538 个 · 按相关度排序
Plan projects that use large language models, from checking whether the task suits a model to designing processing stages. Estimate costs, choose single or multiple agents, and organize prototypes, structured outputs, and iteration.
中文简介正在准备中。当前显示英语简介。
Diagnose file access problems by checking directories, permissions, file headers, and line counts in parallel batches. Also reviews TypeScript imports, fixes duplicates and type-only imports, and checks module exports before retrying the failed operation.
中文简介正在准备中。当前显示英语简介。
Package project files into a ZIP archive and verify that the deliverable exists and is not empty before completing a task. It also defines a fallback for archiving available files when the agent approaches its iteration limit.
中文简介正在准备中。当前显示英语简介。
Analyze agent runs that fail before any work begins. By checking execution counts, tool calls, outputs, and conversation logs, this skill classifies startup failures and directs investigation toward system setup, resources, or input processing.
中文简介正在准备中。当前显示英语简介。
Improve code through repeated changes, checks, and decisions to keep or discard each result. Start with a goal or measurable target, limit iteration counts, and review logs for progress, stalled improvements, or regressions.
中文简介正在准备中。当前显示英语简介。
Advance one development task by managing an existing pull request, fixing a build failure or bug, or implementing a queued idea. Record the work and integrate changes into auto-dev only after automated checks pass.
中文简介正在准备中。当前显示英语简介。
Structure complex work that spans many sessions or iterations. Assess resources and obstacles, identify the current stage, choose one immediate achievable target, and set milestones for moving from preparation toward broader execution.
中文简介正在准备中。当前显示英语简介。
Measure DOCA Flow rule update and disable rates when work runs on the device's DPA processor. Configure workloads, interpret repeated measurements in thousands of operations per second, and investigate zero-operation results or failed self-tests.
中文简介正在准备中。当前显示英语简介。
Measure how quickly a host or DPU CPU installs and deletes DOCA Flow rules. Choose a JSON workload and backend, run repeated benchmarks, and record hardware, software, and execution settings so results can be assessed.
中文简介正在准备中。当前显示英语简介。
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts, iteration-count reporting, PR signoff comments, and blocked-state handling.
中文简介正在准备中。当前显示原文说明。
Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule every framework documents quietly and every team relearns expensively: the LM in the loop is NEVER a reliable terminator. Termination must be provided by an explicit counter + exit predicate + stagnation signal + escalation path that live OUTSIDE the LM's control. This is a tool- level, framework-agnostic skill. It maps onto LangGraph (recursion_limit + state counter + interrupt), CrewAI (max_iter + max_rpm + human_input), Claude / OpenAI SDKs (max_iterations + tool_use_budget), DSPy (declared evaluation budget), Aider (REPL + explicit retry cap), and AutoGen (max_consecutive_auto_reply). Search keywords: infinite loop, recursion limit, recursion_limit, GraphRecursionError, max iterations, max_iter, agent stuck, agent won't stop, runaway agent, ReAct loop not terminating, agent repeating itself.
中文简介正在准备中。当前显示原文说明。
Detects shared stack membership and iterates a command across all PRs in base-to-tip order. Use when a command supports --stack flag for multi-PR iteration.
中文简介正在准备中。当前显示原文说明。
Cost discipline for recurring /loop runs. A loop multiplies per-iteration cost by iteration count, so waste compounds. Encodes cache-aware pacing (avoid the 300s dead zone), event-driven-over-polling, a no-change short-circuit, a compact state handle carried between ticks, and a stop condition. Use when a /loop is running or being set up — especially long-lived or frequently-firing ones.
中文简介正在准备中。当前显示原文说明。
Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Cursor, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, exposing the orchestrator's 69 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose, or running as an Agent Client Protocol (ACP) agent that Zed / JetBrains / Neovim / Emacs / VS Code / dsh can drive directly. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "deep paper review", "auto research", "switch model", "multi-agent", "coding session", "session inbox", "cursor agent", "opencode", "mcp server", "clawo-mcp", "hermes mcp", "model context protocol", "ultracode", "dynamic workflow", "fanout", "fan-out", "best-of-N", "steer turn", "interrupt turn", "fork thread", "rollback turns", "acp", "agent client protocol", "clawo acp", "zed agent", "jetbrains agent", "external agent", "dsh subagent", "deepseek harness".
中文简介正在准备中。当前显示原文说明。
Automated iterative agent runner for spec-based development in Kiro. Wraps kiro-cli in a self-correcting bash loop that picks up tasks from a Kiro spec, implements them one at a time, verifies against exit criteria, and accumulates corrections and codebase patterns across iterations. Use this skill when the user mentions "ralph loop", "ralph", "spec loop", "iterative spec runner", "run my spec tasks automatically", "kiro spec automation", "self-correcting agent loop", "implement spec tasks in a loop", "run kiro-cli in a loop", "automated task implementation", or wants to drive a Kiro spec to completion through repeated agent iterations. Also use when the user wants to set up, configure, troubleshoot, or understand the Ralph Loop workflow — including progress tracking, corrections, codebase patterns, timing logs, and the summary dashboard.
中文简介正在准备中。当前显示原文说明。
Run a strict multi-iteration Reflex Loop with phases (PLAN, PRODUCE||PREPARE, EVALUATE, CRITIQUE, REFINE) to improve an artifact until quality gates pass or iteration limits are reached. Use when user asks for iterative refinement, quality-gated generation, or "generate -> critique -> refine" loops.
中文简介正在准备中。当前显示原文说明。
Run a strict multi-iteration Reflex Loop with phases (PLAN, PRODUCE||PREPARE, EVALUATE, CRITIQUE, REFINE) to improve an artifact until quality gates pass or iteration limits are reached. Use when user asks for iterative refinement, quality-gated generation, or "generate -> critique -> refine" loops.
中文简介正在准备中。当前显示原文说明。
One-fix-at-a-time, approval-gated design fix recovery. Given a checklist of fixes (handover doc, CHECKLIST.md, or inline list), applies each individually, presents a diff, and waits for an explicit APPROVE / REJECT / NO CHANGES decision before committing. Trigger phrases: /design-iteration, "go through the checklist one by one", "fix these one at a time", "bucket recovery", "design fix pass".
中文简介正在准备中。当前显示原文说明。
Execute an autonomous development loop that picks one task per iteration, implements it, verifies it, and commits the result — each iteration in a fresh context window. Use when user runs /ralph, mentions "ralph loop", "autonomous loop", "builder verifier", "run tasks automatically", "iterate on tasks", "develop autonomously", or wants an automated build-verify-commit cycle with task tracking.
中文简介正在准备中。当前显示原文说明。
Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, exposing the orchestrator's 78 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose, or running as an Agent Client Protocol (ACP) agent that Zed / JetBrains / Neovim / Emacs / VS Code / dsh can drive directly. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "auto research", "switch model", "hand off a session", "session handoff", "switch engine", "continue on codex", "continue on claude", "move this session to another engine", "multi-agent coding", "coding session", "session inbox", "grok session", "grok build", "opencode", "mcp server", "clawo-mcp", "hermes mcp", "model context protocol", "ultracode", "dynamic workflow", "fanout", "fan-out", "best-of-N", "steer turn", "interrupt turn", "fork thread", "rollback turns", "acp", "agent client protocol", "clawo acp", "zed agent", "jetbrains agent", "external agent", "dsh subagent", "deepseek harness", "clawo runs", "run ledger", "session cost", "coding-agent token usage", "spend cap", "budget limit", "maxBudgetUsd", "durable workflow", "resume a run", "verify a coding run", "acceptance contract", "evidence bundle", "did the agent's tests actually pass", "protected tests", "agent edited the tests", "human gate", "repair loop", "clawo workflow", "clawo verify", "clawo solve", "clawo fanout", "fix and verify", "solve from the terminal".
中文简介正在准备中。当前显示原文说明。
Use when autonomously improving a measurable scalar metric through bounded, git-tracked iterations: modify one scoped change, verify, keep or revert. Triggers on /mk:loop, 'optimize coverage/bundle size/lint count', 'iterate until the metric improves'. NOT for subjective cleanup (see mk:cook), known-root-cause bugs (see mk:fix), behavioral grading (see mk:evaluate), or shipping (see mk:ship).
中文简介正在准备中。当前显示原文说明。
Continuous localhost UI iteration loop with Arman, through full surface certification. Use when he asks to fix, refine, review, or iterate on a page, route, panel, overlay, or other UI while he may inspect localhost. NOT for a report-only UI audit.
中文简介正在准备中。当前显示原文说明。
在发布文章或部署代码前，由两个独立代理按相同标准审查；仅在双方均通过后继续，否则修改并重新审查，达到迭代上限后将未解决的问题交由人工判断。
分析开放权重语言模型的拒答机制，支持无需重新训练的权重修改实验，并根据计算环境选择模型与方法，比较修改前后的拒答率和回答质量。