop, uses state.py for persistence, and evaluates findings to decide iteration. Never writes code directly.autofix-repo-resolveDisambiguate which repository URL is the actual target when a Jira ticket mentions multiple repos. Reads ticket context and candidate URLs, classifies each URL, and writes a verdict with the target and confidence level.debug-autofix-skillsInvestigate agent-side failures in the autofix-skills plugin. Covers wrong verdicts, review loop issues, state machine bugs, and prompt problems. Use when the agent ran but produced wrong results.autofix-triageUse 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 autofix pipeline orchestrator.autofix-cve-resolveUse when orchestrating CVE remediation for a Jira Vulnerability ticket. Uses a Python state machine (cve_pipeline.py) for deterministic routing between scan, fix, verify, VEX, review, and PR creation agents. Never writes fix code directly.
仓库浏览
opendatahub-io · 仓库与代表性 skills - 第 2 页
按仓库查看 36 个 GitHub 仓库中的 315 个已收集 skills。
odh-monitor-communityMonitor ODH community release progress with automated PR tracking and completion assistanceodh-onboardInteractively onboard new ODH components with guided questions and validationodh-registerInteractively register ODH components for releases with guided questions and validationodh-set-next-releaseInteractively plan ODH releases with guided date calculations and mode selectionodh-trigger-releaseIntelligently trigger ODH releases with component readiness preview and fallback guidance
debug-agentic-ciInvestigate infrastructure-level failures in the agentic-ci framework. Covers container backend issues, skill engine errors, forge MR/PR failures, and gate problems. Use when the container failed, MR operations broke, or the skill engine returned errors.test-e2e-openshellRun end-to-end tests for the openshell backend using real container and API callsrelease-agentic-ciCut a new agentic-ci release by tagging and pushing. Version is derived from git tags automatically.test-e2e-podmanRun end-to-end tests for the podman backend using real container and API calls
add-benchmarkGuide for adding a new benchmark to benchmarks/, covering the Dockerfile, ClusterTrainingRuntime, TrainJob, and CI workflow. Use when adding or modifying benchmarks.add-e2e-testGuide for writing E2E tests in tests/, covering namespace isolation, resource naming, cleanup, tags, notebook editing, and environment variables. Use when adding or modifying E2E tests.update-support-libGuide for modifying the shared test support library in tests/common/support/, covering getters, condition checkers, the client abstraction, and the option pattern. Use when changing shared test infrastructure.
onboard-konflux-components-for-odh-and-rhoaiMaster orchestrator skill for the full ODH/RHOAI component onboarding pipeline. Idempotent — run any number of times for the same Jira. Each run syncs PR/MR state, executes newly-unblocked steps, and posts a summary of what changed. Transitions Jira through…create-component-onboarding-jiraInteractively collects ODH/RHOAI component onboarding parameters from the user, generates a validated component_onboarding_details.yaml, and creates or updates a Jira ticket with the YAML attached. When no Jira URL is provided, automatically creates a new…validate-component-onboarding-jiraPre-flight validation tool for ODH component onboarding. Given a Jira issue URL, fetches issue details, downloads the component_onboarding_details.yaml attachment, and validates it against the JSON Schema. Use before invoking the full onboarding automation to…
release-versionPrepare version bump PRs and releases for mod-arch-library. Use when the user asks to prepare a release, bump version, create a release PR, or publish packages.review-dependabotReview all open dependabot PRs in the repo, check CI status, and approve+merge those that pass. Invoke with /review-dependabot.reviewReview code for design token violations, SCSS convention drift, and theme wrapper compliance. Compares source files against pf-tokens-SSOT.json, MUI-default-theme-object.json, and the project's styling rules. Use when the user asks to review code, audit…
knowledge-extractionIngest enriched failure reports into the LLM wiki and maintain an examples catalog of real incidents and their fixes.enrich-reportsEnrich case study skeletons with analysis-derived lessons, error signatures, fix types, and prevention advice. Non-interactive.knowledge-repoScan merged PRs and propose updates to AI context files (CLAUDE.md, AGENTS.md) and skill files (SKILL.md, prompts) as a git-apply-able patch. Non-interactive.
failure-analysisAnalyze a CI/CD test failure log to identify the root cause and produce a structured verdict.false-alarm-detectionClassify a test failure as a known infrastructure false alarm or a genuine test bug by comparing the log against pluggable pattern definitions.failure-matchingMatch a test failure against historical Jira tickets to find known issues.
analyze-pluginAnalyze a plugin's source repository and generate enriched documentation content with presentation-quality SVG diagrams for the skills-registry documentation site. Use when the user wants to document a plugin, generate diagrams for skills, create enriched…generate-siteOrchestrate full documentation site generation for the skills-registry — structural pages from registry.yaml plus AI-enriched content and presentation-quality SVG diagrams for all plugins. Use when the user wants to rebuild the docs, update the website,…
central-linter-releaseRelease a new version of central-linter. Handles the full two-phase workflow: opening a version bump MR, then publishing the GitLab Release after merge so Renovate updates client repos.repo-reviewerPerform code reviews for central-linter with focused feedback on critical issues
pipeline-rcaRoot cause analysis for a CI/CD pipeline failure error group. Reads trace logs and preprocessed errors, investigates the root cause, and produces structured section files and finding.json.pipeline-groupingGroup failed CI/CD pipeline jobs by shared root cause using preprocessed error files and Jira ticket deduplication. Reads job manifest and error logs from the workspace, produces grouping.json.