1,929 件 ・ 関連度順
概要と使いどころ
This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
日本語の概要は準備中です。原文の説明を表示しています。
This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improving harnesses that mine their own failures and propose bounded edits, evolutionary or population-based search over agent scaffolds, acceptance gates for self-modifying systems, and agentic context evolution where the mechanism that produces context is versioned and evolved. Route governance of a single autonomous loop (locked surfaces, durable logs, rollback, novelty gates, approval boundaries) to harness-engineering, measurement and quality-gate design to evaluation, judge design to advanced-evaluation, and remote sandbox infrastructure to hosted-agents.
日本語の概要は準備中です。原文の説明を表示しています。
Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.
日本語の概要は準備中です。原文の説明を表示しています。
KubeSphere Gateway extension management Skill (ingress-nginx based, uses Kubernetes Ingress API + Gateway CRD gateway.kubesphere.io/v2alpha2). For the newer Kubernetes Gateway API (Traefik + GatewayProxy CRD), see the kubesphere-gateway-api skill instead. Covers installation, uninstallation, status checks, gateway status inspection, and troubleshooting (gateway stuck states, Helm failures, pod issues).
日本語の概要は準備中です。原文の説明を表示しています。
Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.
日本語の概要は準備中です。原文の説明を表示しています。
Manually dispatch and iterate on the Release Canary workflow that smoke-tests published OpenShell artifacts (install.sh on macOS/Ubuntu/Fedora, Helm chart on kind) after each Release Dev publish. Use when changing `.github/workflows/release-canary.yml`, validating a release before tagging, debugging a canary failure, or reproducing a canary job locally. Trigger keywords - release canary, release-canary, canary failed, canary dispatch, test release canary, post-release smoke, install.sh canary, helm chart canary, kind canary, dispatch canary.
日本語の概要は準備中です。原文の説明を表示しています。
Generate sandbox security policies from plain-language requirements and optional REST API documentation. Produces L4 or fine-grained L7 network policies and ordered network middleware configuration. Use for API access rules, middleware host selection, failure behavior, or built-in and operator-run middleware attachment. Trigger keywords - generate policy, create policy, update policy, change policy, sandbox policy, network policy, API policy, security policy, allow API, restrict API, network middleware, supervisor middleware.
日本語の概要は準備中です。原文の説明を表示しています。
Diagnose and fix Superset problems such as connection failures, offline hosts, terminals not attaching, auth or update issues. Use when the user reports something broken or misbehaving in Superset itself ("Superset won't connect", "my host shows offline", "terminal won't attach", "the app is stuck"), before filing feedback.
日本語の概要は準備中です。原文の説明を表示しています。
Cooks and packages a shippable CARLA server from a UE 5.8 ue58-dev checkout via the CMake `package` targets (shipping/development/debug/test), scoping the cook with CARLA_MAPS_TO_COOK, and inspects an existing package for the failures a green build hides — stale pak/ucas mismatch, missing staged OpenDrive/TM road data, missing post-process profiles, and Town15's uncookable content. Use when the user asks to "package CARLA UE5", "cook a map", "build a shipping server", "make a distributable CARLA", or a package builds but renders black / has no maps.
日本語の概要は準備中です。原文の説明を表示しています。
Builds CARLA on Unreal Engine 5.8 from the ue58-dev branch using its CMake build system — configure a preset, then build the carla-unreal / carla-unreal-editor / carla-python-api-install / launch targets — with ROS 2, DLSS, RSS and cook-scope options, and the engine-side build of the CarlaUnreal UE 5.8 fork. There is no Makefile and no Util/BuildTools in this tree, so every UE4 `make` recipe is invalid here. Use when the user asks to "build CARLA UE5", "build ue58-dev", "compile CARLA with cmake", "rebuild the Python API", or hits a CMake configure or target failure.
日本語の概要は準備中です。原文の説明を表示しています。
Register, extend, or audit instructions in the table-driven T.ptx dialect (python/tvm/backend/cuda/ptx/table.py), and move the table to a newer PTX ISA version. Use when adding a PTX instruction or qualifier, widening an operand domain, fixing a ptxas certification failure, or checking the table's comments against the PTX ISA document.
日本語の概要は準備中です。原文の説明を表示しています。
Parses error messages, traces execution flow through stack traces, correlates log entries to identify failure points, and applies systematic hypothesis-driven methodology to isolate and resolve bugs. Use when investigating errors, analyzing stack traces, finding root causes of unexpected behavior, troubleshooting crashes, or performing log analysis, error investigation, or root cause analysis.
日本語の概要は準備中です。原文の説明を表示しています。
Parse CI failures, identify failing job/step, classify as flake, regression, env, or config. Use in CI sweeper loops before any fix attempt.
日本語の概要は準備中です。原文の説明を表示しています。
Produce the smallest possible code change that fixes a specific, well-scoped issue (CI failure, reviewer comment, typo). Use only when the fix target is explicit. Never refactor unrelated code.
日本語の概要は準備中です。原文の説明を表示しています。
Triage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or issue tracker.
日本語の概要は準備中です。原文の説明を表示しています。
Triage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or Linear board.
日本語の概要は準備中です。原文の説明を表示しています。
Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.
日本語の概要は準備中です。原文の説明を表示しています。
Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.
日本語の概要は準備中です。原文の説明を表示しています。
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
日本語の概要は準備中です。原文の説明を表示しています。
AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.
日本語の概要は準備中です。原文の説明を表示しています。
Required before any hive-browser CLI command. The browser is driven from the terminal by running `hive-browser <command> ... --json` via terminal_exec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues, not crashes), the screenshot + coordinate workflow (hive-browser interact with a fractional coordinate) that reaches shadow-DOM inputs selectors can't see, the viewport-fraction coordinate rule (not pixels), rich-text editor quirks ("send button stays disabled" failures), and CSP gotchas. Covers Chrome via CDP through the GCU Beeline extension.
日本語の概要は準備中です。原文の説明を表示しています。
Required before calling image_generate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2 through the Hive image service, billed to the user's Hive credits like an LLM call (no API key needed). Teaches the exact call shape, the quality/cost tradeoff (quality="low" is the default and cheapest), reference-image editing, how to show the result to the user with attach_file, and the failure modes (out of credits, model unavailable, moderation).
日本語の概要は準備中です。原文の説明を表示しています。
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
日本語の概要は準備中です。原文の説明を表示しています。
Run the Omnigent load test and produce a results file explaining the latencies. Load when the user wants to load-test / stress-test / benchmark Omnigent under concurrency ("load test omnigent", "stress test the server", "how many hosts/sessions/turns can it handle", "load test real agent turns / conversations", "run a load test"). The test makes each simulated user a real omnigent host that creates host-bound sessions and drives real multi-turn conversations with a mocked LLM; it boots its own local stack (dev/loadtest/run.py). Gather inputs, run it, then read the generated summary.md and explain the latency distribution (avg/median/p95/p99, throughput, failures). NOT for single-request latency micro-benchmarks (that is dev/benchmarks/).
日本語の概要は準備中です。原文の説明を表示しています。