Set up the AWS side of a Temporal serverless worker — IAM role, Lambda function, and deploy — so the Worker Controller can scale workers from zero and you can exercise serverless worker deployments in the UI. Use when asked how to create the Lambda or IAM role for serverless workers, what to put in the Create Serverless Deployment form, or why an invoked Lambda never connects.

Release workflow for the Stave repository that confirms whether the next release is patch or minor before bumping the version, reviews the actual PR changes and PR description `Changes` sections in the release scope instead of relying on commit titles alone, generates release notes with `conventional-changelog`, and opens a pull request against `main` from a dedicated temporary release worktree so the user's original checkout stays on its original branch. Use when the user asks to cut the next release, ship the current changes as a versioned release, or prepare a release PR. After the PR merges, the repository's GitHub Actions workflow builds and publishes the release artifacts automatically.

Governs how to examine, write, fix, and run tests in the rc-unified-crm-extension monorepo. Use when writing new tests, debugging failing tests, examining test coverage, adding tests for new features or connectors, or asking about test conventions, test structure, mocking strategies, or running tests.

Run a RediSearch end-to-end macro benchmark from tests/benchmarks/*.yml via redisbench-admin. Use this when you want to measure whole-module performance (throughput/latency) against a real redis-server, not micro Rust or C++ benchmarks.

Apply IRQL graph functions to KQL or IRQL query results for Kusto Explorer visualization. Generates Lift_To_Graph mappings and composes Graph_Render_View, Graph_Fold_By_Property, Extract_Node_*, Enrich_Node_*, and Enrich_Graph_* calls. Accepts a supplied query or limited basic natural-language source request; it is not a general natural-language-to-KQL/IRQL skill. WHEN: Lift_To_Graph, Graph_Render_View, Graph_Fold_By_Property, IRQL graph enrichment, graph mapping for existing query results, icon-decorated graph, fold graph nodes. Use azure-kusto-graph for native make-graph analysis, graph-match, shortest paths, components, or persistent graphs.

Use the `cursorctl` CLI (Cursor SDK Bridge) to spawn, send, detach, follow up, inspect, and collect Cursor cloud or local agents. Trigger when delegating work to Cursor cloud agents (`bc-…` IDs), running a local Cursor agent, fire-and-forget with `--detach`, polling `run get`/`wait`/`watch`, collecting artifacts or conversations, managing `cursorctl auth` profiles, or troubleshooting the SDK Bridge. Run cursorctl via Bash. Do not call the SDK Bridge HTTP API directly.

Guided git workflows: prepare PRs, clean up branches, resolve merge conflicts, handle monorepo tags, squash-and-merge patterns. Use when asked to prepare a PR, clean branches, resolve conflicts, or tag a release.

Run an independent code review using the OpenAI Codex CLI in headless mode. Gets a second opinion from a different model family (the current Codex models) on recent changes, a PR, a commit, or the whole app — covering bugs, regressions, security, data consistency, UX/state bugs, performance risks, and testing gaps. Saves a severity-prioritised report to .jez/reviews/. Triggers: 'codex review', 'review with codex', 'independent code review', 'what does codex think', 'get codex to review'.

Sync, update, and validate the OpenAPI specification (backend/openapi.yml) against the Flask API routes. Use whenever endpoints have been added, changed, or removed, or when the user mentions API docs, swagger, OpenAPI, endpoint documentation, "update the spec", or has just added/modified a route or resource class. Also use when checking for drift between the code and the spec.

Filter large Sentry Scraps design-system migration PRs for review by separating mechanical import-path changes, generated baseline updates, snapshot mocks, and pure renames from substantive destination-component and logic changes. Use when asked to review a large "ref(scraps)" PR, a "move component into Scraps" PR, or to filter Scraps migration noise. Do not use for general refactors or migrations outside getsentry/sentry.

Bumps an existing Python dependency in getsentry/sentry through the repository's self-serve GitHub Actions workflow. Use when asked to update, upgrade, or bump a Python package version in Sentry. Does not apply to new dependencies, JavaScript packages, or informational questions about dependency management.

Add a new Seer embed widget — a rich component rendered inline in Seer's markdown output via tag syntax. Covers schema, component, registration, and backend codegen. Use when asked to "add an embed", "new seer embed", "create a seer widget", "add a markdown widget", "new seer tag", or "embed widget".

MUST be used when adding AI, Atlas, an agent, a chat UI, or LLM features to a Flows/Fusion app. Use the Atlas/EOS sidebar via @cognite/app-sdk — not useAtlasChat, vendored atlas-agent, or per-row chat completions. Triggers: atlas, EOS, PAIA, agent chat, chat UI, sendAgentMessage, sendAgentLayoutMode, registerAgentServer, connectToHostApp, useAtlasChat, LLM. In-app chat: integrate-atlas-chat only if the host sidebar cannot work.

MUST be used when a Flows/Fusion app needs to read state it was launched with — a deep link, a shareable URL, or startup/bootstrap arguments set by a host embedding the app (e.g. a Flows dashboard widget). Triggers: initialState, connectToHostApp initialState, startup arguments, bootstrap state, initial state, deep link, restore state on mount, syncInternalState, customAppInternalState.

Final gate of the Flows app certification flow for external submission. Verifies that flows-app-brief, flows-code-review, and flows-design-review have all been run and are in a passing state (App-Brief.md complete, 0 Must Fix in latest code review, design average ≥ 3.8), then runs `npx @cognite/cli apps submit` to zip the repo and pre-populate the submission form. Use when the user asks to submit a Flows app for certification, run flows-external-app-submit, or finalize an app for external review.

Search, read, draft, create, update, or transition Jira Cloud issues; use for comments, labels, acceptance criteria, and JQL.

Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU selection, data downloading inside functions, and result handling.

Anti-slop discipline for AI agent behavior across ALL domains — code, design/UI, security, writing, research, data, creative/media. Use whenever the agent risks doing unasked work, silently skipping part of what was asked, guessing instead of asking or checking, fabricating facts/citations/security claims, laundering unverified tool output as personal fact, hedging vaguely to dodge evidence, or letting an already-sent error stand uncorrected. Triggers: ai slop, slop, ngarang, jangan ngarang, unasked work, jangan kerjain yang belum diminta, kerja setengah, skip diam-diam, bukti bukan klaim, hallucination, halu, proofread, asal kerjain, klaim desain, klaim aman, ngarang sumber, ngarang riset, cacat logika, jawaban ngambang. Always read references/laws.md with this file; read the other references/ files when relevant.

Resolve common penetration testing issues in Ark. Use when fixing security vulnerabilities from pentest reports, security audits, or OWASP Top 10 issues.

Hyperflow memory manager. Use to view, search, add, edit, prune, or clear hyperflow project memory — "show memory", "search memory for X", "clear memory", "what does hyperflow remember about Y". CRUD over .hyperflow/memory/ only — never touches source code.