提示词与推理

interview-me

78Kprompting-reasoning

提取用户实际想要的东西，而不是他们认为自己应该想要的东西。通过一次一问的访谈方式实现，直到对底层意图的置信度达到约95%。当需求表述不明确（例如“给我建个X”但没有说明“给谁用”或“为什么现在做”）、用户明确要求（如“采访我”、“拷问我”、“我们确定吗？”、“压力测试我的想法”），或者在你开始制定任何计划、规格或代码之前，发现自己正在默默填补模糊需求时使用。

addyosmani

cavecrew

75Kprompting-reasoning

将任务委托给穴居人风格子代理的决策指南。告诉主线程何时生成 `cavecrew-investigator`（定位代码）、`cavecrew-builder`（1-2 文件编辑）或 `cavecrew-reviewer`（差异审查），而不是内联执行或使用普通的 `Explore`。子代理输出经过穴居人压缩，因此注入回主上下文的工具结果约小 60%——在长时间会话中，主上下文能维持更久。触发词：“委托给子代理”、“使用 cavecrew”、“生成 investigator/builder/reviewer”、“节省上下文”、“压缩代理输出”。

caveman-stats

75Kprompting-reasoning

显示当前会话的实际令牌使用量和预估节省金额。直接从 Claude Code 会话日志读取——无 AI 估算。通过 /caveman-stats 触发。输出由 mode-tracker 钩子注入；模型本身不计算数字。

caveman-commit

73Kprompting-reasoning

超精简提交信息生成器。去除提交信息中的噪音，同时保留意图和理由。采用 Conventional Commits 格式。主题行 ≤50 字符，仅在“为什么”不明显时添加正文。当用户说“写提交”、“提交信息”、“生成提交”、“/commit”或调用 /caveman-commit 时使用。暂存更改时自动触发。

caveman-review

73Kprompting-reasoning

超精简代码审查评论。去除PR反馈中的废话，保留可操作的关键信息。每条评论仅一行：位置、问题、修复。当用户说“review this PR”、“code review”、“review the diff”、“/review”或调用/caveman-review时使用。审查拉取请求时自动触发。

caveman-help

73Kprompting-reasoning

所有 caveman 模式、技能和命令的快速参考卡。一次性显示，非持久模式。触发词：/caveman-help、"caveman help"、"what caveman commands"、"how do I use caveman"。

caveman

72Kprompting-reasoning

超压缩沟通模式。通过像穴居人一样说话，减少约75%的令牌使用，同时保持完整的技术准确性。支持强度级别：lite、full（默认）、ultra、wenyan-lite、wenyan-full、wenyan-ultra。当用户说“caveman mode”、“talk like caveman”、“use caveman”、“less tokens”、“be brief”或调用/caveman时使用。当请求令牌效率时也会自动触发。

openspec-update-change

67Kprompting-reasoning

Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.

fission-ai

bmad-forge-idea

Test a half-formed idea in a questioning conversation, with different personas probing its weak points, until the user can act on it or drop it with confidence. Optionally writes a short brief for planning skills to build on. Use when the user says 'forge an idea', 'pressure-test this idea', 'stress-test my thinking', or 'harden this idea'

bmad-build-auto

One iteration of an unattended development loop. Use when invoked by name

bmad-party-mode

Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties. Use when the user requests party mode, a roundtable, or multiple agent perspectives — or wants to create/configure a party, define personas, or build an AI focus-group panel

bmad-agent-pm

Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager

prompt-engineering

46Kprompting-reasoning

Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.

sickn33

ai-agents-architect

46Kprompting-reasoning

设计并构建自主AI代理的专家。精通工具使用、记忆系统、规划策略和多代理编排。

sickn33

prompt-engineer

45Kprompting-reasoning

Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)

sickn33

consciousness-council

42Kprompting-reasoning

Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints, needs help making a tough decision, asks for a council/panel/board discussion, wants to explore a problem from multiple angles, requests devil's advocate analysis, or says things like "what would different experts think about this", "help me think through this from all sides", "council mode", "mind council", or "deliberate on this". Also trigger when the user faces a dilemma, trade-off, or complex choice with no obvious answer.

k-dense-ai

phoenix-tracing

OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.

arize-link

Generates deep links to the Arize UI for traces, spans, sessions, datasets, labeling queues, evaluators, and annotation configs. Produces clickable URLs for sharing Arize resources with team members. Use when the user wants to link to or open a trace, span, session, dataset, evaluator, or annotation config in the Arize UI.

arize-dataset

Creates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI. Use when the user needs test data, evaluation examples, or mentions create dataset, list datasets, export dataset, append examples, dataset version, golden dataset, or test set.

arize-annotation

Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize. Applies human annotations to project spans via the Python SDK. Use when the user mentions annotation config, annotation queue, label schema, human feedback, bulk annotate spans, update_annotations, labeling queue, annotate record, or human review.

arize-experiment

Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the ax CLI. Use when the user mentions create experiment, run experiment, compare models, model performance, evaluate AI, experiment results, benchmark, A/B test models, or measure accuracy.

arize-evaluator

Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and continuous monitoring. Use when the user mentions create evaluator, LLM judge, hallucination, faithfulness, correctness, relevance, run eval, score spans, score experiment, trigger-run, column mapping, continuous monitoring, or improve evaluator prompt.

arize-prompt-optimization

Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.