ceilf6
- 60 skills
- 0 followers
- 6 hours ago last updated
- ▌ Gitnexus CLI 2 · ceilf6Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"
- ▌ Repo Evolver 2 · ceilf6 bundle当需要自主循环审视仓库、发现改进点、创建 issue、编写方案、实现变更、提交 PR 并处理 repo-guard 审评反馈时使用。支持 meta-improvement：当 repo-guard 质量偏低时自动优化其 prompts 和 skills。
- ▌ Persona Review 2 · ceilf6 bundle三视角简历评审：渲染当前简历 PDF，HR 初筛/技术面试官/技术主管三个 persona 并行冷读，产出 problems/questions 各 3 份 + 对账摘要。用户说"三视角评审""跑一轮 persona review""让 HR/面试官/主管看简历"或简历大改后要求重新评审时使用。
- ▌ Macos Enterprise App Cleanup · ceilf6Clean up macOS enterprise, MDM, VPN, EDR, security, and company-internal software remnants after a user leaves a company. Use this skill whenever the user asks to remove or audit corporate software, agents, proxies, VPNs, endpoint security, launch agents, system extensions, login/background items, package receipts, or company-branded leftovers on a Mac. Especially use it for Meituan/Sankuai, MOA, 文枢/wenshu, Kaspersky, Cisco AnyConnect, wsAssistant, EDR/MEDR, DNS proxy, Network Extension, Socket Filter, or similar enterprise tools.
- ▌
- ▌ Amap Jsapi Skill · ceilf6 bundle高德地图 JSAPI v2.0 (WebGL) 开发技能。涵盖地图生命周期管理、强制安全配置、3D 视图控制、覆盖物绘制及 LBS 服务集成。
- ▌ Frontend Design · ceilf6 bundleCreate distinctive, production-grade frontend interfaces with a clear visual direction while respecting project design specification constraints, existing design systems, and minimal-diff engineering boundaries. Use when building or restyling pages, landing screens, dashboards, marketing surfaces, or other frontend UI where visual quality materially affects the result.
- ▌ Skill Lifecycle · ceilf6 bundleCreate, evaluate, improve, and benchmark content skills using the local Skill Lab workflow. Use when adding a new skill, tuning an existing skill's trigger behavior, iterating on SKILL.md instructions, or deciding whether a candidate skill should replace the current version.
- ▌ Frontend Reviewer · ceilf6 bundleReview frontend code, UI changes, generated implementations, and pull requests with severity-based findings and checklist-driven analysis. Use when auditing React/TypeScript/CSS code, validating AI-generated frontend output, performing acceptance review before merge, or checking whether a frontend change is safe to ship.
- ▌ Requirement Interviewer · ceilf6 bundleGather missing product, UX, technical, and delivery constraints before planning or coding. Use when a request is underspecified, when several implementations are plausible, when frontend work needs explicit acceptance criteria, or when the agent must ask structured questions before acting.
- ▌ Gitnexus CLI · ceilf6Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki"
- ▌
- ▌
- ▌ Cgc Usage · ceilf6Use for dead code detection, cyclomatic complexity analysis, code graph visualization, or cross-validating GitNexus caller/callee results. Examples: 'find dead code', 'which functions are too complex', 'visualize the call graph', 'cross-check callers'
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Deepwiki Usage · ceilf6Use when researching external open-source projects, understanding unfamiliar libraries, or getting high-level architecture overviews of public repos. Examples: 'How does Next.js routing work?', 'Explain the architecture of langchain', 'What does this repo do?'
- ▌
- ▌ Lark Recall · ceilf6从飞书云文档知识库「字节vc」检索之前会话 / 别人沉淀过的经验，用于当前任务。当用户说「之前有没有类似经验」「查一下知识库」「飞书上有没有记录过」「拉一下之前的沉淀」「有没有踩过这个坑」，或即将排查一个陌生问题、想先看有没有前人经验时触发；要写转正/述职/答辩等汇报材料、需要评分标准与叙事素材时也触发。技能会用 docs 检索 + wiki 树定位，取回并面向当前任务提炼，标注来源 URL；可选把结论写进本地 memory 供本会话快速复用。只读，不改飞书。反向沉淀用 lark-sediment。
- ▌ Mr Comments · ceilf6 bundleMR 评论的统一拉取 / 水位 / 回复单点。当用户在 harness 需求会话里说「看看 MR 评论」「拉一下 MR 评论」「处理 MR 上的评论 / CR 意见」「CodeGuard 又评论了」，或任何要读某个 MR 上全部 CR 评论（Codebase 讨论线程 + Review 附言，含 BITS 详情页展示的同一份数据）、判定哪些是新评论、区分机器人与人工作者、给机器人评论回复的场景，必须经本 skill 的 scripts/mr-comments.sh，不直调 bytedcli codebase mr comment。人工评论只拉取呈现、不自动回复（机械层拒绝）；机器人评论按 harness-ceilf6 的 mr-comment-duty 纪律在当前会话处置。bot mrwatch 轮询出厂关闭，同样调它。
- ▌ Repo Evolver · ceilf6 bundle当需要自主循环审视仓库、发现改进点、创建 issue、编写方案、实现变更、提交 PR 并处理 repo-guard 审评反馈时使用。支持 meta-improvement：当 repo-guard 质量偏低时自动优化其 prompts 和 skills。
- ▌
- ▌ Lark Sediment · ceilf6把当前会话里值得长期保留、跨会话/跨人有用的经验（bug 根因与决定性证据、决策与取舍理由、可复用的排查/验证方法、踩坑与环境结论）沉淀进飞书云文档知识库「字节vc」。当用户说「沉淀」「沉淀一下」「沉淀到飞书/云文档」「记录到飞书」「归档到知识库」「同步到 lark 文档」，或一段排查/决策收尾时触发。技能会自动在知识库中定位最合适的位置、先去重再决定追加或新建子文档，自主选定后直接写入、事后汇报（不打断用户等确认）。凡本会话有实质工作节点（编码、排查、验证、CR、有结论的调研），B 线四问叙事语料（发现/解决/反思/总结，转正/述职取材）必产：harness 需求场景写入需求子文档，非 harness 会话写入台账；MR 合入、需求或排查收尾时也应主动触发本技能。不用于本地 memory / 仓库 docs（那是本地层），不用于纯代码提交。
- ▌ Report Writer · ceilf6 bundle可配置地自动生成并创建个人或团队工作日报/周报。用于写日报、生成日报、今日工作总结、代码提交日报、学城日报、日报创建、本周总结、周报、weekly report 等场景；按 references/config.yaml 中的用户画像、学城目录和群通知配置，日报从学城最近编辑、dev.sankuai.com commit/PR、ONES、TT、日历和用户显式输入中采集当天工作，周报默认基于一周日报聚合工作线和趋势，并通过 citadel 创建、授权或通知。
- ▌ Bytedcli Meego · ceilf6 bundle凡是 Meego 相关操作（条目关联/创建、排期回填、进度评论、节点/状态流转、映射配置），必须使用本 skill。机械层单点 scripts/meego.sh，配置按仓库键控，未绑定空间的仓库自动豁免；advance 转人工后的表单/状态处理步骤、直调 bytedcli 的查询与字段写入形状也在此登记。
- ▌ Harness Ceilf6 · ceilf6 bundle个人需求交付 harness：装载 harness-context 的需求上下文（harness-context 各动作完成后默认自动接续进入本技能），过计划门（轻量复述自动过门 / 实在不明确才转 superpowers 完整规划 / 续入跳过），过门后确保需求 wiki 子文档并把会话改名为需求短题，当前会话直接开发（TDD 红绿纪律），自动驱动评审员（traex gpt-5.6-sol）对抗式 CR 循环（送审→结构化判定→修复→再送审）直至通过或熔断，通过后全量 squash 成单个实质性 commit、变基到 base 远端最新、force-with-lease 推送、经 bytedcli-bits-mr 建 MR、沉淀到需求子文档，收尾汇总不以完成姿态给 MR（待人工 CR → 自测两节点 mark 齐后才产可交付版汇总）；支持无人值守模式（bot 场景由调用方声明）。人工 CR / 测试发现问题后可带全部历史续跑。当用户在装载上下文后要求「开始开发」「跑 harness」「继续 CR 循环」「续跑」时使用。前置：需求分支 + harness-context 已 init。
- ▌ Issue Reviewer · ceilf6 bundle当需要分诊 GitHub issue、评估 issue 质量、分析 bug report 或 feature request 的完整性、清晰度和可执行性，或给报告者提供结构化反馈时使用。
- ▌ Slardar Triage · ceilf6 bundle扫描 Slardar 近 24h 线上 JS 错误（vc_ai/vc_web/vc_pages），按 web 侧改动可能性排序并逐条详细呈现（Issue 链接、分布、代码点位、根因假设、要向 native 确认的问题），决策交给用户；只有用户说「派这条 <issue>，补充：<敲定的细节>」才建 Meego、经 traecli 起 omh、登记看板。当用户说「扫一下线上告警」「看看 Slardar」「挑一个告警看看」「派这条」「这条不修」「看看进度」时使用。
- ▌ Harness Context · ceilf6 bundle按 git 分支管理当前需求的本地上下文仓（<仓库根>/.harness-ceilf6/<分支>/，本地为真源、wiki 为沉淀）。动作：init 初始化并从需求 wiki 子文档导入种子；add 随时存入飞书 IM 群聊消息区间、飞书文档、Meego、MR 评论或自由文本；get 取出全部上下文；为组合式沉淀（如配合 /lark-sediment）供料并记台账。当用户要求初始化需求上下文、导入种子、「把这段消息/这个文档/这个 MR 的评论存进上下文」、取出/装载需求上下文、或沉淀需求经验时使用。init/add/get 完成后默认自动接续 harness-ceilf6 开始开发（用户明确「只存不跑」时豁免）。定位是入口与仓管：抓取由当前 agent 用 lark-cli / bytedcli 完成。
- ▌ Semgrep Scanner · ceilf6 bundle纯本地 Semgrep 静态代码分析 Skill。对指定仓库执行全量扫描，查找 Blocker（ERROR）和 Critical（WARNING）级别的安全与质量问题，直接在对话中输出报告。支持 TypeScript、JavaScript、Python、HTML、CSS 等语言。当用户提到静态扫描、代码分析、安全审计、Semgrep、查找 Blocker/Critical 问题、代码质量检查、全量扫描时使用。
- ▌ Progress Reporter · ceilf6 bundle读取 code-tape 项目 progress.md，结合项目时间规划、技术模块拆解和工作流程，将 GitHub ID 映射为同学姓名，生成带上下文的进展报告并发送到飞书群聊。
- ▌ Agent CLI Architect · ceilf6 bundleDesign, audit, and refactor the outer CLI entry layer for AI agent tools. Use when a request involves multi-mode CLI design, command dispatch, startup flags, interactive versus headless routing, SSH or remote entry flows, slash-command versus subcommand separation, plugin or skill command registration, command discovery, or cold-start optimization. Not for runtime state-tier design or terminal frame rendering.
- ▌ Harness Ceilf6 Lite · ceilf6harness-ceilf6 的收尾专用形态。代码已在需求分支上写好（直接 vibe 或 omh 产出）时，跳过计划门协商、TDD 开发与机审 CR 循环，只做建站与收尾：plan.md 四段凭本会话上下文直接写，随后短题、会话改名、需求 wiki 子文档、Meego 关联/创建+排期、登记看板线程、一次自检（typecheck+相关测试）、commit+squash、变基到 base 远端最新、force-with-lease push、经 bytedcli-bits-mr 建 MR+挂 WIP+meego 评论、自测矩阵子文档、沉淀、收尾汇总；里程碑一次钉到人工 CR，看板备注标 lite。支持续入：人工 CR / 自测打回、代码改完后再调一次即可。当用户说「代码已经写好了，按 harness 流程建 Meego、MR」「只建 Meego 和 MR，不走开发和机审」「vibe 完了走 lite」「omh 跑完了，建 MR 登记看板」「lite 收尾」时使用。前置：在需求分支上、代码已就位。人工节点之后的一切仍按 harness-ceilf6。
- ▌ Tui Render Optimizer · ceilf6 bundleAudit and optimize the terminal rendering layer for React-based TUI applications. Use when a request involves terminal flicker, slow frame rate, excessive redraws, high CPU during streaming output, Ink performance, React terminal render pipelines, HostConfig behavior, Yoga layout churn, dirty-flag rendering, screen diffing, or atomic terminal output. Not for browser-only rendering, general app-state design, or CLI entry architecture.
- ▌ Agent State Architect · ceilf6 bundleDesign and audit the runtime state layer for AI agent interfaces. Use when a request involves streaming state, unnecessary re-renders, useSyncExternalStore, external stores, React and non-React state sharing, side-effect centralization, command queues, file watchers, or tiering state by frequency and lifecycle. Not for CLI entry architecture or terminal renderer internals.
- ▌ Agent Memory Optimizer · ceilf6 bundleAudit, redesign, and incrementally improve memory systems in agent or coding-assistant projects. Use when Codex needs to inspect how a repo loads context over time, diagnose weak recall or memory bloat, separate durable memory from session memory, add runtime memory surfacing, improve turn-end memory extraction, or design Claude Code-style memory phases across startup preload, in-turn dynamic recall, post-turn persistence, and compaction-time session continuity.
- ▌ Repo Harness Bootstrap · ceilf6 bundleBootstrap an open-source repository Harness from zero to one. Use when Codex needs to design or build agent-ready engineering infrastructure for a new or immature open-source project: contributor docs, governance, issue/PR triage, SDD/TDD workflow, Git hooks, local and CI quality gates, GitNexus impact contracts, release/security automation, repo-guard/Codex/Copilot review loops, and completion verification.
- ▌ Group Skills Clis Stats · ceilf6 bundleUse when counting or ranking Friday/SkillHub skills and/or CLI tools created by members of a Daxiang group, especially requests involving group members, group skill statistics, CLI statistics, creator counts, skills per person, Friday skills, Friday CLI, or SkillHub contribution summaries.
- ▌ Report Writer Bytedance · ceilf6 bundleUse when Codex needs to create, update, or verify a ByteDance personal daily report in Feishu/Lark wiki for today or a specified date; triggers include 字节日报, 飞书日结, 今日总结, 今天活动记录, bytedance report, lark-cli, bytedcli, Codebase, Bits, Meego, Cloud Ticket, Oncall.
- ▌ Xuecheng Batch Exporter · ceilf6 bundleUse when exporting or migrating multiple KM/XueCheng/Citadel documents, especially parent directories, collabpage/page links, daily-report folders, or document lists that need local Markdown files for Notion, docs, archives, or downstream import. Trigger on 批量导出学城, 导出 KM 文档, 学城文章迁移, collabpage 批量, XueChengCopyPlugin, Notion migration from KM.
- ▌ Agent Security Architect · ceilf6 bundleDesign, audit, and refactor permission and safety control planes for AI agents and coding tools. Use when a request involves command or tool approval, permission pipelines, sandbox shortcuts, classifier-assisted adjudication, mode-based safety transitions, headless or remote approval, dangerous allow-rule stripping, or fail-closed operational guardrails. Not for general app auth, browser security, IAM, or unrelated infrastructure hardening.
- ▌ One On One Prep Bytedance · ceilf6 bundleUse when preparing or verifying Wang Jinghong's ByteDance weekly Mentor/Leader One-on-One material, including Week-N review, weekly optimization analysis, Friday 15:00 automation, all-source activity collection, Feishu Wiki publication, and private bot notification.
- ▌ Repo Guard Quality Evaluator · ceilf6 bundleUse when evaluating repo-guard review quality, validating code-reviewer or issue-reviewer prompt changes, comparing reviewer contract changes, or diagnosing degraded PR/Issue comments.
- ▌ Persona Review · ceilf6 bundleUse when the user asks for 三视角评审、persona review、HR/技术面试官/技术主管评审简历，或简历大改后需要重新冷读评审。