2.1K skills · sorted by relevance
设计或审计任何循环系统的起点: 将循环拆解为 Trigger(触发器)、Action(动作)、Stop Condition(停止条件) 三要素。 当用户需要设计一个新循环、诊断一个失效循环、或向他人解释"什么是 Loop"时使用。 不适用于: 单次任务执行、非循环的自动化脚本、或已经稳定运行无需重新设计的系统。 关键 trigger: "设计一个 loop"、"这个循环为什么不停止"、"什么是 loop 的最小结构"。
The English summary is being prepared. Showing the original description.
Run an explicit end-to-end goal loop with frozen Scope/criteria, worker delegation, external verification, evaluator review, and bounded retries. Use when the user asks for 'goal-loop', 'ゴールまで回す', '必ずやり遂げる', 'loop until done', 'until it actually works', or an orchestrator + evaluator loop. Do not use for ordinary planning, casual advice, reviews, or small single-file fixes.
The English summary is being prepared. Showing the original description.
Adversarial project planning workflow. Explores the problem space, drafts tickets in batches, then runs sequential adversarial loops — a mandatory UX loop ("should we build this?"), zero or more discretionary specialist loops (security, performance) for projects with architectural implications in those domains, and a mandatory implementer loop ("could we build this?") — to find gaps before implementation. Creates well-specified, batch-tagged tickets upstream only after every applicable loop signs off.
The English summary is being prepared. Showing the original description.
Delegate implementation work to a dedicated implementer subagent, then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants a separate model to write code, mentions handing off / delegating implementation, asks to work through a plan or spec unit-by-unit with a subagent doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer self-reports success, must not run the full test suite by default, must not touch git, and its report is a claim rather than evidence. Cursor port of implementation-loop. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the cursor-engineering-mode skill (it ships in this same plugin).
The English summary is being prepared. Showing the original description.
Track Two / internal innovation system for running small, fast experiments outside the core business. Runs in three modes — Diagnostic for designing the full Protoloop from scratch (intake channels, loop structure, team, exit paths), Review for running the monthly heartbeat meeting (loop-by-loop decisions, forward-loading, portfolio health), and Alert Triggers for defining tripwires that protect, feed, and maintain momentum in the system. Updates company-context.md after every run. Triggers on questions about innovation pipelines, intrapreneurship, Track Two strategy, experimentation systems, handling ideas that don't fit the core business, or building systematic exploration alongside exploitation. Based on 20 years of practice by Eterdis (eterdis.com).
The English summary is being prepared. Showing the original description.
Run a bounded, provider-neutral SDD Composy correction loop on one approved task (EXECUTE, QA, EVIDENCE, REVIEW, VERIFY; at most 3 iterations) with explicit approval, safe-stop guards, and fresh verification. Use to continue an approved TASK autonomously — 'rodar o loop na TASK-003', 'continuar a task até passar', 'start a loop on task 4'. Do NOT use for the host's recurring loop runner, for fleets (sdd-fleet), or for a task without human approval.
The English summary is being prepared. Showing the original description.
Agent fallback for CEngineServiceMgr__MainLoop (auto-generated, category: func). Locate CEngineServiceMgr::_MainLoop in the CS2 engine module via IDA Pro MCP and emit a fresh, minimal-unique artifact. The deterministic preprocessor could not resolve this symbol on the current gamever - your job is the re-sign. Trigger: CEngineServiceMgr__MainLoop, CEngineServiceMgr::_MainLoop
The English summary is being prepared. Showing the original description.
Agent fallback for CEngineServiceMgr_DeactivateLoop (auto-generated, category: func). Locate CEngineServiceMgr::DeactivateLoop in the CS2 engine module via IDA Pro MCP and emit a fresh, minimal-unique artifact. The deterministic preprocessor could not resolve this symbol on the current gamever - your job is the re-sign. Trigger: CEngineServiceMgr_DeactivateLoop, CEngineServiceMgr::DeactivateLoop
The English summary is being prepared. Showing the original description.
Agent fallback for CEngineServiceMgr_GetActiveLoopClientServerMode (auto-generated, category: func). Locate CEngineServiceMgr_GetActiveLoopClientServerMode in the CS2 engine module via IDA Pro MCP and emit a fresh, minimal-unique artifact. The deterministic preprocessor could not resolve this symbol on the current gamever - your job is the re-sign. Trigger: CEngineServiceMgr_GetActiveLoopClientServerMode, CEngineServiceMgr_GetActiveLoopClientServerMode
The English summary is being prepared. Showing the original description.
Improve code through repeated experiments against a measurable target, such as execution time or memory use. After defining scope and constraints, the agent tests changes, keeps improvements, reverts unsuccessful attempts, and logs results.
Turn a feature idea into a detailed implementation plan through research, interviews, and reviews by Gemini and Codex. Produce self-contained work sections with dependencies and acceptance criteria, plus files for supported automated implementation workflows.
Diagnoses applications that fail to start or repeatedly crash on GKE, Google's managed Kubernetes service. It examines logs, events, memory use, image pulls, and connectivity, then proposes configuration patches or commands without applying live changes.
Design loops that improve an agent’s own prompts, workflows, or execution code from failure records. Define bounded edits, preserve candidate histories, and accept changes through independent tests that check improvements and regressions.
Improve research through up to four rounds of external language model review, fixes, and reassessment. Use an OpenAI-compatible API to identify weaknesses, prioritize changes, and keep a cumulative record of reviewer responses, actions, and experiment results.
Compare five Codex execution setups on Terminal-Bench 4.0 under matching conditions. The skill covers benchmark configuration, separate verification environments, image preparation, and result interpretation to help identify misleading scores caused by setup errors.
Turn an approved character still into animated game assets, with a separate video for each action. Process generated or supplied clips into transparent, aligned frames, adjust loops and timing, and export images, video, and playback metadata.
Draft clear instructions for an agent to keep working toward a measurable goal. It defines the objective, constraints, validation commands, and stopping conditions, and guides setup, monitoring, and troubleshooting for the agent's supported runtime.
Run DOCA service containers on BlueField using YAML deployment files and standalone kubelet, the agent that starts containers. Check service readiness and troubleshoot startup failures, image downloads, missing mounts, and repeated restarts.
Detect chromatin loops and point interactions from Hi-C data using cooltools, chromosight, and HiCCUPS-like methods. Identify CTCF-mediated loops and enhancer-promoter contacts. Use when detecting chromatin loops from Hi-C data.
The English summary is being prepared. Showing the original description.
Use Superloopy's lightweight strict-evidence loop for Codex tasks that need durable progress, criteria, and artifact-backed completion.
The English summary is being prepared. Showing the original description.
Use only after explicit Codex `$superloopy:i-have-adhd` or Claude Code `/superloopy:i-have-adhd` invocation, or when a qualifying leading `loopy`/`루피` task receives Superloopy's non-diagnostic ADHD-friendly output overlay. Do not activate from typos, fragmented writing, urgency, grammar, language proficiency, or ordinary discussion of ADHD, attention, focus, accessibility, or cognitive load.
The English summary is being prepared. Showing the original description.
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).
The English summary is being prepared. Showing the original description.
Run one task through the V-model verification loop: CP-2 plan → CP-3 build → CP-3v component verify → CP-4 integration verify (full lane) → CP-5 acceptance. The worker never grades its own homework; evidence rows trace back to AC-n. Opt-in: invoke with /closed-loop or by asking for the closed loop, proper verification, or an evidence trail. Ordinary work does not run this.
The English summary is being prepared. Showing the original description.
Detect growth loops in the business and model each loop's amplification by script. "what growth loops do we have"
The English summary is being prepared. Showing the original description.