MUST USE when an existing .NET test project was excluded from a .slnf/CI solution filter, disappeared from .sln/.slnx discovery, or lost its production ProjectReference; also for requests to set up, create, reuse, add, register, include, or repair a test project. Handles "tests pass directly but CI discovers zero", exact solution wiring, xUnit/NUnit/MSTest, and central packages. DO NOT USE to only author tests in an already-wired project (code-testing), run tests, migrate, or correct MSTest syntax/configuration without changing project or CI files (writing-mstest-tests).

ALWAYS USE before running .NET tests or answering with a test command or flags. Trigger on "run the tests", "exact dotnet test command", one test/class/category/trait/target framework, combined filters, `--filter-query`, `--no-build`, `--diag`, diagnostic logs, TRX, coverage collection, crash/hang dumps, filter errors, or unrecognized options. Chooses repository-compatible classic, VSTest, bridged MTP, or native MTP syntax for MSTest/xUnit/NUnit/TUnit. DO NOT USE for platform identification alone (platform-detection), writing or debugging test code, interpreting an existing coverage report, CI investigation, migration, or a persistent hot reload/watch loop.

Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

Profile and optimize FLA kernels on NVIDIA GPUs, with same-hardware benchmarks and targeted Nsight Compute analysis.

Solve a user-specified web task code-as-action style by driving a local Playwright browser through one bash command at a time, saving screenshots and an action log into `final_runs/run_<id>/`, and visually verifying the result. Use when the user asks to automate a web task (search, filter, form-fill, multi-step flow, data extraction) and wants reusable scripts plus screenshot evidence rather than a one-shot answer.

Turns rough ideas into approved, decision-complete plans before coding. Use when planning architecture, judging whether to build, or writing a handoff. Not for bug fixes or small edits.

Deterministically drive a first-party Civitai App Block in the operator's browser and produce store-ready screenshots, machine-analysable per-state evidence (DOM + console + failed requests + a11y + testids), or attach media to a listing. Use when the user asks to capture / screenshot / re-shoot an app's store images, to add a screenshot / icon / cover / caption to an app listing, to add a new app to the capture set, to FIND DEFECTS in a running App Block or diff a before/after fix, or to run a scripted App Block action (including the spend path behind an explicit flag).

Draft a model description for the CivitaiOfficial account when mirroring a third-party model on civitai.com or civitai.red. Use when the user is publishing or rewriting a mirrored model page (e.g. Sulphur, HappyHorse, Wan, ACE-Step) and wants a structured, properly-credited description rather than a one-line stub. Produces HTML ready to paste into the Civitai rich-text editor.

Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.

Parse CI failures, identify failing job/step, classify as flake, regression, env, or config. Use in CI sweeper loops before any fix attempt.

Implementation details for the EF Core dotnet-ef CLI and tooling. Use when changing dotnet-ef commands, the ef wrapper, EFCore.Tools (PMC), or EFCore.Tasks MSBuild integration.

Use when the user asks to review PAST sessions, find recurring patterns across sessions, or improve project primitives (rules, skills, hooks, docs) from historical IDE transcripts. Do NOT trigger on current-session self-review — use reflect instead.

Screen a pull request from an outside contributor for hidden, obfuscated, or supply-chain-risky changes before any of its code runs.

设计 Agent 评估数据集或单条评估任务时使用——解剖评估任务的四个组成部分、设计验证器与验收标准（含防敷衍性修复）、划分任务难度与陷阱任务、防范训练/评估数据泄漏（参数化实例、canary）、建设评估集的质量控制与长期维护、选择公开基准/自建业务集/生产轨迹回流三个来源。覆盖 τ²-bench、SWE-bench、AndroidWorld、OSWorld、Terminal-Bench、GAIA 的可迁移设计手法。

Carry state between runs of a scheduled routine using Hindsight memory. Use when creating or editing a routine, to write the recall and retain steps into the routine's own instructions, and at the start and end of every scheduled or event-triggered routine run.

Gate on identity questions to the user. Before any "who is X?" (or role / relationship question) reaches the user, exhaust the brain's lookup chain: think → search + page read → mounted sources → timeline/graph → web. If escalation survives the chain, ask WITH a hypothesis, never a bare unknown. Also owns the no-placeholders-at-ingest rule: pages created during bulk ingestion get their relationship/role resolved immediately.

Run `gbrain skillpack-check` to produce an agent-readable JSON health report for the gbrain install. Wraps `gbrain doctor` + `gbrain apply-migrations --list` so a host agent (your OpenClaw's morning-briefing, any OpenClaw cron) can see at a glance whether the skillpack needs attention. Use when the user asks "is gbrain healthy?", when a cron fires a morning check, or proactively when something seems off (jobs not running, brain not updating, autopilot silent).

Ingest links, articles, tweets, and ideas into the brain. Fetch content, save to brain with analysis, credit the author (people page only when they pass the notability gate), and cross-link. Use when the user shares a link or says "read this", "save this", "think about this".

Add hosted API key support to a tool so Sim provides the key (metered and billed to the workspace) when a user has not brought their own. Use when adding a `hosting` config to a tool under `apps/sim/tools/{service}/`.

Recommended repo-engineering guide when adding alerting to a PostHog product or extending the shared alerts platform. Routes lifecycle state machines, AlertPolicy, destinations, HogFunction dispatch, email, fixed-cadence and calendar scheduling, insight evaluation, the AlertWizard, and shared alert editor components. Use for product alert implementations, shared destination types, lifecycle or scheduling options, advanced alert settings, and platform alert infrastructure. Not for configuring alerts in an existing product.