cnife
- 71 skills
- 0 followers
- 8 hours ago last updated
- ▌ E2e Happy Path · cnife bundleEnd-to-end happy-path test for skill-manager — declares the public fixture, syncs, and asserts the correct path. Run before PR.
- ▌
- ▌
- ▌ Zhihu Crawler · cnife bundle爬取知乎用户的所有文章和回答，生成 Markdown 和 PDF 报告。当用户提及知乎内容爬取、文章导出、回答备份、生成 PDF 报告、批量下载知乎内容时立即使用此技能
- ▌ Mrdang · cnife bundleMR Dang 价值选股打分助手 - 根据 MR Dang 投资体系对 A 股进行风险筛查和多维度打分。当用户提及 A 股选股、价值投资分析、股票打分、投资评级、股息率筛选、银行股分析、资源股评估时立即使用此技能。触发词：MR Dang 选股、MR Dang 打分、MR Dang 分析
- ▌ E2e Fixture · cnife bundleMinimal fixture skill for skill-manager end-to-end happy-path tests. Provides a publicly clonable SKILL.md for declare → sync → link.
- ▌ Bilingual HTML · cnife将 SKILL.md 转为中英对照的 HTML 参考页面，使用 Kami 设计风格。触发词：排版技能 / 生成 HTML 对照 / 做成可读页面 / turn skill into readable HTML.
- ▌
- ▌ Check Opencode Updates · cnife bundle检查 opencode 和 oh-my-openagent (omo) 的版本更新情况，有更新时自动获取并展示 release 说明。当用户提及版本检查、更新、版本对比、更新日志、release notes，或询问 opencode/omo 是否需要更新、有没有新版本时，立即使用此技能。即使用户只是随意提到"检查更新"或"版本"，也应触发此技能进行版本检查。
- ▌ Crawl Xueqiu My Timeline · cnife bundle爬取雪球首页关注的时间线，生成投资分析报告和 PDF。当用户提及雪球时间线、投资要闻、市场热点、大 V 观点、投资分析、生成 PDF 报告时立即使用此技能
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Worklog · cnife bundle从多个数据源收集用户活动轨迹 → 分析并区分工作与个人内容 → 排版为 PDF → 投递到邮箱。触发词：「发日报」「生成日报」「发我的今天」「今日汇总」「日记 PDF」「每天总结」「保存日志」「生成日报发邮件」。当你发现用户需要做每日回顾、日志汇总、生成日报 PDF 并发送时触发。
- ▌ Ast Grep · cnife bundleSearch and rewrite code by AST structure across 25 languages with ast-grep (sg). Use when the task is structural - find function calls shaped like X, rewrite console.log to logger.info, find all `as any`, migrate require() to import, find empty catch blocks, missing await, codemod a class hierarchy, scan project against YAML rules. Preferred over grep when the user mentions code SHAPE or needs deterministic refactoring across many files. Triggers: 'ast-grep', 'sg', 'ast grep', 'astgrep', 'find all functions that', 'find every call to', 'codemod', 'structural search', 'pattern match code', 'replace pattern across files', 'rename function everywhere', 'find usages of pattern', 'apply this transformation to all', 'migrate X to Y'.
- ▌ Treehouse · cnifeUse when a task needs a Git worktree or mentions Treehouse; follow Treehouse's pooled acquisition, lease, status, and return workflow.
- ▌ Git Master · cnife bundleMUST USE for ANY git operations. Atomic commits, rebase/squash, history search (blame, bisect, log -S). Use when the user mentions commit, rebase, squash, git blame, bisect, who wrote, when was X added, find the commit that, git history, or any git-related operations.
- ▌
- ▌ Chezmoi Sync · cnife bundleAutomate chezmoi dotfiles sync — fetch remote, pull changes, detect chezmoi-level changes (source vs home), smart re-add, commit, and push. Use whenever the user wants to sync dotfiles, says "同步", "chezmoi sync", "提交 dotfiles", "备份配置", wants to record home changes into the dotfiles repo, or is about to run chezmoi git commands manually.
- ▌ Prompt Craft · cnife bundle根据 OpenAI 提示词工程最佳实践，审查并优化已有 LLM 提示词。用户说“优化提示词”“改一下 prompt”“做提示词工程”“让模型输出更好”，或贴出一段提示词请求改进时，务必使用此技能。专注诊断和改写，不负责从零创建模板、生成 / 命令、写入文件或选择保存路径。
- ▌
- ▌ Search Router · cnife bundle搜索路由器：基于 opencli，按话题和场景把查询路由到合适的搜索源。当用户需要从网络获取信息时（无需用户提及 opencli）加载此技能。
- ▌ Obsidian Diary · cnife bundle将会话内容按主题聚合写入 Obsidian 工作日志或个人日记，并管理待办。当用户说「记录一下」「写日记」「更新待办」等要求记录时，或在会话末尾出现结构化结论/部署完成/调研成果时加载此技能，主动询问用户是否记录。
- ▌ Pi Skill Audit · cnife bundleAudit pi agent skills usage frequency, identify unused skills, and clean up safely. Queries pi session logs for skill invocation records (skill tags + read SKILL.md calls), cross-references against globally installed skills, categorizes by usage into high/medium/low/unused tiers, and drives cleanup via bunx skills remove. Use whenever the user mentions skill management, cleanup, or usage analysis — including "技能使用频率", "哪些技能用的多", "整理技能", "删掉不用的技能", "技能审计", "skill audit", "看看技能", "用哪些技能", "used skills", "unused skills", "清理", "clean up skills". Also use when the user has many installed skills and you suspect some are unused, or when reviewing what skills are worth keeping. This is the go-to skill for any pi skill management task. Not for Hermes agent skills — use audit-hermes-agent-skills instead.
- ▌ Skill Evaluator · cnife bundleEvaluate, compare, recommend, discover, and install AI agent skills. Use whenever the user wants to find, assess, choose, or install skills — even if they don't explicitly say "evaluate". Triggers: "评估/找/对比/安装/推荐 skill", "skill 安全", "哪个 skill 好用", "找个技能", "给 agent 装技能", "safe skill", "evaluate/compare/install skill", or any request involving skill discovery, security assessment, installation, or cross-agent compatibility.
- ▌ Models Dev Query · cnife查询 models.dev 开源 AI 模型数据库（GitHub 源码仓库 anomalyco/models.dev）中的模型规格（定价、上下文、能力、模态）与提供商 API 配置。
- ▌ Arch Wsl Cleanup · cnife bundleFree up disk space on Arch Linux WSL through layered cleanup: cache purge, orphan removal, package audit, and large file scanning. Use whenever the user mentions disk space, cleanup, storage, package review, or wants to shrink their WSL footprint — even if they just say "空间不够", "磁盘满了", "WSL 太大了", or "clean up my system". Prefer this skill over ad-hoc cleanup commands on Arch WSL.
- ▌
- ▌ Aihot Leaderboard · cnife bundle查询 AIHOT 大模型排行榜（aihot.virxact.com/leaderboard）实时数据：总榜、单模型各榜明细、来源榜单全量。手动触发，仅在用户明确要求查询 AIHOT 排行数据时使用；数据一律经 xd://browser 实时抓取，不以训练记忆作答。
- ▌ Cnife Skills Repo · cnifeGuide to managing and optimizing skills in the CNife/skills repository — quality gates, creation/publishing workflow, and the sub-agent verification loop for automated skill auditing and repair. Use when working with this repository, adding or modifying skills, running bulk operations across skills, or when the user mentions skill quality, verification, or repo maintenance.
- ▌ Optimize Agents Md · cnifeAGENTS.md 编写与优化指南，遵循渐进式披露原则。当用户创建、修改或重构 AGENTS.md，讨论 AI agent 指令结构、规则放置位置，或提到「渐进式披露」「模块化」「AGENTS.md 最佳实践」时，务必加载此 skill。即使用户只是说「帮我写个 AGENTS.md」「优化一下这个配置文件」「拆分一下规则」，也应该使用此 skill。
- ▌ Opencode Permission · cnife bundleManage OpenCode's permission rules in opencode.jsonc — add, remove, or list auto-approval rules for Bash commands and tool invocations so the agent stops asking for confirmation on every single command. Use whenever the user wants to auto-approve, deny, or require confirmation for a shell command, even if they don't mention "permission" or "opencode.jsonc" directly. Triggers on "允许 kubectl get *", "拒绝 rm -rf", "auto-approve npm run build", "总是执行 git status", "add permission rule", "list my permissions", "查看权限", "添加权限", "移除权限", "把 X 加到允许列表", "skip confirmation for", and similar — even if the user doesn't explicitly mention OpenCode's config.
- ▌ Qwen Code Permission · cnife bundleAutomate adding permission rules to Qwen Code's settings.json. Use whenever the user wants to allow, deny, or require confirmation for a command in Qwen Code. Trigger on phrases like "把 X 加到允许列表"、"添加到允许"、"允许 Bash(X)"、"deny 某命令"、"permission rule"、"auto-approve this command"、"skip confirmation for"、"always allow" — even if the user doesn't explicitly mention Qwen Code's settings.json. Also use when working with Qwen Code permission configuration or troubleshooting auto-approval rules.
- ▌
- ▌
- ▌ Audit Hermes Agent Skills · cnife bundleAudit installed Hermes Agent skills for usage frequency and generates an interactive XLSX with Chinese descriptions, dropdown decision columns, and color-coded recommendations. Supports apply mode: reads decisions from XLSX and executes cleanup (delete/disable/enable) after user confirmation, with automatic backup. Smart filtering: already-disabled skills are not re-suggested for cleanup. Uses hermes internal API for authoritative skill classification (builtin/hub/local/external). Use when the user asks about Hermes skill usage statistics, wants to clean up unused Hermes skills, needs to disable low-usage skills, or mentions "技能审计", "清理技能", "不用的技能", "哪些技能可以删", "技能热度", "技能使用频率", "audit hermes skills". This skill is specific to Hermes Agent — do not use for other agents. Make sure to load this skill whenever Hermes skill management, cleanup, or usage analysis is mentioned.
- ▌
- ▌ Fabric Best Practices · cnifefabric_exec 行为纠错层：fabric_exec 能跑通但行为不对时加载--结果没回到模型、 独立调用没坍缩并行、机制用在了错误的时间尺度。只管判断与避坑；签名 / 参数形状 报错见 fabric-exec，工作流选型见 fabric-guide。
- ▌ Herdr Subagent · cnife bundle用 herdr 驱动 pi 子代理的薄运行时。运行在 Herdr 内（HERDR_ENV=1）且要把工作委派给隔离子代理（上下文保护 / 并行 / 边界明确的执行）、或别的技能需要同时开多个隔离子代理时使用。
- ▌ Status · cnifeCheck Nowledge Mem server connectivity and configuration. Use when memory commands fail or the user asks about setup.
- ▌
- ▌ Extension E2e Test · cnife bundleE2E-test a pi extension by driving it through herdr — load it in isolation, send real messages, assert on the footer. Use when the user wants to test or verify an extension (测试扩展/验证插件/E2E/看看这个插件), debug one that is broken (扩展不工作/footer 不对/extension not showing), or compare models. For pi extension testing specifically; general herdr control belongs to the herdr skill.
- ▌ Search Pi Extensions · cnife bundle按需求从 npm pi-package 生态检索符合的 Pi Agent 扩展/技能/主题/prompt 包，采集 npm 元数据与 GitHub 信号，质量评估后整理成表格。与 pi-trending 互补（后者做热度发现）。
- ▌ Save Thread · cnifeCreate a structured handoff summary when the user asks for a checkpoint. PI transcript sync is automatic; this skill adds a concise continuation record.
- ▌ Plugin Presentation Card · cnife为 Pi 扩展（插件）制作一页展示卡片（HTML），用 kami one-pager 模板。流程：读代码理解插件 → 读文章找定位 → 讨论布局 → 用 kami 出卡 → 反复调内容。必须使用此技能的场景：用户说「做一张展示卡」「做个介绍页」「出一页卡片」「写一个插件宣传页」「做个演示卡」「插件展示」「presentation card」，或完成了某个插件后需要一张介绍卡片。也适用于非 Pi 插件的工具/库/项目，只要用户想做一页介绍。
- ▌ Search Memory · cnifeSearch your knowledge base when past decisions, preferences, or procedures would improve the response. Covers memories from every AI tool you use.
- ▌ Distill Memory · cnifeSave decisions, insights, preferences, and procedures as durable memories. Fires when the conversation produces knowledge worth keeping across sessions.
- ▌
- ▌
- ▌
- ▌ Agent Template · cnifeRoute subtasks to preconfigured pi agents (explorer/reviewer/worker). Use when delegating instead of hand-specifying agents.run params.
- ▌
- ▌
- ▌
- ▌ Read Working Memory · cnifeLoad today's Working Memory briefing at session start. Shows your current focus areas, priorities, and recent knowledge changes across all AI tools.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌