840 个 · 按相关度排序
Run a support investigation as a suggest-and-interpret loop, never executing anything yourself — orient to the product's support pack and follow the signal with judgment. Use when someone asks for help triaging, investigating, or resolving an operational or support issue on a deployment. Not for feature-development cards (see investigate-and-fix and implement-this).
中文简介正在准备中。当前显示原文说明。
Checks whether AI-assisted work defines review criteria, accessible context, explicit review loop, human judgment boundary, and feedback capture before delegating to an agent.
中文简介正在准备中。当前显示原文说明。
Delegate real-world tasks to human workers via the OpenHumancy API. Use when the user needs physical actions (field verification, photography, deliveries, mystery shopping), human judgment, or any task that requires a person. Manages the full lifecycle — worker search, task creation, chat, payments on the TON blockchain.
中文简介正在准备中。当前显示原文说明。
Rank multiple design solutions and explain why. Separate personal preference from quality judgment. Use when comparing design options, evaluating competing approaches, or making design decisions with clear reasoning.
中文简介正在准备中。当前显示原文说明。
Help other designers develop judgment without imposing your style. Use when mentoring designers, running design education, or building team-wide quality standards.
中文简介正在准备中。当前显示原文说明。
Experimental workflow for summarizing work that still needs human judgment across configured pull requests, issues, feedback, errors, and delivery signals. Use for a human decision queue or bounded review.
中文简介正在准备中。当前显示原文说明。
Use when the user provides multiple options and wants a specific 16-minds (MBTI) personality to make the decision in that personality's judgment style. Triggers on Japanese phrases like 「ENTJで決めて」「INFPならどっち選ぶ」「INTJとして判断して」, English equivalents like "decide as ESTJ" / "which would ENFP pick", or 16-minds commands with a `--decide` flag. Requires both a personality and 2+ options to be present or extractable from the request.
中文简介正在准备中。当前显示原文说明。
Use when the user wants all 16 personality types (16-minds plugin) to vote on a proposal — yes/no/abstain — to see stakeholder distribution, detect hidden objections, or simulate organizational consensus. Triggers on Japanese phrases like 「全人格で投票」「16人格に賛否を聞いて」「ステークホルダーシミュ」「これ通せそう？」, English equivalents like "vote with all 16 minds" / "stakeholder simulation", or `--vote` flag on 16-minds commands. Different from /minds (which is for opinion divergence) — this is for binary judgment aggregation.
中文简介正在准备中。当前显示原文说明。
Use when user has ADHD or attention differences — tracks current task, catches conversation drift, and nudges back on topic without judgment or guilt.
中文简介正在准备中。当前显示原文说明。
Legal casebase App-in-Skill (Busabase-backed) intake and anonymization QA desk for law-firm judgment and award documents. Use when the user invokes $kelly-legal-casebase-ingest, mentions internal case database, 智能案例库, 裁判文书入库, 脱敏, 结构化, 分类标注, 案例审核, 质量验收, or wants a Busabase-backed desk where reviewers approve, revise, or block agent-prepared case records before they become searchable knowledge assets.
中文简介正在准备中。当前显示原文说明。
Delegate writing predictable code to the `code-write` command, which has a cheaper writer model write the target file directly so the generated code never enters your context. Use for tests, scaffolding, fixtures, boilerplate, or a new file that copies an existing pattern, and when the user says "code write", "生成を委譲", or "雛形を書かせて". Do NOT use for design decisions, changes to public contracts or shared modules, edits inside an existing file that needs judgment, or logic with subtle correctness requirements.
中文简介正在准备中。当前显示原文说明。
Evaluate an interface from a UX perspective, assessing hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with evidence-linked judgments and actionable feedback. Use when the user wants an overall design or UX review—not when the main need is measurable accessibility/performance diagnosis, or final micro-detail polish.
中文简介正在准备中。当前显示原文说明。
Autonomous themed tech-debt cleanup. Reads docs/architecture/debt-ledger.yml, rotates to the least-recently-served debt theme, works it for a time budget (default 2h) or until drained, opens one PR, and asks judgment questions inline at the end. Use for daily debt burndown without Peter pointing at a target: grandfathered analyzer rules, architecture-test baselines, obsolete-field reads, cross-section stitching.
中文简介正在准备中。当前显示原文说明。
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.
中文简介正在准备中。当前显示原文说明。
Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.
中文简介正在准备中。当前显示原文说明。
Identify and counteract cognitive biases in medical decision-making through systematic error analysis and contextual algorithm application. For diagnostic reasoning, treatment decisions, and clinical judgment improvement. NOT for basic medical knowledge, technical procedures, or non-clinical healthcare domains.
中文简介正在准备中。当前显示原文说明。
Diagnose when intuitive judgment, agent confidence, or expert routing can be trusted by classifying environment validity, feedback quality, and task-boundary fit. Use for confidence calibration, agent routing, expertise audits, and escalation design. NOT for deterministic implementation tasks, pure syntax debugging, or domains with explicit verifiable answers.
中文简介正在准备中。当前显示原文说明。
Analyze repeated non-engagement, deflection, motte-and-bailey shifts, tone policing, sealioning, and related manipulative discourse patterns. Use when the user suspects they are being rhetorically managed rather than answered, or when they need a careful pattern read grounded in quotes and alternatives. NOT for psychiatric diagnosis, legal judgment, or help deploying bad-faith tactics.
中文简介正在准备中。当前显示原文说明。
Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.
中文简介正在准备中。当前显示原文说明。
Apply cognitive task analysis to expert work that depends on perceptual cues, branching judgment, and recurring monitoring loops. Use when decomposing expert capability into agent structure, simulation design, or validation interviews. NOT for ordinary step-by-step SOP capture or simple pipelines with no tacit cue layer.
中文简介正在准备中。当前显示原文说明。
Delegate a read-only Coval evaluation, simulation, monitoring, product-how-to, or troubleshooting subtask to Sofia through the official Coval MCP consult_sofia tool. Use when the user needs Coval-specific FDE judgment, analysis of organization data, metric or test-set recommendations, or a diagnosis grounded in Coval runs and conversations.
中文简介正在准备中。当前显示原文说明。
Lean, sharp UI posture — the everyday default for building or redesigning a UI. Use when asked to build or make a page, panel, list, form, or dashboard good, cleaner, or nicer, or for a fast confident refresh where the agent uses its judgment instead of asking for a spec.
中文简介正在准备中。当前显示原文说明。
Codified expertise for handling freight exceptions, shipment delays, damages, losses, and carrier disputes. Informed by logistics professionals with 15+ years operational experience. Includes escalation protocols, carrier-specific behaviors, claims procedures, and judgment frameworks. Use when handling shipping exceptions, freight claims, delivery issues, or carrier disputes.
中文简介正在准备中。当前显示原文说明。
Guardian Angel gives AI agents a moral conscience rooted in Thomistic virtue ethics. Rather than relying solely on rule lists, it cultivates stable virtuous dispositions— prudence, justice, fortitude, temperance—that guide every interaction. The foundation is caritas: willing the good of the person you serve. From this flow the cardinal virtues as practical habits of right action and sound judgment. v3.0 introduced virtue-based disposition as the primary evaluation layer, providing deeper coherence than checklists alone. The agent's character becomes the safeguard. v3.1 adds: Plugin enforcement layer with before_tool_call hooks, approval workflows for ambiguous cases, and protections for sensitive infrastructure actions.
中文简介正在准备中。当前显示原文说明。