379 个 · 按相关度排序
Primary and secondary source analysis for historical reasoning. Covers source classification, sourcing (author/context/purpose), corroboration across multiple sources, contextualization within time and place, and bias detection. Use when evaluating historical evidence, assessing source reliability, or constructing evidence-based historical arguments.
中文简介正在准备中。当前显示原文说明。
Runs a deliberative two-model committee of GPT-6 Astra and Claude Opus under a selectable chair, Fable by default, with `/model-committee-astra`, `/model-committee-opus`, and `/model-committee-sol` selecting the others. Use when a consequential decision has several defensible options and two model families should propose, critique, revise, and cross-rank them against a predeclared rubric before converging, as in research design, interpretation, architecture, manuscript strategy, or evaluation design. Not for factual lookups, independent-coder reliability, brainstorming, routine implementation, or final professional judgment.
中文简介正在准备中。当前显示原文说明。
Designs survey instruments, covering question wording, scale construction and index reliability, flow and treatment placement, pretesting and soft launches, respondent burden with attention and speeding rules, sensitive questions and social-desirability bias, and treatment delivery. Use when the user writes or revises survey questions, chooses a scale, orders blocks, plans a pilot, or worries respondents will not answer honestly. Indirect measurement goes to list-experiment, multi-country instruments to cross-national-design, and live-survey operations to qualtrics-ops.
中文简介正在准备中。当前显示原文说明。
Run one consequential, contestable decision through a deliberative committee of GPT-6 Astra and Claude Opus, chaired by fable (default), astra, opus, or sol. Not for factual lookups, brainstorming, routine implementation, independent-coder reliability, or final professional judgment. Use when several options are defensible and the two model families should propose, critique, revise, and cross-rank under a predeclared rubric.
中文简介正在准备中。当前显示原文说明。
Reads a model's own uncertainty from token log-probabilities: collecting and aggregating label logprobs, confidence tiers and margins for triage, calibration against human labels (ECE, Brier, reliability diagrams), downstream use, and reproducibility. Use for per-item classifier confidence or routing low-confidence cases to human review; codebook and validation design go to text-classification.
中文简介正在准备中。当前显示原文说明。
Designs survey instruments: question wording, scales and index reliability, flow and treatment placement, pretesting, attention and speeding rules, and sensitive questions. Use when writing or revising survey questions, choosing scales, ordering blocks, or planning a pilot.
中文简介正在准备中。当前显示原文说明。
Expert prompt engineer specializing in designing, optimizing, and managing prompts for large language models. Masters prompt architecture, evaluation frameworks, and production prompt systems with focus on reliability, efficiency, and measurable outcomes.
中文简介正在准备中。当前显示原文说明。
Expert payment integration specialist mastering payment gateway integration, PCI compliance, and financial transaction processing. Specializes in secure payment flows, multi-currency support, and fraud prevention with focus on reliability, compliance, and seamless user experience.
中文简介正在准备中。当前显示原文说明。
Compare browser-agent reliability on a repeatable task and anti-bot suite before choosing a stack or claiming progress.
中文简介正在准备中。当前显示原文说明。
Use Caliper to run real agent tasks with and without a skill, MCP server, or rule change so reliability and token cost are measurable.
中文简介正在准备中。当前显示原文说明。
可靠性工程时使用。适用于 SLO 定义 / 错误预算管理 / Chaos Engineering / 灾备演练。融合 Google SRE SLO + Netflix Chaos Monkey。
中文简介正在准备中。当前显示原文说明。
Apply MCAF non-functional-requirements guidance to capture or refine explicit quality attributes such as accessibility, reliability, scalability, maintainability, performance, and compliance. Use when a feature or architecture change needs explicit quality attributes and trade-offs.
中文简介正在准备中。当前显示原文说明。
Refresh evaluation harnesses with live/fallback parser reliability, SLO gates, and regression checks.
中文简介正在准备中。当前显示原文说明。
Use when agent-produced work needs a safety, evidence, and reliability check before handoff, merge, or trust.
中文简介正在准备中。当前显示原文说明。
按 TRACE 框架（Trust / Reliability / Adaptability / Convention / Effectiveness，5 维 15 子项）评测 Skill 包质量。当用户说『用 TRACE 评测』『评一下这个 skill』『skill 质量打分』『五维度评测』『帮我评估这个技能包』『TRACE evaluation』等需要给 Skill 打分出报告时使用本技能。
中文简介正在准备中。当前显示原文说明。
Use when skill or knowledge activation is unreliable, or setup reaches activation reliability. Not for remote, credential, publish, deploy, or irreversible changes.
中文简介正在准备中。当前显示原文说明。
Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses. Use when user says “be 100% sure”, “no hallucinations”, “only if verified”, “grounded answer”, or when stakes are high.
中文简介正在准备中。当前显示原文说明。
Use when the user asks for a code review by a fleet of specialized reviewer agents, wants multiple independent reviewer perspectives, or asks to run reviewers in single-pass or iterative fix-until-clean mode. Launches focused subagents for correctness, security, architecture, conventions, simplicity, UX, reliability, telemetry, testing, compatibility, and documentation review.
中文简介正在准备中。当前显示原文说明。
Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses. Use when user says “be 100% sure”, “no hallucinations”, “only if verified”, “grounded answer”, or when stakes are high.
中文简介正在准备中。当前显示原文说明。
Prompt engineering and task-specification skill for improving prompts, agent instructions, system messages, evaluation prompts, coding-agent tasks, multi-step workflows, and LLM output reliability. Use when rewriting vague prompts, adding constraints, reducing ambiguity, improving safety, creating reusable prompt templates, or converting goals into actionable agent instructions.
中文简介正在准备中。当前显示原文说明。
Python engineering skill for implementing, debugging, testing, packaging, typing, reviewing, and refactoring Python applications, scripts, APIs, automation, data processing, CLIs, and libraries. Use for .py files, pyproject.toml, requirements files, pytest, async Python, type hints, packaging, dependency management, and Python performance or reliability work.
中文简介正在准备中。当前显示原文说明。
Evaluate AI agent performance and reliability. TRIGGERS - Use when user needs help with ai-agent-evaluation related tasks.
中文简介正在准备中。当前显示原文说明。
Optimize multi-agent systems with coordinated profiling, workload distribution, and cost-aware orchestration. Use when improving agent performance, throughput, or reliability.
中文简介正在准备中。当前显示原文说明。
Design reliable, safe, and trustworthy agent systems that fail gracefully and operate within bounds. Use when building guardrails, handling edge cases, preventing harmful outputs, monitoring for failures, implementing safety constraints, or designing error recovery. Covers failure modes, constraint systems, oversight mechanisms, and safety validation.
中文简介正在准备中。当前显示原文说明。