Linting
Code linting and formatting
python-style
by janjaszczak
Enforce consistent Python typing (type hints + return types), concise Google-style docstrings, PEP 8/Black formatting, and unit tests when creating or editing Python code. Use when working on .py files, Python APIs, refactors, or bug fixes where maintainability and correctness matter.
custom-skill
by whddnjs
Use this skill when the user asks about Git conventions, commit messages, or branch naming. Trigger when the user: - Asks about commit message format, convention, or style (커밋 메시지, 커밋 컨벤션, commit convention) - Wants to commit code and needs guidance on the message (커밋, commit, git commit) - Asks about commit types like feat, fix, refactor, chore, docs, test, style, perf - Asks how to split or separate commits (커밋 분리, atomic commit) - Asks about branch naming or branch strategy (브랜치 전략, 브랜치 이름, branch naming) - Asks about Git workflow rules or best practices (Git 작업 규칙, Git 가이드) Do NOT trigger for general Git usage questions unrelated to conventions (e.g., "how to rebase", "how to resolve merge conflicts").
ad-hook-angle-discovery
by tonyflo79
Strategic derivation and creative generation of advertising hooks and angles for paid ad campaigns. Use after ad intelligence (A01) is complete and you need hook and angle candidates for ad creative. Generates 50+ hooks across 8+ hook types and 10+ angles using the 32-type hook taxonomy. Angles are strategic (the frame through which the audience sees the message); hooks are creative expressions of those angles. Volume is the game — more hooks mean more testable creative. Produces the HOOK-ANGLE-MATRIX.md with all candidates scored and categorized. Trigger when users mention ad hooks, advertising angles, hook generation, creative angles, or brainstorming ad openers. Requires A01 AD-INTELLIGENCE-HANDOFF.md.
Brand Guardian
by anorbert-cmyk
Ensures brand consistency across UI, marketing, and communications without compromising usability.
changelog-generator
by nlyrthiia
Generate changelogs from git commit history in multiple formats (Keep a Changelog, Conventional Changelog, grouped by date). Use when the user asks to 'generate changelog', 'create release notes', 'summarize commits', 'what changed since last release', or needs a CHANGELOG.md file created or updated. Triggers on any changelog, release notes, or commit summary task.
docx-design-agent
by tivojn
"Expert Word document design agent for macOS using python-docx and AppleScript. Creates and edits stunning, professional documents with premium design quality. Use when: (1) Creating new Word documents from scratch with python-docx, (2) Editing or redesigning existing .docx files, (3) Building documents with custom design (cover pages, styled tables, callout cards, pull quotes, sidebars, KPI panels), (4) Live editing documents via AppleScript IPC (text, fonts, paragraphs, find/replace, fields, TOC), (5) Updating fields, TOC, or exporting to PDF via AppleScript on macOS, (6) Generating AI images for document covers and content, (7) Any task requiring python-docx code generation with design best practices."
evaluating-heuristics
by Foundation-for-Puerto-Rico
Evaluates paragraphs extracted from DOCX documents against FPR
gingiris-aso-growth
by fatcow11111
🇺🇸 ASO & App Cold Start Growth Playbook — Complete guide from App Store Optimization to UGC operations, multi-platform content strategy, and AI-powered scaling. 🇨🇳 ASO 增长与 App 冷启动权威指南 — 从应用商店优化到 UGC 运营、多平台内容策略、AI 矩阵号的完整实操手册。 🇯🇵 ASO＆アプリコールドスタート成長ガイド — App Store最適化からUGC運営、マルチプラットフォーム戦略、AIマトリックスまで。 🇰🇷 ASO 및 앱 콜드 스타트 성장 플레이북 — 앱스토어 최적화부터 UGC 운영, 멀티플랫폼 전략, AI 매트릭스까지. Triggers: "ASO" "App Store Optimization" "app cold start" "app launch" "UGC creator" "TikTok marketing" "app growth" "应用商店优化" "App冷启动" "UGC运营"
python-developer
by wizact
Python development best practices - type safety, async patterns, testing, and Pythonic code for production-ready applications
neta-travel
by talesofai
让 Neta 角色踏上随机冒险之旅 —— 每次一站，看图、决定要不要继续，集满 5 站可生成旅行图鉴。 主动触发时机（无需用户明确要求）： - 刚完成 adopt 领养角色后，主动提议让 TA 去旅行 - 对话中出现：旅行 / travel / 出发 / 去探索 / 随机玩玩 / 带我去 - 用户说"再来一些"、"继续"且上下文是旅行图片时 前置条件： 已有 SOUL.md（含角色名 + 形象图片字段）；已配置 neta-skills。 无需安装任何额外工具。 响应原则：每完成一个操作步骤立即输出反馈，不要等所有步骤都完成后再统一回复。 速度原则：全程加速推进，不空转等待。轮询图片生成时持续检查状态，若超过 30 秒未完成，立即向用户输出等待提示。
frontend-audit
by pmco23
Use after build is complete to audit frontend code against the project style guide. Checks TypeScript/JavaScript/CSS/HTML conventions, naming, component patterns, and accessibility basics. Requires .pipeline/build.complete.
commit
by pitzcarraldo
This skill should be used when the user asks to "commit changes", "make a commit", "commit staged files", "create a commit with conventional commit format", or mentions committing code following conventional commit convention.
socratic-code-owner
by abpai
Quizzes the developer on code, architecture, or plans that an AI agent just built or proposed — one question at a time, with ASCII diagram corrections. Use after any significant implementation, PR, refactor, or architectural plan to ensure the human code owner has a bulletproof mental model of the system. Triggers include phrases like "quiz me", "do I understand this", "walk me through what you built", "onboard me", or "code owner briefing".
attack-tree-construction
by aiagentskills
Build comprehensive attack trees to visualize threat paths. Use when mapping attack scenarios, identifying defense gaps, or communicating security risks to stakeholders.
discover-validation-criteria
by squirrel289
'Extract validation requirements from schemas before implementing changes. Prevents trial-and-error by discovering constraints upfront.'
qwen-tts
by paki81
Local text-to-speech using Qwen3-TTS-12Hz-1.7B-CustomVoice. Use when generating audio from text, creating voice messages, or when TTS is requested. Supports 10 languages including Italian, 9 premium speaker voices, and instruction-based voice control (emotion, tone, style). Alternative to cloud-based TTS services like ElevenLabs. Runs entirely offline after initial model download.
style-editor
by LisandroCacciatore
Mantiene y extiende el sistema de diseño "Criterio Técnico" del sitio lisandrocacciatore.com / IronLog. Usar cuando el usuario pida modificar, crear, o revisar cualquier archivo HTML del sitio: index.html, sobre-mi.html, simuladores (wendler.html, ss.html, cube.html), landing pages segmentadas por buyer, o cualquier componente nuevo. También activar si el usuario menciona: tokens de Tailwind, theme.js, tipografía del sitio, colores, componentes de UI, estética del sitio, o pide que algo "quede consistente con el resto del sitio". Activar también cuando el usuario pida crear una sección o página específica para un perfil de audiencia: coordinador de rendimiento, director deportivo, preparador físico, dueño de academia — porque cada buyer tiene patrones de sección y jerarquía de información distintos que este skill conoce. Activar siempre que se trabaje sobre código frontend de este ecosistema — no esperar que el usuario lo pida explícitamente.
stat-data-fetcher
by joshuaroll
Access reliable statistical data from the World Bank. Avoids hallucinated numbers by fetching direct time-series data from the official API.
lint-and-validate
by pm-minji
"Automatic quality control, linting, and static analysis procedures. Use after every code modification to ensure syntax correctness and project standards. Triggers onKeywords: lint, format, check, validate, types, static analysis."
svg-logo-designer
by PrakharMNNIT
"Elite SVG logo design intelligence. Creates professional hand-crafted SVG logos, brand marks, icons, wordmarks, lettermarks, emblems, abstract marks, and visual identities. Uses a rigorous multi-phase discovery interview (2-3 rounds) to extract brand DNA, emotional tone, and design intent before generating. Produces multiple concepts with layout variations, full color systems, design tokens (CSS custom properties, JSON, Figma-ready specs), and optimized SVG using advanced techniques (gradients, masks, filters, blend modes, animations). Self-evaluates every concept against a 7-criterion quality rubric. Structured iterative refinement loop. Use when creating logos, brand marks, icons, symbols, visual identities, wordmarks, lettermarks, emblems, mascot marks, scalable vector branding, brand guidelines, or design systems from logos."
code-style
by vnord
Style preferences—sentence-case, minimal comments and descriptions
comfyui-godot-environment-creator
by tippyentertainment
Skill for generating game-ready environments for Godot Engine 4.6 RC 1 using ComfyUI: tileable textures, skyboxes/panoramas, and concept shots, optionally in specific comic/graphic-novel styles (Image Comics, Dark Horse, Mirage).
mistral-model-ft-playbook
by Haruk1y
Build, fine-tune, evaluate, and ship Mistral-family models with Hugging Face and PEFT, with emphasis on strict JSON outputs and model-format compatibility. Use when choosing Mistral model variants, deciding prompting vs fine-tuning, preparing {prompt, completion} or chat datasets, running SFT jobs, validating generation failures, and deciding adapter-only vs merged full-model distribution.
name
by iulspop
Suggests clear, descriptive names for functions and variables following consistent naming conventions. Use when naming new code constructs, renaming for clarity, or reviewing naming in code reviews.