「decide」の検索結果

Routes LLM requests to a local model first (Ollama, LM Studio, llamafile), validates the response quality, and escalates to cloud only when the local result fails. Tracks local vs escalated vs cloud outcomes in a persistent dashboard. Use when: (1) user asks to run a task with a local model first, (2) user wants to reduce cloud API costs or keep requests private, (3) user wants post-outcome quality validation before committing to a local result, (4) user asks to see token savings or the routing dashboard, (5) any request where local-vs-cloud routing should be decided automatically with a quality gate. Supports Ollama, LM Studio, and llamafile as local providers.

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。

Watch a CI run's jobs to completion without idling or hand-writing a poll loop. Use when a dispatched or pushed build takes minutes to finish and its per-job results decide the next step.

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。

Puts the agent into a cautious production mode for live systems: read-only inspection may proceed, but credentials and out-of-scope personal data need permission first, every state-changing action needs explicit per-action approval with its resource risks and rollback stated, and anything unexpected halts work until the user decides. Use when the user invokes `/prod` or `$prod`, or says they are working on production, a live or customer-facing server, a mail server, or a production database, or asks for care on a system where mistakes affect real users.

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。

Instancia esta plantilla en un proyecto real mediante una entrevista guiada — detecta si el proyecto es nuevo o existente, rellena los placeholders, adapta los docs al tipo de proyecto y decide la política de permisos. Úsalo cuando la persona clone/adopte esta plantilla y quiera configurarla para su proyecto (p. ej. "instancia esta plantilla", "configura este template para mi proyecto", "arranca el proyecto desde esta base").

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 raw idea into ONE honest recommendation: interview one question at a time until the problem, requirements, goals, non-goals, and constraints are CONFIRMED, then deliver a single verdict — do, don't, cheaper alternatives, trade-offs, ordered checklist, success metrics. Required: the user wants exactly ONE recommendation — not options, not a debate — and their framing is open to challenge (advise may answer a different question than the one asked). Triggers on "what should I do about X", "advise me on X", "am I approaching this right", "is this the right move". Do NOT use to be interrogated with no recommendation (→ mk:grill) — advise also interviews one question at a time, but only to reach a verdict. Do NOT use when the framing is settled and only the options are open (→ mk:brainstorming). Do NOT use to decide whether something is worth building (→ mk:office-hours). Do NOT use when you want several perspectives to argue it out (→ mk:party).

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。

Runtime router for context decisions during a task — decide read-more / stop / ask / assume / delegate, pick a minimal read-set, and time compaction. Front-page mental model is Write / Select / Compress / Isolate; a lazy pattern index routes to 25 context-engineering patterns, one reference per decision. Use when context is near budget, a long session is degrading, you must choose what to read for a task, or you are deciding /compact vs /clear vs a sub-agent. NOT for structural .claude/ overhead audits (see mk:context-audit); NOT for owning persistence (see mk:memory); NOT for USD cost (see mk:budget).

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 ruLake as the agent's working memory. Auto-invoke /rulake-memory:memory-recall when the agent needs to look up something it might already know; auto-invoke /rulake-memory:memory-remember after the agent learns or decides something worth pinning. Closes the self-learning loop without requiring the agent author to wire it explicitly.

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。

Save important context to persistent memory for future sessions. PROACTIVELY USE THIS when you detect: - Decisions: "let's go with", "decided to", "chose", "went with" - Learnings: "I learned", "turns out", "TIL", "realized", "discovered" - Errors resolved: "fixed", "the problem was", "solution was" - Client info: names, emails, phone numbers, addresses, invoice amounts - Preferences: "I prefer", "I like", "don't like", "always use" - References: API keys locations, file paths, URLs, credentials - Patterns: "pattern", "convention", "always do", "standard approach" - Important commands run worth remembering Do NOT ask permission - just capture silently when these patterns appear.

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 on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the `cacheComponents` flag, work through a flood of blocking-prerender / instant validation errors, run the `cache-components-instant-false` codemod, or decide between opting routes out with `export const instant = false` and fixing them in place.

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。

Choose what kind of knowledge to transfer between teacher and student models: response, feature, or relational, and decide among offline, online, self, or cross-modal distillation schemes. Best for distillation strategy selection, capacity-gap diagnosis, and transfer planning. Activate on "knowledge distillation", "teacher-student", "soft labels", "feature distillation", "online distillation", or "cross-modal transfer". NOT for generic compression checklists or unrelated training work.

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。

Meta-skill that orchestrates the discourse skill suite: routes between steel-man-argument, socratic-questioning, toulmin-argument-analysis, logical-fallacy-detector, bad-faith-rhetoric-detector, discourse-elision-analyzer, forensic-speech-structure, and productive-discourse-facilitator. Use when analyzing conversations, facilitating discourse, or operating as a dialogue copilot. Maintains mode (silent analysis, coaching overlay, active facilitator) and decides which skills to invoke based on conversation dynamics.

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。

Decides HOW to mutate a DAG when a node fails, quality is below threshold, or new information changes the plan. Selects from mutation strategies (add node, replace agent, fork paths, loop back, downgrade model) based on failure type, cost budget, and execution history. Activate on "DAG failed how to fix", "mutation strategy", "replan on failure", "adaptive DAG", "recovery strategy", "what to do when node fails". NOT for detecting failures (use dag-quality), executing mutations (use dag-planner), or runtime execution (use dag-runtime).

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。

Validates agent outputs against schemas and quality criteria, scores confidence, detects hallucinations, monitors convergence, decides when to iterate, and synthesizes actionable feedback. Use when checking if a node's output is acceptable, scoring confidence, detecting fabricated content, deciding whether to re-execute, or generating improvement feedback. Activate on "validate output", "check quality", "confidence score", "hallucination check", "should we iterate", "improvement feedback". NOT for executing DAGs (use dag-runtime), planning DAGs (use dag-planner), or matching skills (use dag-skills-matcher).

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。

Batch effect correction for CRISPR screens covering ComBat empirical-Bayes, RUV, SVA, control-sgRNA normalization, and the model-based alternative of including batch as a covariate in MAGeCK MLE or Chronos. Covers screen-specific batch sources (passage cohort, library lot, infection day, sequencing run, Cas9 lot, FBS lot), PCA + variance-decomposition diagnostic to decide if correction is needed, when correction harms biology by over-correcting condition into batch, limma removeBatchEffect for visualization-only correction, and relationship to multi-condition design matrices. Use when combining screens for joint analysis, when passage cohort confounds biology, when DepMap-style panels need Chronos with batch covariates, when picking ComBat vs RUV, or when correction harms biology and should be replaced with explicit covariate modeling.

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。

Decides how to preprocess plasma cfDNA sequencing data so the recoverable signal survives - library-prep-aware fragment expectations (dsDNA vs ssDNA/adaptase prep), UMI/duplex consensus with fgbio (ExtractUmisFromBam, GroupReadsByUmi --strategy paired for duplex, CallMolecularConsensusReads vs CallDuplexConsensusReads, FilterConsensusReads min-reads "total s1 s2"), the align->group->consensus->RE-align ordering, and the cfDNA dedup trap where naive coordinate dedup collapses nucleosome-coincident independent molecules. Covers when single-strand consensus suffices vs when duplex is mandatory, the singleton/sensitivity tax at low input, and reading the insert-size histogram as a pre-analytical QC instrument. Use when processing plasma cfDNA reads before fragmentomics, ctDNA mutation calling, or tumor-fraction estimation.

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。

Decide whether commonly-excluded patients (eating disorders, elderly ≥75, upper GI disease) can actually receive a GLP-1 receptor agonist. Use when a clinician asks "can I give semaglutide to a patient with binge eating disorder / anorexia / bulimia", "is liraglutide safe in an 80-year-old", "GLP-1 with GERD or chronic gastritis", "GLP-1 in sarcopenic elderly", or anytime a patient is being ruled out for GLP-1 therapy based on a perceived contraindication. Grounded in Gorgojo-Martínez 2023 §6 (Myths or Reality).

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。

Classify the severity of hypercalcemia at the bedside — mild, moderate, or severe — by combining the corrected/ionized calcium level with the acuity and symptom pattern, and decide whether the patient needs urgent therapy. Trigger when a clinician asks "is this hypercalcemia severe", "how bad is this calcium level", "when to admit for hypercalcemia", "is this hypercalcemic crisis", "how to grade hypercalcemia", or shares a calcium level and asks how worried to be.

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。

Determines whether to perform adrenal venous sampling (AVS) to lateralize aldosterone excess in patients with confirmed primary aldosteronism (PA) who are being evaluated for surgical treatment. Indicated when surgery is feasible and desired by the patient, or when subtype workup is planned for a surgical candidate, especially in those younger than 35 years with spontaneous hypokalemia, marked aldosterone excess, and unilateral adrenal lesions on CT.

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。

Calculate the Maryland Aggregate Pathology Index (MAPI) on a deceased donor procurement kidney biopsy to predict graft survival and decide single vs dual vs discard allocation. Trigger when a clinician asks "what's the MAPI score", "interpret donor kidney biopsy", "should I use this marginal kidney", "MAPI cutoff for transplant", "procurement biopsy scoring", or has histology results from a deceased donor kidney and needs an objective grading.

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。

Decide when to order coronary artery calcium (CAC) scoring in a primary-prevention patient and interpret the result per the 2026 ACC/AHA multisociety dyslipidaemia guideline. Covers the Class 1 indication (men ≥40 / women ≥45, borderline / intermediate PREVENT-ASCVD risk, uncertainty about LLT), CAC score interpretation (0, 1–99, 100–299, ≥300, ≥1000), how CAC modifies LDL and non-HDL goals, when to repeat CAC, and pitfalls (incidental CAC on non-cardiac CT, radiation, cost). Use when a clinician asks should I order a CAC score, CAC indications, what does CAC 150 mean, treatment goals with CAC score, repeat CAC frequency, CAC in a smoker, CAC vs CCTA, is CAC useful in intermediate risk. Grounded in the 2026 ACC/AHA multisociety dyslipidaemia guideline.

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。

Decide whether a kidney from a brain-dead deceased donor (DBD) with diabetes mellitus and/or hypertension is suitable for transplantation, using the ISOT 2025 Delphi consensus and Table 4 eligibility checklist. Trigger when a clinician asks "can I use a kidney from a diabetic deceased donor", "is this DBD with HTN/DM acceptable", "ECD donor with diabetes — accept or decline", "DBD eligibility for hypertensive donor", or shares a deceased donor with diabetes or hypertension and needs an accept/borderline/decline decision.

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。

Execute a swarm plan wave by wave with filesystem isolation via git worktrees. For each wave, main context decides the scenario recipe + implementation contract for every task, then spawns one swarm-worker per task in parallel. Each worker executes its recipe and reports JSON status. Worktree merge-audit verifies write-set discipline before changes land on main. Aborts remaining waves on any audit or task 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。

Workflow Phase 6 — TDD coordinator. Decides the scenario recipe and the implementation contract in main context, writes them to a state file, seeds per-worker tasks (scenario, implement, verify-tick, design-ui-tick) into the TaskList, and yields with harness_state continue so the harness invokes each worker as its own tick. No subagent delegation; no nested Skill calls.

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。

End-to-end workflow orchestrator. Walks the 11-phase pipeline, invoking each phase skill in order inside an internal loop, yielding at consent gates (/approve-direction, /approve-swarm, /grant-commit), and exiting cleanly on yield/failure/done. Decides swarm-vs-solo at Phase 6. Auto-loops /tdd on integrate failures that don't require a spec change. The harness_continuation Stop hook is a safety net that re-fires harness only when the loop exited mid-flow.

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。