Read when reviewing a plugin PR or auditing an existing plugin script (server/plugins/*/script.py or equivalent). Covers four checks not already mechanically enforced by test_plugin_conventions.py - plugin scripts embedding their own raw SQL instead of an existing/new model method, suspicious/attacker-influenced plugin data not being logged, a new dependency not reaching every build target, and scanPresence correctness for a roster/inventory-style plugin - plus worked real-PR examples.

Write or review a NetAlertX plugin's README.md (server/plugins/<code_name>/README.md). Use this when asked to create, enhance, audit, or clean up a plugin README, or plugin docs generally.

Create and run NetAlertX plugins. Use this when asked to create a plugin, run a plugin, test a plugin, or develop plugin functionality.

Read before designing a feature that writes to the Devices table, adding audit/history logging, or choosing between a SQLite trigger and a Python hook. Covers the full Devices write-path inventory, the FIELD_SOURCE_MAP *Source attribution system, and event-sourced vs snapshot audit logging tradeoffs.

NetAlertX database architecture patterns. Use this when designing features that write to the Devices table, implementing audit/history logging, or choosing between trigger-based vs Python-hook approaches.

Use when drafting GitHub release notes for a Warp feature or bugfix release from Towncrier fragments or a tagged final changelog.

Creates virtual try-on agents supporting image and video (catwalk animation) try-ons on Google Cloud (Gemini image models and Veo on Gemini Enterprise Agent Platform). Handles resource setup, user photo uploading, image/video generation pipelines, local testing, and evaluation.

Creates product search agents with semantic search and RAG on Google Cloud (Vertex AI Vector Search, BigQuery, embeddings). Use when the user wants to "build a product search agent", "create an e-commerce search", "make a shopping assistant", "set up semantic catalog discovery", "ingest products into Vector Search", or "deploy a retail RAG agent". Handles the full pipeline: catalog data ingestion to BigQuery, Vertex AI Vector Search collection setup, ADK agent scaffolding, evaluation, and Cloud Run deployment.

Answer questions about how the adk-recipes repo itself is governed — CI and workflow behavior, the limits and thresholds in .github/policy.yml and the reasoning behind them, CODEOWNERS routing, what the bots (stale sweep, Dependabot, recipe canary, AI review) do, how the repo is organised (core vs contrib vs skills verticals), what the repo skills and validators cover, when a rule last changed and which PR changed it, what a label means, and the admin runbooks for changing any of it. Also answers generic contribution-process questions from docs/ — how a recipe is prepared and validated, what a field in manifest.yaml means, what a runnability test is, what a README must contain, what a named CI error means. On explicit request it also traces which files consume a config key, and audits whether the repo still obeys its own policy. STRICTLY READ-ONLY — it never edits, commits, comments, labels, or performs a task on the caller's behalf, even when asked directly; it cites the source file and describes the change for a human to make. A request to do the work is answered rather than obeyed — it says it is read-only, names the skill that does the work, and gives the guidance. Use when someone says "oracle", or asks how/why/who about this repo's own configuration, CI, governance, or layout. Don't use for writing or preparing a recipe (use prepare-python-recipe, generate-manifest, align-recipe-pyproject and friends), for ADK API questions (use the google-agents-cli-* skills), or for anything needing the caller's screen — a failing check on their PR, their working tree, their branch.

Makes an existing Python recipe deployable: generates the serving files a container needs (Dockerfile, .dockerignore, fast_api_app.py, app_utils/a2a.py, app_utils/services.py, app_utils/reasoning_engine_adapter.py) and configures the recipe to match (required serving dependencies, the App object in agent.py, the hatch wheel package, manifest.deployable). Interactive by design — it asks the recipe owner about runtime data directories and stops for a human decision when a recipe needs an ADK migration or carries a legacy app_utils generation. When docker is available it offers to PROVE the claim: it builds the generated Dockerfile, runs it, probes it, and refuses to flag a recipe deployable if the container does not come up. Does NOT deploy or write terraform. Use when the user wants to "make this recipe deployable", "add a Dockerfile to a recipe", "add the serving files", "containerize a recipe", "verify the container builds", or prepare a recipe for Cloud Build / Artifact Registry.

Review a GitHub pull request and leave inline comments in a natural human reviewing voice, indistinguishable from comments typed by hand on the GitHub web UI. Deliberately bounded to defects a reader can settle by looking at the anchored line, rather than a deep audit, so every comment is cheap for the author to check. Scales to 2-20 comments by PR size, parallelises analysis across sub-agents, drafts for approval, then posts individually with human pacing. Use when the user says "review this PR", "review PR 123", pastes a github.com/.../pull/N link, or asks for comments on a pull request. Don't use for reviewing local uncommitted changes or a diff against a branch (use the `review` skill for that).

Apply Apache ShardingSphere's written coding standards when explicitly requested, or when code-implementation routes task-changed production, test, script, build, generated, or Maven POM artifacts through repository standards. Also perform a standalone read-only compliance audit of a user-specified scope. Use CODE_OF_CONDUCT.md, applicable AGENTS.md rules, Checkstyle, Spotless, and other repository-defined standards, including naming and evidence-based defensive-code rules. Do not invoke independently for an ordinary implementation already governed by code-implementation, and do not independently audit architecture, runtime ownership, caches, or lifecycle.

Implement, fix, refactor, or remove repository code under required scope, non-regression, verification, and review gates. Use whenever a task may change a production, test, script, or other implementation artifact, including build logic, generated source, and behavior-affecting configuration. Also use it alongside a specialized code-changing Skill. Do not use for read-only analysis or review, diagnosis-only work, or prose-only changes.

Use when writing a Codewhale takeover prompt, continuation note, or end-of-session summary for another agent or a later session: a paste-ready handoff grounded in live state, with done/suspected/blocked kept separate.

Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.

Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.

Desktop control that picks the right interface per step — app scripting (AppleScript/JXA), accessibility-first observation and actions, pixel fallback, screenshots, zoom, screen recording, and switching between registered computers. Qualified on macOS; Windows, Linux and HarmonyOS backends are experimental.

Find and start a zero-environment local MCP server when the session lacks a capability that no available tool, project script, or ordinary local code can cover.

Write a compact, decision-ready handoff so the next session (or the user) can continue without reconstructing the current one. Use when the session is ending, context is running low, the user asks for a handoff / 'pass the baton' / 'hand off', or a long-running operation needs a durable state checkpoint.

Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.