Generate, consume, and enrich Ginkgo reports — console verbosity (-v/-vv/--trace/--no-color/--succinct), machine-readable reports (--json-report/--junit-report with --output-dir/--keep-separate-reports), programmatic reporting nodes (ReportAfterEach, ReportAfterSuite, CurrentSpecReport), AddReportEntry with ReportEntryVisibility, and profiling (--cover/--race/--cpuprofile/--memprofile). Use when you need a report file, custom suite-level reporting, attaching data to a spec, controlling console output, or profiling a suite.

Run Ginkgo suites in parallel — ginkgo -p / --procs, the separate-process (not goroutine) model, SynchronizedBeforeSuite/SynchronizedAfterSuite vs BeforeSuite, GinkgoParallelProcess() for sharding ports/tmpdirs/databases, building a binary once via gexec, piping child-process output to GinkgoWriter, and what N processes actually cost (compilation vs teardown, and the fixed ~1s --race adds per suite — GORACE=atexit_sleep_ms=0). Use when parallelizing a suite, speeding up integration tests, auditing why a parallel run is slow, fixing parallel-only flakes/races, sharding external resources, or choosing between BeforeSuite and SynchronizedBeforeSuite.

Control spec ordering and manage flaky specs — Serial, Ordered containers with BeforeAll/AfterAll/ContinueOnFailure, OncePerOrdered, SpecPriority, plus FlakeAttempts/--flake-attempts, MustPassRepeatedly, --repeat, and --until-it-fails. Use when specs must run in a fixed order, you need once-per-group setup, you're combining Serial+Ordered, a spec is flaky, or you want to hunt order-dependence with --until-it-fails -p --randomize-all.

Diagnose a failing Ginkgo suite as an agent — always run with --json-report into a predictable temp/gitignored location, read the terminal verdict line, then use jq to extract structured failure details (name, message, file:line, panic value, captured logs). Covers the panicked-vs-failed trap, panic locations pointing into the Go runtime, parallel output interleaving, reproducing with --seed, and progress reports for hangs. Use when a suite failed and you need to know why. Also invokable as /ginkgo:debugging-failures.

Read the Convex deployment's 72h insights (read limits, OCC contention), root-cause each event in code, report evidence-backed perf/cost findings with fixes.

Use when drafting, sending, or preserving email correspondence for an existing ClawHub content rights case.

Create and manage Axiom monitors and notifiers via the v2 public API. Use when building alerting, routing notifications, validating monitor behavior, and maintaining alert configurations end-to-end.

Build, test, and maintain the Uno DevServer (CLI tool, RemoteControl Host, MCP proxy, add-in discovery). Use when working under src/Uno.UI.DevServer.Cli, src/Uno.UI.RemoteControl.Host, or src/Uno.UI.RemoteControl.DevServer.Tests, or on DevServer CLI commands, the MCP proxy, IDE channel, or add-in resolution.

Run MiniCPM5-1B or MiniCPM5-2B in LM Studio (desktop GUI) using either the GGUF runtime (cross-platform) or the MLX runtime (Apple Silicon, faster). Includes OpenAI-compatible local server. Use when the user mentions "LM Studio", desktop GUI inference, "lms" CLI, or wants a no-code chat UI for MiniCPM5.

Use this skill when creating a new Java E2E integration test (failsafe IT) that requires a new replay proxy YAML snapshot file in test/snapshots/

Run the Open SWE dashboard locally against real GitHub data, signed in with the `gh` CLI instead of a per-machine GitHub App. Use when asked to run the app locally, test a dashboard change against real PRs, reproduce something a screenshot shows, or when local login fails with "GITHUB_APP_CLIENT_ID not configured".

评估和处理 OpenCreator GitHub PR，先审查实际功能与风险，对不能合入的 PR 用英文反馈，并将满足门禁的 PR 合并到 develop。用于查看、评审或处理 https://github.com/krillinai/OpenCreator/pulls；不用于合并 master 或发布。

IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida_* modules (50+), idautils iterators, and common patterns.

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.

Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills.

Use this skill for failed MoviePilot video or music transfer history IDs. Inspect the exact records, preserve durable retry evidence, group only records with a trustworthy shared identity, and re-identify/reorganize only legacy records that were actually deleted.

Use this skill when the user asks MoviePilot to identify and organize a local or downloaded video/music file, season folder, recording, album directory, or mixed folder that automatic transfer did not handle. If failed transfer history IDs are supplied, use transfer-failed-retry instead.

Use this skill when a user provides a torrent name or file name and wants to fix recognition issues, or asks to add/manage custom identifiers (自定义识别词). This skill generates identifier rules based on the WordsMatcher preprocessing logic, checks for duplicates against existing rules, and saves them through the structured MoviePilot API gateway. Because custom identifiers are global, generated rules must default to conservative, sample-specific regex patterns instead of broad matches unless the user explicitly wants global cleanup. Applicable scenarios include: 1) A torrent or file name is incorrectly recognized (wrong title, season, episode, etc.); 2) The user wants to block unwanted keywords from torrent names; 3) The user needs episode offset rules for series with non-standard numbering; 4) The user wants to force recognition of a specific media by source-native ID; 5) The user wants TV recognition to use a specific TMDB episode group.

Use this skill when you need to inspect, query, maintain, or carefully modify the MoviePilot database. This skill uses the bundled scripts/mp-db.py helper, which reads MoviePilot local settings itself and never requires database passwords or full PostgreSQL DSNs in the agent prompt. Applicable scenarios include data statistics, counts, aggregations, inspecting or fixing records, cleanup requests, and questions like "how many downloads", "show site stats", "delete old records", or "why is this subscription stuck".

Use this skill when the user sends a slash command or asks to run a MoviePilot system or plugin command in natural language. Discover the live command catalog, resolve the exact command, and dispatch it through the structured API gateway.