5,519 件 ・ 関連度順
概要と使いどころ
Trae-compatible PUA high-agency governance skill. Use only for explicit PUA requests, repeated failures, user frustration, giving-up/passive behavior, or unverified completion. Do not trigger for normal first-attempt tasks.
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。
Pi-compatible PUA high-agency governance skill. Use for explicit PUA/PIP requests, repeated failures, passive/giving-up behavior, user frustration, or unverified completion. Pair with /pua-on extension command when persistent pressure is desired.
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。
Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/stas00/ml-engineering/blob/master/skills/ml-engineering/SKILL.md
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。
Reduces an always-on LifeOS context file that has grown too big via a human-gated pass — deterministic GC of stale entries first, then semantic merges and relocations — never dropping a directive and committing every change reversibly. USE WHEN /trim, trim the context, trim OPERATIONAL_RULES, this file is too big, reduce a doctrine file, prune an always-loaded file, fold the proposal inbox, shrink CLAUDE.md or DA_IDENTITY. NOT FOR general code refactoring, trimming video or audio media (use AudioEditor for audio files), or removing AI writing patterns from prose.
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。
Scaffolding that helps a writer build a story they already want to tell — fills in structure, hidden wound, theme, and prose from the writer's own material across seven narrative layers, deriving the spine from their notes as proposals they ratify. Bans generic AI patterns; scales short story to multi-book series. USE WHEN write story, fiction, novel, chapter, story bible, character arc, plot outline, creative writing, worldbuilding, draft story, help me write my story, develop my novel, layer my story, build out my book, I have notes for a story. NOT FOR narrative summaries of real content.
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。
The scientific method as a universal problem-solving algorithm — goal-first, plural falsifiable hypotheses, designed experiments, and honest measurement, scaling from TDD to feature validation to MVP launch. USE WHEN think about, figure out, experiment, iterate, optimize, hypothesis, science, full cycle, quick diagnosis, structured investigation, how do we test, analyze results. NOT FOR multi-angle lens passes (use IterativeDepth).
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。
Audits any AI instruction set for over-prompting using the core test — would a smarter model make this rule unnecessary? Applies Five Questions to every rule (Claude already does this? Contradiction? Redundant? One-off fix? Vague?) then classifies as CUT/RESOLVE/MERGE/EVALUATE/SHARPEN/MOVE/KEEP. Workflows: Audit (full system, token savings), QuickCheck (single file). Principle: less scaffolding = better output. USE WHEN BPE, bitter pill, audit setup, over-prompting, trim instructions, dead weight, simplify setup, clean up CLAUDE.md. NOT FOR attacking logical flaws in ideas (use RedTeam).
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。
Iterative improvement loop — refine a target across multiple Algorithm cycles toward ideal state. USE WHEN loop, iterate, refine, multiple passes, keep improving, revisit, rework.
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。
Turn a tech-spec directory into an interactive, marketing-grade web presentation — built so engineers understand the design, the reader is convinced of the why, and the result is shareable in public. Use when someone wants a spec turned into a deck.
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。
Use when registering iii functions, binding triggers, selecting sync/void/enqueue invocation, creating workers, inspecting the live worker registry, installing registry workers, authoring custom triggers, moving channel data, or adapting external HTTP functions across TypeScript, Python, and Rust.
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 for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending effective context capacity without lowering answer quality.
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。
Use when deploying KubeEye for cluster inspection, creating InspectRule/InspectPlan resources, or retrieving inspection results. Covers InstallPlan-based deployment, OPA/PromQL/FileChange/Sysctl/Systemd/NodeInfo/FileFilter/ServiceConnect/CustomCommand rule types, and report retrieval. Always consult this skill when the user mentions KubeEye, cluster inspection, InspectRule, InspectPlan, or inspection reports.
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。
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.
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。
Query and filter Datadog logs from the shell using the Composio CLI. Run scoped log searches, pivot across services/environments, and export structured JSON for downstream agents instead of click-driving the Datadog UI.
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。
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this URL, process this source, read and file this source, batch ingest, ingest these sources.
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。
Arrange the tabs and split panes of a Superset workspace in the desktop app from an agent. Use when the user asks to split a pane, open a tab, run a command in a new pane, resize, swap, move, focus, close, or even out panes, lay out a dashboard of terminals, or show them something side by side, including "split this and run the tests on the right", "open the logs in a new tab", "make this pane bigger", "put the server and the tests side by side", "close those extra panes". Not for coordinating worker agents (use superset:orchestrate) or driving web pages (use superset:browser).
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。
Verify UI behavior end-to-end by driving the running desktop app over the Chrome DevTools Protocol. Use when asked to verify, reproduce, or confirm a UI change, bug, or regression in the real app rather than in tests.
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。
Check that a tRPC change is safe for released desktop, mobile, CLI, and SDK builds, pick the compatible pattern, and decide when a deprecated procedure can be removed. Use when changing, renaming, or removing an existing procedure, input field, or output field in packages/trpc or packages/host-service, when reviewing such a PR, or when a deploy broke released clients.
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。
Runs the Autoware autonomous-driving stack against CARLA on UE 5.8 over CARLA's native ROS 2 interface — no bridge process. Reports the DDS contract (rt/vehicle/status/* out, rt/control/command/* in), the Autoware-only sensor blueprints, generates the lanelet2 + point-cloud map artifacts Autoware needs instead of an .xodr, and drives the two shipped modes (classical NDT stack, or the camera-only VAD end-to-end model). Use when the user asks to "run Autoware on CARLA", "connect an AV stack", "drive the ego from Autoware", "generate a lanelet2 map", or asks which topics CARLA exchanges with Autoware.
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。
Reads a CARLA Leaderboard results.json — per-route driving score, route completion, infraction penalty and the infraction lists — explains how the score was computed for that leaderboard version, and rescores an existing result under the other version's rules (2.0 multiplicative vs 2.1 additive) without re-running anything. Also diffs two runs and merges sharded result files. Use when the user asks "what did I score", "why is my score low", "did my agent pass", "why don't my scores match the leaderboard", or hands over a results.json.
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。
Spawns vehicles on a running CARLA server and destroys them — scattered across the map's spawn points on Traffic Manager autopilot, a row queued in a single lane at a fixed spacing, or a single hero/ego vehicle (optionally named for native ROS 2 publishing with --ros-name). Covers blueprint filtering, the atomic autopilot hand-off, and cleanup. Use when the user asks to "spawn vehicles/cars/traffic", "add N cars driving around", "put cars in a lane 15 m apart", "spawn the ego/hero vehicle", or "remove the vehicles".
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。
Installs CARLA's ScenarioRunner (the official scenario engine) and picks the branch that matches the CARLA in use — master for 0.9.14-0.9.16 (UE4), ue5-master for 0.10.0 (UE5), leaderboard-1.0/2.0/2.1 when driving the Leaderboard. Clones or checks out the branch, installs requirements, wires PYTHONPATH (including the `agents` package the carla wheel does not ship), and verifies the import. Use when the user asks to "install scenario runner", "set up SR", "run CARLA scenarios", "use OpenSCENARIO", or has a scenario_runner that fails to import.
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。