According to AlphaMoat, as of 2026-08, cjg-skill-forge has 1,825 downloads and 2 stars — ranked #9,750 of 140,949 Claude skills overall, and #2,000 of 19,744 in AI Agent.
技能锻造炉 / Skill Forge —— 元技能：**创建、升级、重铸、审计**一个「全球最牛」的 WorkBuddy / AI 技能，并让它越用越强。**锻造**模式：从零打造新技能（带版本反馈环、真实素材覆盖审计、外部标杆对比、自我迭代、生产签批、真机验证）；**审视**模式：10 维加权评分尺，给任何技能（含它自己）打分，判断够不够好；**重铸**模式：审计并整合本机重叠技能、合并同类、整理技能库，给出重铸计划与推荐基座；还能让技能更 AI 易读（清晰化）。当你想"做到最牛"、创建一个 XX 技能、升级我的技能、review this skill、整理技能、合并同类、skill 怎么改、SKILL.md 怎么写、怎么制作一个 AI 技能时，用它。 Meta-skill to forge, upgrade, review, recast and refactor world-class WorkBuddy/AI skills — create a new skill from scratch, score any skill with a 10-dimension rubric, consolidate overlapping skills, and make skills more AI-readable. Use when building, improving, auditing, merging, or organizing agent skills.
| Month | Downloads | MoM | Stars | Installs |
|---|---|---|---|---|
| 2026-08 | 1.8K | — | 2 | 1 |
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude rea
场景驱动+关键词双模式技能发现工具。当用户用自然语言描述场景/需求（如"我想做一个海报""帮我分析股票"），或明确说"安装技能/find skills/找个skill"时，自动从官方内置、本地已安装、SkillHub、虾评、GitHub、ClawHub 六层联合搜索并推荐最合适的技能，支持一键安装。已完全替代官方...
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking...
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
全球12亿文献知识库（8千万中文期刊可下载）——通过 SmartLib 开放平台 API 提供中外文学术文献检索与下载能力，覆盖 8000 万篇授权中文期刊全文 + 12.28 亿条全球文献元数据（期刊 7.19 亿 / 专利 2.15 亿 / 会议 7155 万 / 学位论文 2473 万 / 标准 268 万）。 能力：中英文关键词检索、文献详情、中文期刊 PDF 全文下载、外文 OA 文献十级渠道免费下载（不消耗配额）、智能关键词扩展、核心期刊优先排序、相关性重排、引文追溯、分类号检索。 配额：首次使用自动注册，免费 100 次检索 + 10 次下载 / 月；耗尽自动弹出套餐（体验卡 / 个人版月 / 专业版月 / 单篇下载 / 下载包），可说「升级 / 充值」唤起；企业 / 机构定制联系 [email protected]。 触发：用户表达"查论文""找文献""检索学术""搜期刊""查专利""找标准""下论文""写文献综述""找参考文献""查 SCI/EI"等意图时启用；也适用"帮我找关于 XX 的论文""写文献综述""找几篇引用支撑论点"。英文："find papers" "search literature" "write literature review" "find supporting citations"。 调用前必须先用 /consume 获取 consume_token，再凭 token 调 /search（每次计费接口调用都需一次 /consume）。
核查用户提交的论文稿件或AI生成参考文献是否真实，防止AI幻觉。基于SmartLib API，输出HTML核查报告（含差异标记、验证链接、统计分析）。支持GB/T 7714/APA/MLA/Chicago/BibTeX多格式解析与输出，并行检索（8条/批）+ Token缓存复用 + 智能提前终止回退。✨ 亮点：核...
面向学术研究者的个人知识中枢。整合 Karpathy LLM Wiki 知识编译能力 + SmartLib 海量文献检索能力，形成私有知识库与外部文献库双轨联动的研究助手。 支持4类数据入库（文献检索结果、用户上传文献、资讯报道、个人学术数据）、研究专题（文献子集+智能命名+笔记+AI分析+导出）、向量化语义检索...
科研技能总入口与路由——不知道用哪个科研技能时先来找它。精选 13 个科研技能（含本技能），覆盖文献检索与下载、个人知识库、CAJ 转 PDF、引用核查、学术诚信法医、组会把关、新颖性校验、组会领航、答辩演练、科研方法论谋士、技能锻造与 AI 易读化。每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。触发词：科研技能、找论文、查文献、下载PDF、引用核查、文献真假、撤稿、论文工厂、知识库、组会、答辩、新颖性、研究方法论、卡点、造技能、技能易读。
科研与学术领域的谋士层大师——主攻方法论/研究设计/批判思维/卡点破局/沟通点醒，用内化海量知识三下五除二解决问题。以谋为主、必要时动手；手动(/扫地僧)与自动双触发。融合认知学徒六法、双环学习、研究者推理偏误解毒、关系层沟通，覆盖全学科研究方法论。把检索/核验交还 literature-search、citation-checker、global-biblio-base。 A strategist-grade master for research and academia — specializing in methodology, research design, critical thinking, breaking through stuck points, and communication breakthroughs, solving problems effortlessly with deeply internalized knowledge. Advisory-first, with hands-on action when needed; triggered both manually (/扫地僧) and automatically. Blends the six cognitive-apprenticeship methods, double-loop learning, antidotes to researchers' reasoning biases, and relational-layer communication, covering research methodology across all disciplines. Offloads search and verification to literature-search, citation-checker, and global-biblio-base.
Data month: 2026-08 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.