Use when a question, decision, plan, tradeoff, or claim needs a rigorous verdict and one perspective is not enough. Spawns a panel of 3 to 5 subagent jurors that form independent blind opinions, deliberate anonymously under an anti-anchoring and anti-sycophancy protocol, and return one committed verdict with confidence, preserved dissent, and a concrete next action. Domain-agnostic across engineering, architecture, data, product, hiring, strategy, vendor choice, build-vs-buy, and research design. Trigger phrases include "convene a jury", "have agents debate and decide", "get a panel to decide", "multi-agent decision", "stress-test this and decide", "monte um juri", "tribunal de agentes", "painel para decidir". Do NOT use to only critique without deciding (use the-fool for that), to build a plan or write the solution itself, or for simple factual lookups.

Customize and extend Zensical documentation sites with interactive pages, custom templates, JavaScript widgets, and CSS styling. Use when working on documentation site customization including: (1) creating custom or interactive doc pages, (2) adding JavaScript widgets or third-party libraries to docs, (3) overriding templates or partials, (4) adding/modifying CSS styles, (5) creating custom page layouts (landing pages, demos, dashboards), (6) configuring zensical.toml settings, (7) integrating external JS frameworks into doc pages. Triggers on: docs site, documentation page, interactive demo, custom template, zensical, extra_css, extra_javascript, overrides, template block, page layout, widget integration. Do NOT use for: writing or editing markdown documentation content, general MkDocs questions (this is Zensical-specific), or reading/viewing existing docs pages.

Configure TrustyAI model monitoring for bias detection and data drift on deployed InferenceServices. Use when: - "Monitor my model for bias" - "Set up drift detection on my inference endpoint" - "Configure TrustyAI for my deployed model" - "Check if my model has fairness issues" - "I need SPD / DIR metrics for my model" Handles TrustyAIService deployment, bias metric configuration (SPD, DIR), drift metric configuration (MeanShift, FourierMMD, KS-Test, Jensen-Shannon), threshold tuning, and monitoring validation. NOT for deploying models (use /model-deploy first). NOT for input/output content safety guardrails (use /guardrails-config). NOT for infrastructure-level observability (use /ai-observability).

Create and configure Data Science Projects on OpenShift AI with namespace setup, S3 data connections, pipeline server, and model serving enablement. Use when: - "Create a data science project" - "Set up a new namespace for ML work" - "Add an S3 data connection to my project" - "Configure the pipeline server" - "Enable model serving on my project" Bootstraps an RHOAI Data Science Project with proper labels, data connections, pipeline infrastructure, and model serving configuration. NOT for deploying models (use /model-deploy). NOT for creating workbenches (use /workbench-manage). NOT for managing pipelines after setup (use /pipeline-manage).

Troubleshoot failed or slow InferenceService deployments on OpenShift AI. Use when: - "My InferenceService won't start" - "Model deployment is stuck" - "Inference endpoint returns errors" - "Model is slow / high latency" - "GPU scheduling failed for my model" Progressive diagnosis: status conditions, events, pod logs, GPU health, and observability analysis. NOT for deploying models (use /model-deploy). NOT for creating runtimes (use /serving-runtime-config).

This skill should be used when the user asks to "convert this PDF to markdown", "convert this image to quarto", "turn my diagram into mermaid", "transcribe my notes", "sketch to text", "scribble to quarto", "turn this sketch into a document", "process my Boox export", or provides a JPEG/PNG/PDF file path and wants it converted to structured text. Converts handwritten notes and diagrams (from Onyx Boox or any source) into Quarto (.qmd) or Markdown with Mermaid diagrams.

Generates abstract invariants using domain abstraction — intervals, octagons, polyhedra, sign domains — to find invariants that concrete reasoning misses. Use when standard invariant inference fails, when the invariant involves relationships between multiple variables, or when verifying numerical code.

Generates code test-first — writes a failing test from a requirement, then generates the minimal code to pass it, then refactors, in strict red-green-refactor cycles. Use when building new features where the spec is clear, when the design is uncertain and you want tests to drive it, or when you need high confidence in coverage from the start.

Generates metamorphic tests — tests that check relationships between multiple runs instead of checking exact outputs, useful when the correct output is unknown or expensive to compute. Use when there's no oracle, when testing ML/numerical/search code, or when the spec describes properties rather than values.

Sets up taint tracking by defining sources, sinks, and sanitizers from Project CodeGuard's input-validation taxonomy, then configures the target tool (CodeQL, Semgrep, custom instrumentation). Use when wiring taint analysis into CI, when the user asks for taint tracking, or when you need a source/sink catalog for a specific language.

Recommends the specific code change to remediate a detected vulnerability by dispatching on CWE to the matching Project CodeGuard rule's prescribed fix pattern. Use after a finding has been confirmed and located, when the user asks how to fix a vulnerability, or when generating remediation PRs.

Proves two program fragments semantically equivalent using symbolic reasoning — stronger than testing, applicable when differential testing is insufficient or impossible. Use when behavior preservation must be proven rather than sampled, when the input space is too large to enumerate, or when a transformation needs a correctness argument.

Extracts language-agnostic pseudocode from real code, stripping syntax noise and language-specific machinery while preserving the algorithmic structure. Use when documenting an algorithm for a paper or spec, when porting and wanting a neutral intermediate, or when explaining code to someone who doesn't know the source language.

Translates a single function or small code unit between programming languages, mapping idioms and preserving observable behavior. Use when porting one function, when the user pastes code and asks for it in another language, or as the per-unit primitive for larger migrations.

Generates code comments that explain non-obvious intent, constraints, and tradeoffs — not what the code already says. Use when code is correct but opaque, when documenting for future maintainers, or when a function's why is harder to see than its what.

Gong API for searching calls, transcripts, and conversation intelligence. Use when working with Gong call recordings, sales conversations, transcripts, meeting data, or conversation analytics. Supports listing calls, fetching transcripts, user management, and activity stats.

Read Google Analytics 4 reporting data through the GA4 Data API. Use for explicit GA4 property metadata, compatible metric/dimension reports, traffic analysis, key events, quotas, and bounded exports.

End-to-end GitHub repository maintenance for open-source projects. Use when asked to triage issues, review PRs, analyze contributor activity, generate maintenance reports, or maintain a repository. Triggers include "triage", "maintain", "review PRs", "analyze issues", "repo maintenance", "what needs attention", "open source maintenance", or any request to understand and act on GitHub issues/PRs. Supports human-in-the-loop workflows with persistent memory across sessions.

Infrastructure as Code with Terraform and Terragrunt. Use this skill whenever the user mentions Terraform, Terragrunt, HCL, or infrastructure as code. Triggers include writing or reviewing .tf files, creating reusable modules, debugging terraform plan/apply errors, managing remote state and locks, fixing state drift, setting up CI/CD for Terraform, scaffolding new modules, validating module structure, and implementing Terragrunt DRY patterns across environments.

This skill should be used when the user says "ensure config", "check arn infra config", "arn-infra-ensure-config", "verify arn infra setup", or wants to verify that Arness Infra configuration is present for the current project. This skill is primarily consumed as a reference by entry-point skills (arn-infra-wizard, arn-infra-assess) which read the `references/step-0-fast-path.md` reference as Step 0 before proceeding with their workflow.