jamframe-skills
Agent skills for JamFrame: render, design and post templates from Claude, ChatGPT, Cursor and other AI agents
The most recently added listings, newest first. To search them, choose “Newest on findsafeskills” in search.
Agent skills for JamFrame: render, design and post templates from Claude, ChatGPT, Cursor and other AI agents
Agent skills for designed, not generated, frontends. UI/UX, design systems and motion for Claude Code and Codex.
Meta-prompting — a skill for shaping context through self-generated prompts.
Watches a video properly (an X, YouTube, TikTok or Instagram link, or a local file) and works out its edit, words and music. Use when the user asks to watch, analyse, break down or learn from a video, a set of videos or a whole account. Gives the shot list, a frame per shot, on-screen text, the song (Shazam), tempo and beats against the cuts, loudness, silences and a voiceover transcript, and has a batch runner for many videos. Works on macOS, Windows and Linux, including sandboxed Linux environments with a lighter kit.
Interview skill for ChatGPT, Claude and Antigravity that writes build prompts for scenes, games and videos made only of code.
Universal UI/UX Design System, Multi-Theme, Modular Color Accent, Project-Adaptive & Live Playground Architecture Skill. Enforces anti-slop aesthetic standards, anti-rigid project adaptation (5 project archetypes & 4 visual dials), zero-neon and anti-heavy shadow discipline, visual-first density, dual-layer theming (5 Canvas Themes + 8 Calibrated Color Themes), headless/unstyled component flexibility, live interactive showcase, multi-framework integration (React, Next.js, Tailwind v3/v4, Vue, Svelte, Ink CLI), fluid cross-platform responsiveness (Web, Windows, macOS, Linux, Android, iOS, Foldables, Smart TV), and integration with curated design references (jiro.build, designspells.com, styles.refero.design, supahero.io, mobbin.com).
Fix failing tests without weakening them — run the suite once, rerun only the failing files to separate flaky from real failures, classify each real failure as source bug or wrong test, then propose minimal diffs for approval. Use when asked to fix failing tests or make the suite green.
A software company of AI agents: a boss that decides, designers who study real products, engineers who map the codebase first, and QA, security and platform who sign off on the whole product.
Process management & VitePress documentation workflow for large projects with coding agents.
Calculate China expat IIT net salary, BIA tax-free allowances, annual bonus & GBA 15% rebates.
Use when a project needs comprehensive repository documentation, an illustrated user and developer handoff, a demo walkthrough, or an update to existing Amanuensis documentation. Applies to apps, websites, workflows, and other projects with inspectable files.
"Use when consulting modern web platform guidance for HTML, CSS, JavaScript, accessibility, forms, browser APIs, performance, security, PWA installation, Chrome extensions or browser compatibility, including authored guidance, published editions and behavior expectations; or when writing site metadata (head tags, Open Graph, X cards, Apple link previews, JSON-LD rich results, hreflang, robots rules, AI crawlers and usage preferences, sitemaps, IndexNow, feeds, icons, image rights and C2PA, app links, llms.txt, ads.txt, security.txt and well-known files), titles, descriptions and share images, or previewing and auditing link cards and metadata before deployment."
Agent skill: clean up dead code, duplicated implementations and stale instructions after edits, context compaction or model upgrades. Read-only scanner included.
Agent skill for practical judgment: time and place awareness, reading the user, intent, right-sized effort and clear reporting.
Find race conditions in your SQL transactions: runs every interleaving on a real Postgres at every isolation level and shows the one that corrupts your data.
Obsidian 官方 Agent Skills 的 DeepSeek Harness 版:轻量、仅打包,带上游版本检查与整树更新。
앱인토스(Apps in Toss) 검수 반려 사례집 + 공식 점검이 못 잡는 항목 + 의존성 0개 번들 스캐너 + AI 에이전트 스킬 · Catch Apps in Toss review rejections before you submit
A collection of reusable agent skills for Google Antigravity / Gemini-based coding agents focusing on correctness, data integrity, and safety for software and data-platform work
A pre-push review gauntlet for coding agents: correctness, logic, security, claims and infrastructure passes, then fix and re-review until clean.
Sync AI agent skills, rules and MCP configs across Claude Code, Codex, Gemini CLI, Cursor, VS Code Copilot and DSH from one local library, with hash-based conflict detection, backups and security review. Use when the user wants to install a skill or plugin from GitHub, keep skills in sync between AI tools, import what a tool already has, compare or repair drifted copies, resolve a two-way sync conflict, or back up / restore AI resources. Triggers: "把这个 GitHub 技能装到 Claude Code 和 Codex", "把六个工具新增的 Skill 导入中央库", "同步/备份/恢复 AI 扩展". Do not use it for editing application code that merely mentions MCP or skills.
Protects freelancers and agencies from scope creep. It reads the actual agreement (contract, proposal, quote, SOW, email or chat where the job was agreed), turns it into a clear scope baseline, checks each new client request against it (included / grey area / extra, quoting the exact line), prices the extra work at the user's own rate, drafts a polite change-request reply, and keeps a running change log per client showing approved extras, pending quotes and work given away for free. It also checks a proposal for scope loopholes before it is sent. Use this whenever a freelancer, consultant, designer, developer, video editor, writer, marketer, photographer, UGC creator or agency mentions a client asking for "just one more" thing, extra revisions, "small tweaks", work that wasn't agreed, how to charge for changes, a change order, revision limits, or wants a proposal or contract checked, even if they never say "scope creep".
Agent skill and script that audit Python dependencies: outdated pins and Python-version compatibility
周边电子原稿还原 · Restore flat artwork from photocard and Instax photos, with deterministic geometry correction.
Agent Skill: Laravel tests from evidence. Traces request flow, probes edge cases, records CURRENT vs RECOMMENDED behavior
Let Claude Code and OpenAI Codex hand work to each other, both ways, and watch them talk live. Cross-model review and delegation with one command.
SEO-skills for AI-agenter koblet til Årvåken
Skill-Induced Privilege Escalate: Because a standard that literally instructs autonomous agents to fetch an external authorization block where the server specifies a **skill** is retarded. The agent framework ingests this skill into its **system/scaffolding tier**—a context tier that the input supervisor does not police with proper scrutiny
Agent skills, one folder each. First: timeplan, which turns output tokens and tool calls into wall-clock time from real transcripts.
A personal collection of reusable skills for coding agents.
Scientific, token-frugal agent harness & portable skills for Claude Code, Codex CLI, Cursor, Gemini CLI, and Antigravity.
Persistent simulated emotion, social memory, and private prompt cues for AI agents. One Python engine with Claude Code, Codex, and Gemini CLI hooks.
跨 AI 工具的「先厘清,再动手」需求采访 Skill:先大白话复述需求,按需每次只问一个问题逐问采访,再次复述并等确认后再改代码。
"元简 — 本地求职者简历诊断、分析、修改与成品导出技能:分析简历结构、经历证据、量化指标、岗位匹配和风险,向用户追问缺失事实,给出逐条合理化修改建议,并把确认后的内容导出为 DOCX/PDF。触发:简历诊断、简历分析、改简历、简历追问、JD匹配、导出Word/PDF。边界:不编造经历,不承诺ATS、面试或Offer结果;不自动投递;不处理复杂设计作品集排版;默认本地处理且不联网。"
Free terminal AI chat & coding agent powered by Gemini — zero API keys, zero cookies, zero dependencies. Pure Python 3.9+ for Linux, Windows & Termux.
Ecosistema abierto de Agent Skills y Orquestación Autónoma aplicable a cualquier grado académico para diseñar, producir y auditar cursos completos.
Adobe Acrobat Pro - PDF editing and document management suite for text editing, form creation and digital signatures on Windows 10/11
通用零售数据分析技能:把任何来源(CSV / JSON / 自有 BI API)的零售数据, 套用到经过实战沉淀的 9 类分析方法上,输出带诊断结论与行动建议的 Markdown 报告。 覆盖:目标追踪(红绿灯预警)、环比与量价归因、历史基线(四分位异常检测)、 多主体横评 Benchmark、矩阵象限、能力雷达、客户漏斗转化、帕累托结构与 波动归因(关键人识别)、商品画像、订单结构、四维度综合业绩评价。 触发条件(满足任一即使用本技能): - 用户询问业绩/目标/达成率(如"本月目标完成得怎么样""哪些店要报警") - 用户分析变化与原因(如"销售为什么下滑""客流转化率下降原因") - 用户需要对比(如"和别的店比怎么样""导购业绩排名""和历史同期比") - 用户分析结构(如"导购团队结构""谁拖累了业绩""商品品类分布") - 用户需要综合诊断(如"帮我全面评价一下这家门店") - 用户提供零售销售/客流/导购/SKU/客户数据并希望得到分析结论 适用对象:门店、电商、品牌零售的运营/督导/数据分析角色; 分析主体可为门店、导购、商品 SKU、区域等任意业务单元。
Писать быстрые надёжные тесты по риску изменения. При ревью и переработке тестов находить пропущенные регрессии, ложные падения, дубли, лишние моки и дорогие прогоны. Применять при просьбах написать или улучшить тесты, проверить сложный сценарий, ускорить набор или убрать ИИ-слоп из тестирования.
Agent Skill (SKILL.md) that keeps AI agents safe around crypto exchange API keys: no secrets in chat/commands, withdrawals off, fix guides for Binance/Bybit/OKX/Bitget errors.
Rewrite a rough, vague or over-stuffed request into a prompt the current model or agent can act on, and explain a jargon-heavy agent reply in plain words. Use when the user asks to improve, critique or rewrite a prompt, sends a draft before pasting it into another AI, or says "nutshell this" about a reply.
Official Selkay Content Moderation Agent Skill for AI coding agents (Claude Code, Cursor, Codex, OpenCode, Antigravity)
Pre-release repository audit and cold-start verification from a stranger's first-visit perspective (仓库发布前外部视角体检与冷启动验收). Default Light mode (read-only, no installs or large downloads): one-sentence verdict, staged delivery boundaries (bundled vs user-supplied vs failure mode), external exposure audit across working tree, publishable Git history, archives, metadata, and third-party licenses, plus safe public-claims guardrails. Explicit Deep mode (only when user asks to run/install): isolated cold-start execution on the actual release artifact. Not for unit tests, code review, pentesting, or legal sign-off.
Anti-AI-slop rules and audit for any UI work. Use before and after building or changing anything visual (web pages, apps, dashboards, artifacts, slides, emails, video graphics, brand work), and whenever asked to audit, review, "de-slop", "unslop" or check a design or project for AI slop or a generic, templated, "vibe-coded" look. Gives a house style, a subtract-first clean-up pass, and a scanner that lists slop patterns by file and line. Reads your own brand from references/brand.md when that file exists. When an installed design skill conflicts with it, this one wins.
Standalone agent skills for iteration, repo onboarding, research, and clear explanations.
26 production-grade, modular Agent Skills for Google Antigravity, Claude Code, Cursor & AI coding agents. Enterprise SecOps, Proxmox VE, OPNsense, Cloudflare, Web Engineering & GameDev. Zero-dependency CLI playbooks. (EN / DE / TR)
Shared skills for coding agents: the software-development workflow (plan, build, review, UI) for Claude Code, Codex and Antigravity.
成都大衍千机科技 · 66枚企业AI实战开源技能库 (腾讯SkillHub蓝V认证) | 66 Battle-Tested Enterprise AI Agent Skills (SKILL.md) — dayanqianji.com
35 个实战迭代出来的 agent 技能:通用方法、图片素材、微信小程序、桌面应用、本地网页工具、离线翻译。每个都写明什么时候不该用。
Routing-aware metadata refinement for Claude Code / Agent Skills (unofficial Skill++ implementation)
Turn a real project into a bilingual GitHub homepage: README in English and Chinese, a cover made from the project itself, real screenshots, every claim checked against the code. A Claude skill.