716 个 · 按相关度排序
Direct a claim-driven research experiment project from post-Idea intake through method realization, prioritized evidence collection, Human Gates, and Evidence Freeze. Use for scientific planning, state transitions, queues, budgets, or recovery; not for running code or independently auditing results.
中文简介正在准备中。当前显示原文说明。
Use when verification depends on agent runtime phases, queued input, tool-call lifecycle, save points, retry, abort, compaction, or branch behavior.
中文简介正在准备中。当前显示原文说明。
Discover, message, and coordinate AI coding agents (Claude Code, Codex CLI) running on the same machine via a shared Unix socket broker backed by SQLite. The broker wakes recipients natively (Claude inbox socket, codex queue) and turn-boundary hooks catch missed wakes. Supports cross-session task delegation, peer summaries, and session lifecycle management. Triggers on 'peer agents', 'cross-session communication', 'message Codex', 'inter-agent messaging', 'coordinate agents'.
中文简介正在准备中。当前显示原文说明。
Freeze outside-the-repo state into one snapshot. Use when the work depends on the current state of a service, database, queue, third party, or live logs.
中文简介正在准备中。当前显示原文说明。
Use when creating FreeRTOS tasks, queues, semaphores, or mutexes, catching stack overflow, writing FreeRTOSConfig.h, or debugging tasks over OpenOCD and GDB. Not for probe setup: use openocd-jtag.
中文简介正在准备中。当前显示原文说明。
Use when the user asks "where to help", "contribution opportunities", or "find a good first issue". Returns data-backed first steps. Not for PR review queues: use gh-review-requests.
中文简介正在准备中。当前显示原文说明。
Use when the user asks to find PRs to review or check the team review queue. Not for summarizing or resolving feedback on a specific PR: use resolve. Read-only.
中文简介正在准备中。当前显示原文说明。
Use when landing a queue of open PRs: gate each PR, sweep its review feedback to root cause, then merge, repair, hold, or close it. Human-only.
中文简介正在准备中。当前显示原文说明。
Use when dependency upgrades need batching for CVEs, a major release, forced compatibility, a scheduled or vulnerability-triggered sweep. Not for PR queue triage: use github-backlog-triage.
中文简介正在准备中。当前显示原文说明。
Run, schedule, and diagnose registered Laravel Feeds exports, interpret command results, and verify publication, queue delivery, and streaming performance.
中文简介正在准备中。当前显示原文说明。
Freeze one eligible Proto UI autonomous-maintenance candidate into a bounded mission packet and lease. Use before observation when a current request or governed queue supplies scope, oracle, baseline, capability, risk, budget, completion, and stop conditions. Do not observe, verify, repair, or invent a mission.
中文简介正在准备中。当前显示原文说明。
Inspect one bounded Proto UI Issue queue slice and route ready governed work toward claim and implementation. Use for intake health, readiness, ownership, claim conflicts, stale state, or a candidate task search. This evidence leaf is read-only; authorized claim and implementation continue in their registered leaves.
中文简介正在准备中。当前显示原文说明。
Close one technically complete Proto UI autonomous-maintenance transition after adequate independent review and required validation. Use to synchronize the finding, remediation packet, mission, run ledger, residual-risk queue, and recorded integration decision.
中文简介正在准备中。当前显示原文说明。
Inspect one bounded Proto UI pull-request slice, produce canonical review input, and route each eligible exact head toward review and integration. Use for review queues, linked work, evidence gaps, merge conflicts, stale revisions, or portfolio health. This evidence leaf is read-only; authorized review and integration continue in their registered leaves.
中文简介正在准备中。当前显示原文说明。
Use when working with TeamCity CI/CD or when a user provides a TeamCity build URL — drives the `teamcity` CLI for builds, logs, jobs, queues, agents, pools, projects, and pipelines.
中文简介正在准备中。当前显示原文说明。
Work with the @upstash/redis TypeScript/JavaScript SDK, a serverless HTTP-based Redis client for Next.js, Vercel, Cloudflare Workers, edge runtimes, and Node.js. Use when adding a cache (cache-aside, write-through, TTL and expiration strategies), session storage and user sessions, a key-value store, leaderboards and rankings with sorted sets, counters, distributed locks, queues with lists, streams and consumer groups, sparse index-addressed arrays and ring buffers (ARSET, ARINSERT, ARRING, ARGREP, AROP), embeddings and nearest-neighbour vector search stored inside Redis (VECTOR commands via redis.vector, separate from @upstash/vector), JSON documents, pipelines and MULTI/EXEC transactions, Lua scripting, read replicas, or full-text search, typo-tolerant search, facets, aggregations, and search over Redis stream entries with Upstash Redis Search (different from regular FT.SEARCH; also available for TCP clients via @upstash/search-redis and @upstash/search-ioredis). Also use when migrating from ioredis or node-redis, when a Redis connection is needed from a serverless function without connection pooling, when integrating @upstash/ratelimit, or when the user says Redis cache, KV store, session store, serverless Redis, or Upstash Redis. Also use when building AI agents on Redis with Upstash AgentKit (agent memory, chat history, RAG tools, tool caching, chat persistence, resumable streams, distributed locks) for the Vercel AI SDK, TanStack AI, or Vercel Eve. Supports automatic serialization/deserialization of JavaScript types.
中文简介正在准备中。当前显示原文说明。
Work with any Upstash product, SDK, or tool, including serverless Redis (caching, sessions, leaderboards, key-value storage), Ratelimit (rate limiting and throttling), QStash (message queue, cron schedules, background jobs), Workflow (durable long-running functions), Vector (vector database for embeddings, semantic search, and RAG), Search (full-text and semantic search), Box (sandboxed cloud containers for AI agents, TypeScript/JavaScript and Python), Blob (serverless S3-compatible file storage with direct browser uploads), the Upstash CLI, and no-signup scratch Redis for agents. Use when the user mentions Upstash or needs any of these capabilities in a serverless, edge, or Node.js app.
中文简介正在准备中。当前显示原文说明。
Provision a zero-config, no-signup, temporary Upstash Redis database for an AI agent with a single POST to https://upstash.com/start-redis, with no account, API key, or SDK setup required. Use when an agent needs scratch Redis right now and the user has not provided credentials, for short-term memory across tool calls, conversation history, a sub-agent work queue, ranked recall, or a quick prototype or demo. Covers idempotent creation and re-fetching credentials, calling the database through the body-style REST API or the official SDKs, and telling the user how to claim it. The database lives 3 days unless the user claims it; not for production data, PII, or secrets.
中文简介正在准备中。当前显示原文说明。
Analyze Ascend NPU schedule, operator dispatch, operator launch, and Host Bound profiling issues in Ascend profiling data. Use when need to diagnose device Free time, framework/operator dispatch latency, launch latency, PYTORCH_API/CANN_API launch gaps, aclrtSynchronizeStream stalls, task queue behavior, CPU scheduling interference, GC/lock pauses, CPU affinity, or schedule-side optimization actions.
中文简介正在准备中。当前显示原文说明。
This skill should be used when the user asks to "hush", "be quiet", "stop speaking", "silence narrator", "narrator hush", "shut up", or wants to immediately stop all current and queued speech output.
中文简介正在准备中。当前显示原文说明。
Use when analyzing an existing TypeScript or JavaScript codebase to decide where and how to introduce Inngest. Covers repository discovery, framework and package detection, finding durability gaps in HTTP handlers, webhooks, cron jobs, queues, long-running jobs, AI agents, Agent Evals, polling loops, eval loops, and side-effect-heavy code, then producing and implementing an incremental integration plan.
中文简介正在准备中。当前显示原文说明。
Drive the terum-skills CLI from a Claude Code or Codex session: run any verb with --format md and show its board — inspect the Library or the team Marketplace, search, fetch with sync, validate or fix a local skill, install the latest version into Global or an added project, publish a local skill as an immutable version, manage the eval queue — and prepare the verbs that belong in a terminal (project setup, skill move/copy/rename/delete, prune, reconcile, machine uninstall, team administration). Use when the user wants to manage, evaluate, publish or install skills and no narrower terum-skills skill fits.
中文简介正在准备中。当前显示原文说明。
Inspect Orchestra projects and tasks, assign workers, queue planning, approve exact plans only on human instruction, request replanning with feedback, show stored PR linkages, reconcile receipts, and scope native agent/skill authoring. Orca-managed worktrees use the separate Orca CLI skill.
中文简介正在准备中。当前显示原文说明。
Read every application.yaml in the workspace and report the state of the search — the ranked queue, what is waiting on you, what has gone quiet, and the regression of the pipeline's own predictions against actual outcomes. Writes the calibration findings back into job_search.md and preferences.yaml.
中文简介正在准备中。当前显示原文说明。