Skills

Each entry shows what its maintainer published and when the project was last touched. Where a repository has been deleted or archived, that is stated on the entry instead of being quietly left out.

Worked on in the last 90 days (57)

Someone pushed a commit recently. This is the shortlist worth trying first.

nexu-io-html-anything-deck-simple — last commit 2026-07-28
通用 horizontal-swipe HTML deck, 不要 magazine 调
nexu-io-html-anything-deck-swiss-international — last commit 2026-07-28
16 列网格 + 单一饱和 accent + 22 个锁死版面 (Klein Blue / Lemon / Mint / Safety Orange)
nexu-io-html-anything-deck-tech-sharing — last commit 2026-07-28
GitHub-dark + JetBrains Mono + 终端代码块, 含 agenda + Q&A
nexu-io-html-anything-deck-xhs-pastel — last commit 2026-07-28
奶油底 + 柔光 blob + 马卡龙圆角卡片 + Playfair 斜体序号
nexu-io-html-anything-deck-xhs-post — last commit 2026-07-28
9 页 3:4 竖版图文, 暖 pastel + 虚线 sticker 卡片
nexu-io-html-anything-deck-xhs-white — last commit 2026-07-28
纯白 + 顶部彩虹 bar + 渐变文字 + 马卡龙软卡片 + 黑底 pill
moonlight-lupin-agent-skills-claude-plugin-converter — last commit 2026-07-27
Convert Claude Code plugins into self-contained Hermes plugins — discovery analysis then full conversion
moonlight-lupin-agent-skills-decision-log — last commit 2026-07-27
ADR-style decision journal for agents and teams. Create numbered decision records, track superseding chains, schedule periodic reviews, and…
moonlight-lupin-agent-skills-document-converter — last commit 2026-07-27
Convert between document formats: Markdown↔HTML, CSV↔JSON, YAML↔TOML, JSON↔YAML, CSV↔Markdown table, HTML→plain text, JSON→CSV (flattening…
moonlight-lupin-agent-skills-fact-checker — last commit 2026-07-27
Targeted claim verification pipeline. Given a factual assertion, search multiple independent sources, cross-check for agreement or contradi…
moonlight-lupin-agent-skills-file-organizer — last commit 2026-07-27
Use when the user wants to organize, tidy, or restructure a messy directory (Downloads, Desktop, documents folder). LLM-powered file organi…
moonlight-lupin-agent-skills-library-rag — last commit 2026-07-27
Semantic search over a personal library using bge-m3 embeddings + sqlite-vec. Index books, documents, any text corpus; query by meaning. In…
moonlight-lupin-agent-skills-log-analyzer — last commit 2026-07-27
Parse agent log files to identify error patterns, rate limit hits, timeout clusters, tool failures, and component-level error counts. Produ…
moonlight-lupin-agent-skills-media-analyzer — last commit 2026-07-27
Technique-focused media analysis. Detects rhetorical tools (loaded language, cherry-picking, source selection bias, framing, omission, emot…
moonlight-lupin-agent-skills-news-monitoring — last commit 2026-07-27
Recurring topic/news monitoring with web search, multi-language sources, digest formatting, and automated delivery via Hermes cron jobs. Co…
moonlight-lupin-agent-skills-scheduled-summary — last commit 2026-07-27
Cron-driven cross-session digest. Aggregates session activity, cron job outputs, memory changes, and tool usage stats into a compact summar…
moonlight-lupin-agent-skills-skill-maintainer — last commit 2026-07-27
Track upstream drift and sync adapted skill libraries
moonlight-lupin-agent-skills-source-tracker — last commit 2026-07-27
Persistent citation database for multi-session research. Add URLs as they're cited, dedup variants, tag by topic, check link health, and ex…
moonlight-lupin-agent-skills-travel-itinerary — last commit 2026-07-27
Create, update, sanitize, route, and export structured business-trip itineraries from booking confirmations, emails, tickets, PDFs, screens…
moonlight-lupin-agent-skills-website-scraping — last commit 2026-07-27
Generic playbook for extracting structured data from any website — hotel prices, flight fares, e-commerce listings, real estate, jobs, comp…
drafael-coding-harness-brainstorm — last commit 2026-07-27
Use before any creative work or significant changes. Activates on "brainstorm", "let's brainstorm", "deep analysis", "analyze this feature"…
drafael-coding-harness-clarify — last commit 2026-07-27
This skill should be used when user appears confused, frustrated, or shows misalignment between expectations and reality. Triggers on phras…
drafael-coding-harness-code-review — last commit 2026-07-27
Perform a focused, evidence-based code review covering correctness, regressions, security, performance, architecture, and testing without i…
drafael-coding-harness-debug-error — last commit 2026-07-27
Systematically debug and fix errors using structured investigation. Use when the user asks to "debug", "fix an error", "troubleshoot", "inv…
drafael-coding-harness-explain-code — last commit 2026-07-27
Analyze and explain code functionality with structured breakdowns. Use when the user asks to "explain this code", "how does this work", "wh…
drafael-coding-harness-humanizer — last commit 2026-07-27
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based o…
drafael-coding-harness-java-coder — last commit 2026-07-27
Mandatory for every task in a Java codebase, including planning, implementation, debugging, refactoring, review, testing, Maven or Gradle b…
drafael-coding-harness-owasp-security — last commit 2026-07-27
Use when reviewing code for security vulnerabilities, implementing authentication/authorization, handling user input, or discussing web app…
drafael-coding-harness-pdf — last commit 2026-07-27
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining…
drafael-coding-harness-refactor-code — last commit 2026-07-27
Simplify and improve code through narrow, behavior-preserving, test-backed changes without speculative architecture or scope growth. Use wh…
drafael-coding-harness-skill-hunter — last commit 2026-07-27
Use when the user wants to find NEW external skills for a project, build a skill stack from external registries, or compare external option…
drafael-coding-harness-test-coverage — last commit 2026-07-27
Analyze and improve test coverage. Use when reviewing coverage gaps, writing missing tests, setting up coverage tooling, or improving branc…
drafael-coding-harness-typescript-coder — last commit 2026-07-27
Mandatory for every task in a TypeScript or mixed TypeScript codebase, including planning, implementation, debugging, refactoring, review,…
drafael-coding-harness-write-tests — last commit 2026-07-27
Write unit, integration, component, and end-to-end tests for code. Use when the user asks to "write tests", "add tests", "add test coverage…
drafael-coding-harness-wrong — last commit 2026-07-27
Reset and re-evaluate when current approach isn't working. Use when user says "wrong", "this isn't working", "wrong approach", "start over"…
feiskyer-claude-code-settings-brainstorming — last commit 2026-07-27
Explore user intent, requirements, and design options through collaborative dialogue before implementation. Use before building new feature…
feiskyer-claude-code-settings-codex-skill — last commit 2026-07-27
Leverage OpenAI Codex/GPT models for autonomous code implementation, code review, and plan review. Triggers: "codex", "use gpt", "gpt-5", "…
feiskyer-claude-code-settings-deep-research — last commit 2026-07-27
Multi-agent research orchestration: split a research goal into parallel sub-goals, run each via headless `claude -p` subprocesses, aggregat…
feiskyer-claude-code-settings-github-fix-issue — last commit 2026-07-27
Fix GitHub issues end-to-end — analysis, branch creation, implementation, testing, and PR submission. Use whenever the user mentions fixing…
feiskyer-claude-code-settings-github-review-pr — last commit 2026-07-27
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants…
feiskyer-claude-code-settings-gpt-image-skill — last commit 2026-07-27
Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Use ONLY when the user explicitly names OpenAI or GPT a…
feiskyer-claude-code-settings-grill-me — last commit 2026-07-27
针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。
feiskyer-claude-code-settings-handoff — last commit 2026-07-27
将当前对话压缩为交接文档（handoff document / session handoff brief），供下一个 agent 接续工作。手动调用 /handoff。
feiskyer-claude-code-settings-nanobanana-skill — last commit 2026-07-27
Generate or edit images via Google Gemini (nanobanana). This is the DEFAULT image skill — use whenever the user asks to generate, create, o…
feiskyer-claude-code-settings-skill-creator — last commit 2026-07-27
Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger qualit…
feiskyer-claude-code-settings-translate — last commit 2026-07-27
Translate English or Japanese tech articles into natural, fluent Chinese. Use whenever the user asks for Chinese translation, says "transla…
feiskyer-claude-code-settings-youtube-transcribe-skill — last commit 2026-07-27
Extract subtitles/transcripts from YouTube videos. Triggers: "youtube transcript", "extract subtitles", "video captions", "视频字幕", "字幕提取", "…
jeecgboot-skills-jeecg-bpmn — last commit 2026-07-27
Use when user asks to create/generate/edit/modify a BPM workflow, design a Flowable BPMN process, or says "创建流程", "生成流程", "新建流程", "设计流程", "…
jeecgboot-skills-jeecg-codegen — last commit 2026-07-27
Use when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模…
jeecgboot-skills-jeecg-codegen-new — last commit 2026-07-27
Use when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模…
jeecgboot-skills-jeecg-dev — last commit 2026-07-27
JeecgBoot 开发规范（仅手动触发）。⚠️ 本技能只在用户显式输入 /jeecg-dev 命令时使用，禁止自动触发——编写/修改 JeecgBoot 代码、应用 GitHub PR/issue 改动、修复 bug、新增功能、重构、代码生成等场景都不要自动调用本技能。内容涵…
jeecgboot-skills-jeecg-onlchart — last commit 2026-07-27
Use when user asks to create/edit Online graph charts, data visualization, or says "创建图表", "生成图表", "新建图表", "做一个图表", "online图表", "数据图表", "柱状…
jeecgboot-skills-jeecg-onlreport — last commit 2026-07-27
Use when user asks to create/edit/query Online reports, SQL reports, data reports, or says "创建报表", "生成报表", "新建报表", "查询报表", "online报表", "SQL…
jeecgboot-skills-jeecg-system — last commit 2026-07-27
JeecgBoot 系统主数据查询与管理。Use when user asks to query/create/manage system master data, or says "查询角色", "查询用户", "查询部门", "查询字典", "创建字典", "创建角色",…
jeecgboot-skills-jeecg-uniapp-codegen — last commit 2026-07-27
JeecgBoot UniApp3 移动端 CRUD 代码生成器。Use when user asks to generate UniApp3/mobile/APP CRUD pages, create mobile list/form pages, or says '生成移动…
jeecgboot-skills-jimubi-bigscreen — last commit 2026-07-27
Use when user asks to create/design a big screen (大屏), full-screen data visualization, or says "创建大屏", "生成大屏", "新建大屏", "设计大屏", "做一个大屏", "BI…
jeecgboot-skills-jimureport — last commit 2026-07-27
积木报表生成器 — 自然语言描述报表需求或提供截图，自动生成积木报表（支持数据报表、打印报表、分组报表、循环报表、数据填报等全类型）。Use when user says "积木报表", "jmreport", "Excel报表", "数据填报", "可视化报表", "打印报表…

Repository gone or archived (3)

The registry still lists these, but the linked repository returns 404 or the owner archived it. Shown so you do not spend time discovering that yourself.

rikocr8orh8-compliance-skills-previews-aeo-site-audit — archived by owner, last commit 2026-07-26
You can be found by an AI assistant and still be unusable to it.
rikocr8orh8-compliance-skills-previews-ai-agent-governance-audit — archived by owner, last commit 2026-07-26
Can you stop your agent right now, and prove what it did last Tuesday? Generic AI governance checklists audit models; agents are different…
rikocr8orh8-compliance-skills-previews-ai-content-fact-audit — archived by owner, last commit 2026-07-26
'The AI wrote it with citations, so it's sourced' is how a fabricated stat ships.

Page 30 of 50

How this page is ordered

Entries are grouped by whether anyone is still working on them, using the date of the most recent push to the repository. They are not ordered by stars, because a star is a bookmark somebody left once and never took back.

Where we have not checked an entry yet, it says so rather than being mixed in with the verified ones.