提示词与推理
提示词工程、角色设定和推理模式
Skills 列表
santa-method
多智能体对抗性验证与收敛循环。两个独立的审查智能体必须同时通过，输出才能发布。
affaan-mcouncil
召集四声议会，处理模糊决策、权衡取舍和放行/叫停判断。当存在多条合理路径且需要在选择前进行结构化辩论时使用。
affaan-mck
Claude Code 的持久化项目记忆。自动加载项目上下文，通过 Git 活动追踪会话，并写入原生记忆。命令运行确定性 Node.js 脚本——行为在不同模型版本间保持一致。
affaan-mfoundation-models-on-device
Apple FoundationModels 框架，用于设备端 LLM — 文本生成、使用 @Generable 的引导生成、工具调用以及 iOS 26+ 中的快照流式传输。
affaan-magent-harness-construction
设计和优化AI智能体的动作空间、工具定义和观察格式化，以提高任务完成率。
affaan-mcost-aware-llm-pipeline
LLM API 使用成本优化模式——根据任务复杂度进行模型路由、预算跟踪、重试逻辑和提示缓存。
affaan-msecurity-scan
使用 AgentShield 扫描您的 Claude Code 配置（.claude/ 目录），检查安全漏洞、配置错误和注入风险。检测 CLAUDE.md、settings.json、MCP 服务器、hooks 和代理定义。
affaan-meval-harness
Claude Code 会话的正式评估框架，实现评估驱动开发（EDD）原则
affaan-m
skill-creator
创建新 Skill、修改并优化现有 Skill，以及评估 Skill 的运行表现。当用户需要从头创建 Skill、编辑或优化现有 Skill、运行 eval 测试 Skill、通过方差分析对 Skill 性能进行基准测试，或者优化 Skill 的 description 以提高触发准确率时使用。
anthropics
caveman-explore
Read-only repository explorer. Use PROACTIVELY for cold-start exploration, broad cross-file localization, or when a direct search has failed and you need to find where something lives. Skip it when the issue already names the exact file or symbol, or a previous turn already returned usable file:line evidence. Returns only compact path:line citations; its reads and greps never enter the main conversation.
juliusbrusseecaveman-optimize
Turn Caveman's exact report-only repository observations into an operator-chosen optimization candidate with a paired baseline/candidate evaluation. Use when the user asks to inspect an optimization observation, evaluate a candidate change, or act on the current Caveman optimization report. Require a logged-in Caveman CLI connection and explicit approval; never infer money or actuation from a profile.
juliusbrusseeinvestigate-first
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
juliusbrusseeverify-and-stop
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
juliusbrusseesurgical-patch
Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
juliusbrusseesafe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
juliusbrusseecaveman-learn
Close the loop on a Caveman learn report — review the ranked token sinks and apply cost-lowering fixes (trim config, offload recurring context to cavemem) with per-edit consent. Use when the user runs "caveman learn", asks to lower their agent's token cost, wants to trim a heavy CLAUDE.md, or wants to offload context they re-paste every session into cavemem.
juliusbrusseelean-build
Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
juliusbrusseecaveman-evidence-review
Review Caveman Cloud evidence read-only: costs, Cave Score, Cave Plan, workflows, traces, latency, errors, compression, routing, and verified savings. Use when the user asks what Caveman found, where LLM spend goes, why cost or quality changed, which workflows need attention, or asks for a trace or analytics review. Prefer Caveman MCP tools; fall back to CLI JSON.
juliusbrusseecaveman-discover
Find every LLM workflow in the current repository and label it, so Caveman Cloud groups spend by what the code actually does (support-reply, nightly-digest) instead of one anonymous bucket. Use when the user pastes the Caveman discovery prompt, says "discover workflows", or asks to break LLM spend down by workflow. The repo should already route through the Caveman gateway (the caveman-setup skill does that part).
juliusbrusseecaveman-manage
Inspect Caveman Cloud's eval-gated experiment lifecycle and block unsafe execution. Use when the user asks to start, approve, cancel, promote, or roll back a Caveman experiment, or asks what action an experiment's evidence supports. Read evidence first; do not execute lifecycle mutations until server-authoritative transition and evidence gates ship.
juliusbrusseemigration
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
juliusbrussee
ponytail-gain
以紧凑记分牌形式展示 ponytail 的实测影响：更少代码、更低成本、更高速度，数据来自基准测试中位数。一次性显示，非持久模式，也非每个仓库的数值。触发方式：/ponytail-gain、“ponytail gain”、“what does ponytail save”、“show ponytail impact”、“ponytail scoreboard”。
dietrichgebertponytail-debt
将代码库中所有 `ponytail:` 注释收集到债务台账中，使 ponytail 留下的有意捷径和延期得到跟踪，而不是腐烂成“以后意味着永远”。当用户说“ponytail debt”、“/ponytail-debt”、“what did ponytail defer”、“list the shortcuts”、“ponytail ledger”或“what did we mark to do later”时使用。一次性报告，不改变任何内容。
dietrichgebertponytail-review
专注于过度工程的代码审查。找出可以删除的内容：重新发明的标准库、不必要的依赖、投机性抽象、死掉的灵活性。每个发现一行：位置、要删除的内容、替代方案。当用户说“审查过度工程”、“我们可以删除什么”、“这是否过度工程”、“简化审查”或调用 /ponytail-review 时使用。补充以正确性为重点的审查，此审查仅寻找复杂性。
dietrichgebert