搜索
搜索结果
49 results for "juliusbrussee"
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.
juliusbrusseecaveman-setup
Wire the current repository through the Caveman Cloud gateway so every LLM request is measured — cost, tokens, latency — with zero behavior change. Use when the user pastes the Caveman setup prompt, says "set up caveman", or wants LLM spend observability added to an app. Requires the gateway URL and a Cave API key (the setup prompt carries both).
juliusbrusseemigration
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
juliusbrusseecavecrew
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”。
juliusbrusseecaveman-stats
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。
juliusbrusseecaveman-commit
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。
juliusbrusseecaveman-review
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。
juliusbrusseecaveman-compress
将自然语言记忆文件（CLAUDE.md、待办事项、偏好设置等）压缩为“穴居人（caveman）”极简格式，以节省输入 Token。完全保留所有技术干货、代码、URL 及结构。压缩版本将直接覆盖原文件，同时保存一份可读性强的备份为 FILE.original.md。触发词：/caveman-compress <文件路径> 或“压缩记忆文件”。
juliusbrusseecaveman-help
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"。
juliusbrusseecaveman
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。
juliusbrusseebuild
针对 SPEC.md 进行先规划后执行的实现。原生单线程循环，无子代理。测试或构建失败时，在重试前自动调用 backprop 技能——失败的验证总会考虑新的 §V 不变量是否能防止再次发生。当用户要求构建、实现、执行规范或处理特定 §T 任务时触发（`build §T.3`、`build --next`、`implement next task`、`run the build`）。期望 SPEC.md 存在；如果不存在，则交由 spec 技能处理。
juliusbrusseespec
在仓库根目录创建、修订或反向传播缺陷到 SPEC.md。作为项目规格的唯一修改者。当用户要求编写规格、启动新规格、从现有代码提炼规格、添加不变量、修订章节（§G、§C、§I、§V、§T、§B）或通过反向传播记录缺陷时触发。常见表述：“为……编写规格”、“新规格”、“缺陷：……”、“修订 §V.3”、“从代码提炼规格”、“规格化这个想法”。读取并遵循 FORMAT.md 中的原始编码规则以及 §T 和 §B 的管道表格式。
juliusbrusseecheck
只读漂移检测器。将 SPEC.md 与当前代码进行差异比较，并按严重程度分组报告违规情况。不写入任何内容——通过 spec 或 build 技能建议修复方法，但绝不调用它们。当用户要求检查漂移、审计规范、验证不变量，或询问代码是否仍符合规范时触发。表述方式："check drift"、"audit the spec"、"does the code still match §V"、"check invariants"、"spec vs code"。
juliusbrusseebackprop
Bug 到 Spec 的反向回溯协议。当发现 Bug 或测试失败时，追查根因，判断新增 §V 不变量是否能防止复发，并将记录追加至 §B。这是 SDD（规范驱动开发）区别于常规“先规划后执行”模式中最精妙的一环。触发场景包括：测试失败、Bug 报告、事故复盘或用户明确要求。
juliusbrussee