Re-derive something written into the shortest version that still covers everything. Use when something already written should get shorter and nothing it covers can be lost.

One committed verdict on something that exists, cited. Use when something exists and a claim about it needs a verdict.

Find the route to guaranteed failure, negate it. Use when a goal keeps not being reached head-on.

Put one settled thing in the user's head, plainly. Use when the user does not hold something already settled.

Draw out what the user holds but can't say. Use when the user knows something they cannot yet express.

Build the thing the user can't specify, choices surfaced. Use when the user needs something to react to before they can choose.

Plan the skills an ask needs, invoke each as its condition arrives. Use when the ask has multiple aspects that different skills carry, or the user named multiple skills.

Turn words with two readings into one confirmed ask. Use when the user's words admit two readings that would build different things.

Rewrite a rule so anyone applies it the same way. Use when a stated rule or claim takes the reader's judgment to apply.

Use when adding or changing a skill, hook, or runtime file in this repo — including deciding which unit a new capability should be.

Run the upstream Flux controller patch release procedure for helm-controller, image-automation-controller, image-reflector-controller, kustomize-controller, notification-controller, source-controller, and source-watcher. Use when preparing a new controller patch release from a release series branch, drafting changelog entries, tagging releases, and opening the follow-up changelog PRs back to main.

What it does: Chainlink Confidential AI Attester (alpha) runs an LLM inside AWS Nitro Enclave/TEE over private documents and returns the model result; raw documents do not leave TEE. When to use: trigger on private inference, attested AI, TEE inference, confidential AI, or sensitive-document analysis, including lending, accredited-investor, KYC/AML, and proof-of-reserves. Key capabilities: submit document resources, choose model, request structured JSON, poll completion, and use the result without exposing source documents onchain. Do not use for generic TEE/enclave work without document inference; use CRE Confidential Workflows for confidential Chainlink workflow logic. Do not trigger on generic confidentiality/TEE/enclave requests that involve no document upload or private inference — a user who wants a Chainlink workflow's own logic or data kept confidential from node operators, with no document analysis involved, wants CRE Confidential Workflows, which chainlink-cre-skill covers.

Creates the plugin's own Python environment and installs or upgrades mixpanel_headless (0.3.0 or newer) with pandas, numpy, matplotlib, seaborn, networkx, anytree, scipy, and pyarrow (Python 3.11+ only) on Python 3.10+, then checks the imports, mp help, and the credentials. Use when setting up Mixpanel analysis, or when the plugin environment is missing or older than 0.3.0. Do not use for login or account changes (use auth).

Analyzes Mixpanel data with Python, the mixpanel_headless library, and pandas. Use when the user asks about their Mixpanel data, such as event trends, DAU/WAU/MAU, funnels, retention and churn, user paths, user profiles, cohorts, a user's tracked event history (activity feed), segment comparisons, revenue, feature adoption, or experiment results. Also use to explore a project's events and properties, build a custom property or cohort, share a query as a report link, read or write business context, or manage entities such as cohorts, feature flags, experiments, alerts, annotations, webhooks, Lexicon definitions, and other governance objects, or when code runs mixpanel_headless queries or `mp query` / `mp inspect`. Do not use for adding tracking to an app's source code, for what a specific user did on screen (use session-replay), for building or editing dashboards (use dashboard-expert), for logging in, credentials, or switching accounts (use auth), or for installing the library (run /mixpanel-headless:setup).

Analyzes, builds, modifies, and adds explainer text cards to Mixpanel dashboards with the mixpanel_headless Python library. It reads a dashboard's layout and runs every report on it, creates dashboards with text cards and a grid layout, edits cells and rows in place, and writes data-driven explainer cards. Use when the user asks to analyze, summarize, explain, build, create, redesign, update, reorganize, or clean up a Mixpanel dashboard; asks about dashboard layout, rows, cell widths, text cards, or which chart type suits a board; or wants to turn queries into reports placed on a dashboard. Do not use for general analytics questions or one-off queries (use mixpanelyst), or for what a specific user did in a session recording (use session-replay).

Programmatically interact with Domino using python-domino SDK and REST APIs. Covers authentication, running jobs, managing projects, file operations, model deployment, and automation. Use when automating Domino workflows, integrating with CI/CD, or building custom tooling around Domino.

Deploy and monitor model API endpoints in Domino. Covers creating prediction endpoints, version management, Grafana dashboards for latency/errors/resources, alerting, and GPU inference with NVIDIA Triton. Use when deploying models as APIs, monitoring production endpoints, or debugging endpoint issues.

Create, run, and manage Domino Jobs - batch executions for scripts, training, and data processing. Covers job configuration, hardware tiers, scheduled jobs (cron), monitoring status, viewing logs, and API-driven execution. Use when running batch workloads, scheduling recurring tasks, or automating training pipelines.

Trace and evaluate GenAI applications including LLM calls, agents, RAG pipelines, and multi-step AI systems in Domino. Uses the Domino SDK (@add_tracing decorator, DominoRun context) with MLflow 3.2.0. Captures token usage, latency, cost, tool calls, and errors. Supports LLM-as-judge evaluators and custom metrics. Use when building agents, debugging LLM applications, or needing audit trails for GenAI systems.

Deploy web applications to Domino Data Lab with expertise in React apps (Vite) behind Domino's reverse proxy. Covers app.sh configuration, port configuration, base path handling for SPAs, CI/CD with GitHub Actions, and proxy troubleshooting. Use when deploying apps to Domino, setting up CI/CD pipelines, fixing broken routing, or configuring JavaScript frameworks for Domino's proxy.