技能目录
补足短板的 技能
按用途寻找能补足诊断短板的技能。复制安装命令即可立即应用。
技能说明以原文（英文/韩文）显示。
安装太麻烦？这一行就够了
把下面的命令粘贴进 Claude Code 一次，之后 只需说“帮我装技能” 即可完成。这是只收录经过验证技能的官方仓库。
/plugin marketplace add x77xdavid-prog/checkup-skills收录：prompt-master · korea-public-data · repo-shipper — 持续新增 · 在 GitHub 上查看
20 / 1326 款
- 评审与质量已验证仓库
advanced-evaluation
This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment.
上下文工程（Koylan）来源: muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/skills/advanced-evaluation ↗ · ⭐ 给作者加星
/plugin marketplace add muratcankoylan/agent-skills-for-context-engineering /plugin install context-engineering@context-engineering-marketplace许可证: MIT
- 评审与质量已验证仓库
evaluation
This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines.
上下文工程（Koylan）来源: muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/skills/evaluation ↗ · ⭐ 给作者加星
/plugin marketplace add muratcankoylan/agent-skills-for-context-engineering /plugin install context-engineering@context-engineering-marketplace许可证: MIT
- 编排与代理已验证仓库
harness-engineering
This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.
上下文工程（Koylan）来源: muratcankoylan/Agent-Skills-for-Context-Engineering/tree/main/skills/harness-engineering ↗ · ⭐ 给作者加星
/plugin marketplace add muratcankoylan/agent-skills-for-context-engineering /plugin install context-engineering@context-engineering-marketplace许可证: MIT
- 评审与质量已验证仓库
agent-self-evaluation
Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.
ECC 代理框架系统来源: affaan-m/ECC/tree/main/skills/agent-self-evaluation ↗ · ⭐ 给作者加星
/plugin marketplace add affaan-m/ECC /plugin install ecc@ecc许可证: MIT
- 自动化与调度已验证仓库
autoresearch-agent
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed,
模块化技能包来源: alirezarezvani/claude-skills ↗ · ⭐ 给作者加星
/plugin marketplace add alirezarezvani/claude-skills /plugin install autoresearch-agent@claude-code-skills许可证: MIT
- 营销与 SEO已验证仓库
creative-director
AI creative director with recursive self-assessment: 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER, Synectics), 3-axis evaluation calibrated against Cannes/D&AD/HumanKind, 5-phase process from brief to presentation.
来源: smixs/creative-director-skill ↗ · ⭐ 给作者加星
npx skills add https://github.com/smixs/creative-director-skill --skill creative-director许可证: MIT
- 金融与支付已验证仓库
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis, hedging strategies, load profiling, and sustainability reporting frameworks. Use when procuring energy, optimizing tariffs, managing demand charges, evaluating PPAs, or developing energy strategies.
ECC 代理框架系统来源: affaan-m/ECC/tree/main/skills/energy-procurement ↗ · ⭐ 给作者加星
/plugin marketplace add affaan-m/ECC /plugin install ecc@ecc许可证: MIT
- 测试与调试已验证仓库
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
ECC 代理框架系统来源: affaan-m/ECC/tree/main/skills/eval-harness ↗ · ⭐ 给作者加星
/plugin marketplace add affaan-m/ECC /plugin install ecc@ecc许可证: MIT
- 项目管理已验证仓库
gsd-eval-review
Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.
来源: gsd-build/get-shit-done ↗ · ⭐ 给作者加星
npx skills add https://github.com/gsd-build/get-shit-done --skill gsd-eval-review许可证: MIT
- 测试与调试已验证仓库
healthcare-eval-harness
Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures.
ECC 代理框架系统来源: affaan-m/ECC/tree/main/skills/healthcare-eval-harness ↗ · ⭐ 给作者加星
/plugin marketplace add affaan-m/ECC /plugin install ecc@ecc许可证: MIT
- 编排与代理已验证仓库
init
Create a new AgentHub collaboration session with task, agent count, and evaluation criteria. Use when the user runs /hub:init or asks to start a multi-agent competition on a task.
模块化技能包来源: alirezarezvani/claude-skills ↗ · ⭐ 给作者加星
/plugin marketplace add alirezarezvani/claude-skills /plugin install agenthub@claude-code-skills许可证: MIT
- 自动化与调度已验证仓库
mdr-745-specialist
EU MDR 2017/745 compliance specialist for medical device classification, technical documentation, clinical evidence, and post-market surveillance. Covers Annex VIII classification rules, Annex II/III technical files, Annex XIV clinical evaluation, Art. 86 PSUR schedules, and EUDAMED integration. Use
模块化技能包来源: alirezarezvani/claude-skills ↗ · ⭐ 给作者加星
/plugin marketplace add alirezarezvani/claude-skills /plugin install ra-qm-skills@claude-code-skills许可证: MIT
- 数据与分析已验证仓库
mle-workflow
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
ECC 代理框架系统来源: affaan-m/ECC/tree/main/skills/mle-workflow ↗ · ⭐ 给作者加星
/plugin marketplace add affaan-m/ECC /plugin install ecc@ecc许可证: MIT
- 测试与调试已验证仓库
prompt-engineer-toolkit
Turns marketing prompts into tested, versioned production assets: A/B prompt evaluation against structured test cases, immutable prompt version history with diffs, ready-to-use marketing prompt templates (ad copy, email campaigns, social posts, landing pages, SEO meta), and an LLM-governance playboo
模块化技能包来源: alirezarezvani/claude-skills ↗ · ⭐ 给作者加星
/plugin marketplace add alirezarezvani/claude-skills /plugin install marketing-skills@claude-code-skills许可证: MIT
- 数据与分析已验证仓库
risk-management-specialist
Medical device risk management specialist implementing ISO 14971 throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use when user mentions risk management, ISO 14971, risk analysis, FMEA, fault tree analysis, hazard identifi
模块化技能包来源: alirezarezvani/claude-skills ↗ · ⭐ 给作者加星
/plugin marketplace add alirezarezvani/claude-skills /plugin install ra-qm-skills@claude-code-skills许可证: MIT
- 评审与质量已验证仓库
scholar-evaluation
Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.
ECC 代理框架系统来源: affaan-m/ECC/tree/main/skills/scientific-thinking-scholar-evaluation ↗ · ⭐ 给作者加星
/plugin marketplace add affaan-m/ECC /plugin install ecc@ecc许可证: MIT
- 评审与质量已验证仓库
skill-stocktake
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.
ECC 代理框架系统来源: affaan-m/ECC/tree/main/skills/skill-stocktake ↗ · ⭐ 给作者加星
/plugin marketplace add affaan-m/ECC /plugin install ecc@ecc许可证: MIT
- 测试与调试已验证仓库
swiftui-debugging
Diagnose and fix SwiftUI rendering performance issues, including unnecessary body re-evaluations, slow or janky views, scrolling/list/grid stutters, view identity bugs, lost state, excessive `Self._printChanges()` output, `@Observable` versus `ObservableObject` observation scope, `AnyView` performan
设计技能（MengTo）npx skills add https://github.com/MengTo/Skills --skill swiftui-debugging许可证: MIT
- 安全已验证仓库
tech-stack-evaluator
Technology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, evaluating technology stacks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.
模块化技能包来源: alirezarezvani/claude-skills ↗ · ⭐ 给作者加星
/plugin marketplace add alirezarezvani/claude-skills /plugin install engineering-skills@claude-code-skills许可证: MIT
- 安全已验证仓库
ai-risk-management
Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency, accountability, third-party model risk, monitoring for drift, and AI incident response. Broader than prompt-injection (which is the security slice). Use when the user mentions 'AI risk,' 'AI governance,' 'NIST AI RMF,' 'AI compliance,' 'ML governance,' 'model risk management,' 'AI fairness,' 'AI bias,' 'algorithmic accountability,' 'AI Bill of Rights,' 'EU AI Act,' 'AI transparency,' 'model card,' 'AI red team,' 'AI safety,' 'responsible AI,' 'model drift,' 'concept drift,' 'AI monitoring,' 'AI incident,' or needs to assess or govern an AI / ML system.
来源: briiirussell/cybersecurity-skills ↗ · ⭐ 给作者加星
/plugin marketplace add briiirussell/cybersecurity-skills /plugin install cybersecurity-skills@cybersecurity-skills许可证: MIT
搜索词将匿名收集以改进技能推荐
在找这类功能吗？
按你想做的事来找技能。在上方搜索框输入用途即可看到推荐。
演示文稿·PPT
幻灯片生成、修改、读取一次搞定
pptx · pptx-generator · slides · image · make-pdf
报告·文档
从 Word 文档撰写到 PDF 转换、Wiki 整理
docx · make-pdf · writer-memory · wiki
PDF
PDF 读取、生成、转换
pdf · make-pdf · minimax-pdf
网页爬取·采集
从网上抓取数据并整理、检索
scrape · data-scraper-agent · insane-search · deep-research
制作代理·技能
打造并安装你自己的技能与代理
skill-create · skillify · install-agent · agent-sort
网站·落地页
落地页、主页从设计到诊断
frontend-design · ui-ux-pro-max · design-html · landing-report
博客·SEO
自动化搜索曝光与博客营销
seo-audit · ai-seo · naver-blog-marketing · programmatic-seo
代码检查·Bug
代码评审、安全检查、隐藏 Bug 排查
code-review · security-review · silent-failure-hunter · ai-slop-cleaner
自动化·重复工作
用钩子与 Git 联动自动化重复工作
hookify · github-ops
邮件·资讯
撰写冷邮件与资讯邮件
cold-email · emails
视频·YouTube
视频下载、编辑、制作
video · video-downloader · fal-video-edit
部署·服务器
安全地部署与配置服务器
ship · deployment-patterns · setup-deploy
深度研究
对主题深入挖掘的资料调查
deep-research · deep-dive · competitors