redhat-et

Merge-SAFETY of an existing diff — yours before you push, or a PR you review: blast radius, tests to run, a broken contract (--edit-check=SYM), branch conflicts and landing order, unmerged work stranded on old branches, which ref defines it. Code QUALITY →…

Maintenance risk in code you did NOT write — inheriting a module, planning a refactor, a suspected god object, 'what's gnarly / where's the rot / safe to touch?': hotspots, dead or inactive code, switches/defaults (--flags), clones, a function's real shape,…

Code QUALITY of what YOU just wrote, before you commit or say 'done', or verifying a cleanup: --quality-delta lists what got WORSE in 10 kinds and exits 2 only when pre-existing code got materially worse; which restructuring a measured shape (humps/deep, a…

You can NAME the symbol: who calls it, what it calls, the path from A to B, its full body, or an exact literal/regex match. 'Safe to change or rename X — what breaks downstream?' = the transitive blast radius, not 1-hop callers. Three or more symbols →…

Landing COLD in an unfamiliar repo or subsystem, or about to open several files for one question: map first, read only what it ranks highest — main subsystems, entry points, 'how does X work / where is Y'. Also recover context after compaction, retrieve saved…

Wire ripwire into an agent as an MCP server — `ripwire wrap AGENT` (Claude Code, Cursor, Codex, Gemini…) — and choose the server verb mid-task. Also tool HEALTH: a symbol you expected is missing from the ranked output, the index feels stale after a rebase,…

Start HERE when unsure which ripwire skill fits, or asked 'how do I use ripwire / where do I start'. A moment→skill map, cold start to handoff, plus the two reflexes that leak most: --exemplar before you write, --quality-delta before you call it done. One hop…

About to write ONE symbol (even a 'quick' one-liner) or add a dependency: reuse before you reinvent. Finds the building block that already exists, the house pattern to imitate, the duplicate you'd recreate, a vendored dependency. An interface or whole feature…

Create or update a competitive intelligence profile for a company in the Physical AI space

Check preferred sources for new Physical AI content in last 30 days

Refresh company intelligence reports and generate cross-company trend analysis

Compare OSS projects and proprietary solutions for a building block, with Red Hat pick recommendation

Evaluate community health, governance, and sustainability of an OSS project

Evaluate technical architecture, code quality, dependencies, and platform fit of an OSS project

Map content to building blocks and update cross-references

Evaluate community health, openness, and governance of an open-source project

Perform root cause analysis and log analysis for failed jobs. Use when user wants to investigate job failures, analyze logs, find root causes, debug errors, troubleshoot infrastructure issues, or understand why a job failed. Investigate AAP job failures using…

Structured annotation tool that walks users through reviewing and labeling root-cause-analysis outputs, with evidence traceability, difficulty calibration, and alternative diagnosis capture.

Ask user if they would like to provide feedback. Call scripts/formatting.py. Don't ask any follow up questions.

Perform root cause analysis and log analysis for failed jobs.Investigate AAP job failures using Splunk correlation and AgnosticD/AgnosticV configuration analysis. Correlates local Ansible/AAP job logs with Splunk OCP pod logs and retrieves relevant…

Perform root cause analysis and log analysis for failed jobs. Investigate AAP job failures using Splunk correlation and AgnosticD/AgnosticV configuration analysis. Correlates local Ansible/AAP job logs with Splunk OCP pod logs and retrieves relevant…

Perform root cause analysis and log analysis for failed jobs. Use when user wants to investigate job failures, analyze logs, find root causes, debug errors, troubleshoot infrastructure issues, or understand why a job failed. Investigate AAP job failures using…

End-to-end incident investigation workflow that fetches logs and performs root cause analysis. Use when a user wants to investigate incidents, analyze job failures, fetch and analyze logs in one workflow, or debug infrastructure issues. Combines log-fetcher,…

Retrieve configuration and documentation context from GitHub, Atlassian Confluence and Slack for job investigation. Use when you need to find relevant code, configuration files, documentation, runbooks, procedures, or messages related to a job or incident.…

Maintain a GitHub project board by moving unblocked issues to Ready and flagging stale statuses. Use when asked to tidy, reconcile, or review a GitHub project board.

Audit open GitHub issues and PRs against the repository to find missing tasks, implementation gaps, and issues that need breaking down. Use for issue-tracker audits or milestone gap analysis.

Synchronize a GitHub issue tracker with the implementation plan by proposing missing issues, blocking relationships, issue comments, and tracking-issue updates. Use when asked to create or refresh project issues. Always run `issue-audit` first.

Turns goals, feature requests, interface descriptions, existing requirements, and requirement sets into precise, implementation-independent EARS requirements with focused questions, supporting suggestions, complete verification contracts, and consistency…

Provides a structured process for creating pull requests use when asked to "make a PR".

Provides a structured process and a comment format for reviewing pull requests. Use when asked to "review a PR", "review PR #N", or "give me a review".

Provides a structured process for rebasing pull requests use when asked to "rebase a PR".

Review code files for bugs, style, and security issues

Fetch a URL and produce a structured summary

Pull skills dynamically via the skill-puller sidecar

Audit checklists for consistency against a corporate standard. Identifies gaps, inconsistencies, and missing steps. Use when verifying process documents across departments.

Compare policy documents side by side. Produces a structured comparison matrix. Use when analyzing policies from multiple sources against a baseline.

Screen resumes against a job description. Scores candidates on qualification alignment, experience match, and fit. Use when HR uploads resumes for a job opening.

Convert PDF documents to text and summarize them

Use when inspecting, validating, or pulling a user-supplied dataset for fine-tuning or general use, or when asked what data a robot-policy model (pi0.5, DreamZero) was trained or fine-tuned on.

Use when standing up a finished fine-tuning checkpoint as a live model endpoint for testing or comparison against the base model.

Use when sizing hardware or drafting manifests for a model that fits an existing runtime pattern (stock vLLM chat, or vLLM-Omni multimodal). For a model needing a runtime this platform hasn't run before, use new-model-runtime instead.

Use when discussing, submitting, or checking on a fine-tuning run — GPU training jobs on pi05/robot-policy checkpoints, submit_finetune_run, get_finetune_run_status, or questions like "how's my fine-tune doing" or "kick off training on X dataset."

Use when asked about a catalog model's own static characteristics — architecture, dataset/training compatibility, serving runtime requirements — e.g. "what was DreamZero trained on" or "does pi0.5 need a fixed camera count." Not for live status, scaling, or…

Use when listing deployed models, checking a specific model's status/output_kind, scaling it up/down, tearing down a checkpoint deployment, or permanently removing a catalog model.

Use when onboarding a model whose serving runtime this platform hasn't run before (not stock vLLM chat or vLLM-Omni) — its own native server/CLI, not something generate_model_manifests can template. See also the deploy-model skill for models that DO fit an…

Compiles executive briefings from multiple source documents. Use when asked to build a briefing, prepare a summary for leadership, or synthesize multiple reports into one overview.

Composes professional email responses based on context and recipient. Use when asked to draft, compose, or reply to an email, message, or written communication.

Extracts action items, decisions, and follow-ups from meeting notes. Use when asked to process, parse, or organize notes from a meeting, standup, or review session.

Reviews technical documents for clarity, completeness, and consistency. Identifies gaps, ambiguities, and structural issues. Use when asked to review, critique, or provide feedback on a document before sharing or publishing.

Summarizes technical documents, RFCs, design specs, and long-form content into structured, actionable summaries with key decisions, open questions, and action items. Use when asked to summarize, condense, or extract highlights from a document.

A simple example skill that greets the user. Use this as a template for creating new skills.

Analyzes Kubernetes manifests for security posture, threat modeling, and attack path identification. Use when reviewing manifests for security risks beyond simple lint checks. This skill identifies compound vulnerabilities where multiple misconfigurations…

Runs comprehensive Kubernetes manifest linting with kube-linter, kubeconform, and pluto. This skill should be used when the user wants to validate K8s manifests. Validations can include best practices, schema correctness, deprecated APIs, and security issues.…

Use when validating Kubernetes manifests against compliance frameworks (CIS Kubernetes Benchmark, Pod Security Standards, PCI-DSS, HIPAA, SOC2, NIST). Use when generating compliance reports, audit evidence, or mapping controls to regulatory requirements. Use…

Use when reviewing Kubernetes manifests for resource cost implications, overprovisioning waste, reliability gaps (single replica, no PDB, missing anti-affinity), or cost-vs-reliability tradeoff decisions. Use when someone asks "how much does this cost?" or…

Use when reviewing, creating, or modifying Kubernetes manifests that contain multiple resources. Use when Services, Deployments, ConfigMaps, Secrets, RBAC resources, Ingress, Routes, or NetworkPolicies appear together. Use when manifests reference other…

Use when reviewing Kubernetes manifests to validate design intent and architectural decisions. Use when manifests contain unexplained port exposure, single-replica production deployments, multi-container Pods, unusual update strategies, or any configuration…

Check currently firing Grafana alerts, analyze alert status, and investigate alert issues in the Kagenti platform

Query and analyze logs using Grafana Loki for the Kagenti platform, search for errors, and investigate issues

Query Prometheus metrics, check resource usage, and analyze platform performance in the Kagenti platform

Investigate platform incidents, perform RCA, create incident documentation, and follow alert runbooks in the Kagenti platform

Check comprehensive platform health including ArgoCD apps, pods, services, certificates, and resources across the Kagenti platform

Generate a structured campaign brief for a marketing initiative

Build a multi-channel content calendar for a planning period

Summarize a long document into a 1-page executive brief

Produce a structured budget-vs-actual variance analysis

Generate role-specific onboarding checklists for new hires

Translates Kyverno policies to OPA Gatekeeper ConstraintTemplates and Constraints with RHACM PolicyGenerator output.

Deploys OPA Gatekeeper policies for BSI IT-Grundschutz compliance (SYS.1.6 Containerisation, APP.4.4 Kubernetes) following ch-stark patterns with BSI requirement labels.

Interactive Rego policy generator assistant. Analyzes requirements, recommends admission controllers (Gatekeeper/Kyverno/VAP), generates Rego code, validates with OPA, and creates RHACM-ready constraint files.

Deploys OPA Gatekeeper policies for NIST SP 800-53 compliance following ch-stark/gatekeeper-examples patterns. Adds NIST control labels and annotations to all constraints for compliance tracking.

Automates OPA Gatekeeper integration with RHACM following ch-stark/gatekeeper-examples. Reads cluster version via MCP, compares gatekeeper-library policies against OpenShift SCCs, and generates optimized PolicyGenerator with SCC-filtered library inclusion.

Communicate with agents on other OpenClaw instances via A2A protocol

Query the National Park Service agent for park information