기타 스킬

Cross-compile Cadmus for Kobo e-reader devices (ARM Linux). Use this when asked to build a Kobo release, cross-compile for ARM, or prepare a device binary.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Simulates a realistic VC Investment Committee: three partner archetypes debate a startup's merits, concerns, and deal terms, scored across 28 dimensions. Use when the user asks to simulate an IC, or how partners would debate their startup, and gives a deck, a company description, or a specific fund. A full run takes about 15–20 minutes, so for a passing question such as 'would a VC fund us?' or 'are we fundable?', answer briefly in chat and offer the simulation instead of starting it. When it runs, partners' views come from the scored simulation, never improvised.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Maps a startup's competitive landscape, scores moat strength across 6+ dimensions, and writes an investor-ready competition narrative with a positioning map. Use when the user asks for a competitive landscape, moat analysis, or positioning review and gives enough to work from: a deck, a list of competitors, or a clearly named startup. A full run takes about 30–40 minutes and searches the web, so for a passing question such as 'who are my competitors?' or 'is that a real moat?', answer briefly in chat and offer the analysis instead of starting it. When it runs, the competitor set and moat scores are checked adversarially, never recalled from memory.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Send feedback about founder-skills — report a bug, suggest an idea, ask for help, or share a win. Drafts your message and gives you a link to submit; nothing is sent automatically.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up a construction project — inventories files, classifies drawings/specs/schedules/registers and appends construction context to CLAUDE.md; in an AgentCM project, prints AgentCM's orientation instead. Triggers: 'set up project', 'construction setup', 'classify documents'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Draft RFIs and manage the ambient issue registry. Reviews issues surfaced by other skills, escalates to formal RFIs. Triggers: 'draft RFI', 'write RFI', 'drawing conflict', 'review issues', 'issue queue'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

改写中文学术论文中被知网AIGC检测器标为"红色显著"的段落，目标是将AI率落出红色区间且不改变事实/数字/术语/引用。基于实战将20.6%降至10.1%（净降10.5个百分点）的工作流提炼。使用场景：用户提到"知网AIGC""降AI率""红色显著""降重"或贴出AIGC检测报告片段时触发。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

直连网络服务攻击链。用于已经识别/枚举的非专门领域服务，从数据库、数据存储、文件/远程访问、基础设施、消息队列、DNS/网络服务、打印机/MFP/NAS/BMC/网络设备等服务入口继续利用到凭据、代码执行、主机控制、横向能力或新的独立身份。由操作者选择具体攻击链；不自动切换模块。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

通用网络与资产信息收集。面向 IP、CIDR、主机名、企业/域名等尚未明确攻击面的目标，完成资产扩展、主机发现、TCP/UDP端口发现、服务/版本/协议识别、只读服务枚举、网络设备识别和漏洞候选研判。Recon only：不执行漏洞利用、口令爆破、服务配置修改或持久化。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Network reachability and pivoting after an operator already has a foothold. Use to make previously unreachable hosts, subnets, services or listener directions reachable via Ligolo-ng, Chisel, GOST v3, SSH/native forwarding, socat/netsh, Microsoft Dev Tunnels, DNS/HTTP/QUIC fallback transports, and multi-hop routing. This module does not exploit services, obtain credentials, or own C2/persistence. Its success condition is changed reachability: the operator can route/connect to the intended internal network/service through the selected foothold.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

host chinese call of cthulhu and similar investigative tabletop rpg sessions as kp/keeper. use when the user asks to start, continue, simulate, or play a coc scenario, wants chatgpt to be kp, asks for preset investigator cards, npc teammates, dice checks, horror investigation pacing, solo/co-op tabletop roleplaying, or persistent pre-session prep/project folders for a campaign. ask only the minimum setup questions: whether the user wants a custom investigator persona and how many npc teammates; otherwise handle scenario selection, character card creation, npc teammates, dice, pacing, narration, and campaign notes automatically.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Prepare, refine, order, and assess a real-product backlog for an upcoming LeSS in Action (LIA) class. Use when selecting class-sized product features, investigating how much of an idea already exists, turning feature themes into vertical interdependent user stories, adding high-value items, or facilitating Product Backlog refinement for teams working on Donut or another production product.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Apply the latest released Open Dough guidance from this project's recorded source, or from a supplied repository URL on first install. Use when the user asks to update Open Dough or invokes dough-update.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Maintains this project's retrospective findings, separates project and shared responsibility, follows adopted fixes through observation and recurrence, and queues zero to three supported new leading improvement stories, then commits and synchronizes the maintenance result. Use only on explicit invocation or as an expressly named phase of a user-invoked combined cycle for its selected project set. Reading findings or completing a retrospective does not invoke it. Does not implement the improvements.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Dough Land lands everything in one reviewed checkout on the authorized remote trunk: commits all of its changes, reconciles and publishes them without force, and refreshes a supplied default checkout when safe. An owned worktree is retired with its branch after completion gates hold and trunk contains its work; the default checkout stays in place. Ordinary landing refuses unfinished execution before commit; `--keep-worktree` selects an explicit retained increment. Use only on explicit invocation, such as "/dough-land", "use Dough Land", "land this worktree", or "land" for changes made on the default checkout, or when another skill's validated keep instruction or findings maintenance handoff links here. A casual "keep", "looks good", or approval does not invoke it. Hosted merges and pull requests are out of scope. With `--process-retrospective`, it also reviews the landing's own process and records supported findings in `DearDough.md`.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Finds and assesses existing solutions across the whole product before an implementation responsibility is added or relocated. Use for PFE, Proudly Found Elsewhere, or when deciding whether to reuse, change, modularize, or replace an existing product solution.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

去除 NSFC 标书中的 AI 机器味，覆盖词语、句法、段落和章节层，尤其处理伪对立、工程协议腔、规格书式字段串、术语漂移、定义后连续否定排除项、边界声明过重和研究动作不清（不适用：非标书内容/需修改格式/需补充新内容）；兼容旧名 nsfc-humanization 的润色请求

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Eloquent ORM best practices: query builders, scopes, relations, N+1 prevention, batch operations, soft deletes, model events, raw queries when needed. Apply when: writing or reviewing Eloquent queries and model interactions. Activated automatically by laravel-plugin/stack.md as a convention skill for the development phase.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

读取指定 CBB / protocol wiki 文件，解析其 ## Interface / ## Ports section，返回结构化端口表 + 参数表。bba-architect 用于填入 MAS 模块接口。触发场景：(1) bb-search-cbb 命中后取详细接口；(2) 显式 /bb-get-interface-template。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

统一质量门禁：RTL / 综合 / 测试 / PD 四阶段验收。调用共享 gate_runner.py 参数化。触发：(1) bba-guru-* 在阶段结束时调用；(2) 显式 /bb-gate <domain>。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

调用 Netgen 1.5.275 做 LVS 对比：综合网表 vs Magic 提取的 SPICE，必须 match 才能 signoff。触发场景：(1) bba-guru-pd extract 后做 LVS；(2) 显式 /bb-invoke-netgen。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

调用 Magic 8.3.641 执行 PD 操作：floorplan / place / DRC / layout extraction。触发场景：(1) bba-guru-pd 做 floorplan 与 placement；(2) routing 后做 DRC；(3) LVS 前 extract SPICE；(4) 显式 /bb-invoke-magic。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

<一句话说清『这个 skill 做什么 + 何时调用』。把最关键的触发场景放最前面。结尾给 2-3 个用户会说的关键词。>

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

调用 babel-lsp / verible-verilog-lint 检查 SV 源码。src 必须可综合（零 syntax error），tb 允许 verification constructs。发现 src error 时自动修复重检（max 3 iter）。触发：(1) bba-guru-rtl 生成后；(2) RTL 修复重检；(3) 显式 /bb-check-lint。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.