rhoai-security-reviewer

Plugin rhoai-security-reviewer from marketplace opendatahub-skills in opendatahub-io/skills-registry. Commands read from the repo's manifest — 8 days ago.

Skills (29)

• bench-answer-flat

  Answer architecture question using flat file access (Read/Glob/Grep)

• bench-answer-query

  Answer architecture question using arch-query CLI

• bench-judge

  Score a benchmark agent's answer against ground truth using a 4-dimension rubric

• bug-completeness

  Score bug report completeness (0-100)

• bug-context-map

  Map bug to available architecture context

• bug-fix-attempt

  Attempt to produce a fix for a bug

• bug-test-plan

  Generate a comprehensive test plan for a bug

• bug-write-test

  Write QE tests for opendatahub-tests based on a fix attempt and test plan

• doc-gap

  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

  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

  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

  Full pipeline orchestrator. Sequences doc-gather, doc-gap, doc-validate, doc-review, and doc-generate skills based on the requested pipeline mode.

• doc-plan

  STRAT-level documentation planning. Traverses a strategic initiative's child epics and stories to produce a systematic doc plan identifying what documentation is needed, what type, and at what priority.

• doc-post

  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

  Adversarial review of AsciiDoc documentation against context sources. Checks factual accuracy, completeness, consistency, and hallucination. Produces workspace/review-findings.json.

• doc-validate

  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.

• epic-create

  Create RHOAIENG epics from an approved RHAISTRAT strategy. Only creates epics (not child tasks, stories, or spikes). Requires the strategy to have passed review (recommendation: approve) and security review (verdict: PASS). Use when the user says "create epics for RHAISTRAT-XXXX" or invokes /epic-cr

• epic-submit

  Create Jira tickets from epic-task artifact files and update frontmatter with Jira keys

• explain-claims

  Explain why a contradicted or insufficient-evidence claim was produced by correlating source artifacts, verification evidence, job logs, traces, and tool activity. Use after verification to route improvements to skills, context, retrieval, workflows, tools, models, policies, or human-owned sources.

• extract-claims

  Extract atomic, context-preserving factual claims from AI-generated pipeline artifacts, write durable claim files, and ingest them into Observatory. Use for issue-scoped or artifact-scoped claim analysis before verification.

• patch-validation

  Validate a patch using odh-tests-context recipes

• security-reviewer

  Independent security reviewer for multi-reviewer consensus. Checks risk pattern catalog and performs creative exploration against a STRAT's threat surface inventory.

• skill-review

  Review and validate Claude Code skills for completeness, packaging correctness, and marketplace compatibility. Use when reviewing a skill, checking skill packaging, validating SKILL.md before publishing, or running /skill-review. Checks frontmatter, file references, variable substitution, and extern

• strat-security-review

  Security review of STRAT documents using multi-reviewer consensus. Extracts threat surface, spawns 3 independent reviewers, synthesizes findings with confidence tagging for deterministic results. Use when the user says "security review RHAISTRAT", "run security review", "strat security review", or i

• strat.create.local

  Create RHAISTRAT Jira tickets from approved RFEs using local MCP+REST API approach.

• strat.security.review

  Security review of STRAT documents using multi-reviewer consensus. Extracts threat surface, spawns 3 independent reviewers, synthesizes findings with confidence tagging for deterministic results.

• strat.submit

  Push refined strategy content back to RHAISTRAT Jira tickets. Reads local strat-task artifacts, updates the Jira ticket description with the full strategy content, and applies a label to mark submission.

• verify-claims

  Verify extracted claims against version-appropriate source material and architecture context, record evidence-backed verdicts, and submit them to Observatory. Use only after claim extraction; do not infer forensic root cause in this stage.

• unit-convert

  Convert units between measurement systems (imperial mode)

Similar plugins