Showing 9961–9990 of 15737 skills
Use when implementing local data storage with Room, DataStore, or offline-first patterns. Covers entities, DAOs, migrations, Paging3, and the repository pattern for data management.
GuillemRoca/agent-skills-android
Use when building features incrementally. Each increment leaves the system in a working, testable state. Covers vertical slicing, feature flags, and rollback-friendly development for Android.
GuillemRoca/agent-skills-android
Use when requirements are vague, contradictory, or thinner than the work deserves — before writing a spec or starting implementation. Iterative questioning that raises requirement confidence to ~95% instead of guessing and building the wrong thing.
GuillemRoca/agent-skills-android
Use when adding logging, crash reporting, or performance monitoring, or before shipping a release that must be watched in production. Covers Crashlytics, Play Vitals thresholds, structured logging with Timber, reportFullyDrawn, release-health monitoring, and CI performance gates.
GuillemRoca/agent-skills-android
Use when measuring or improving Android app performance. Covers Android Vitals (startup, jank, ANR), Macrobenchmark, APK size, recomposition tracing, and profiling with Android Studio tools.
GuillemRoca/agent-skills-android
Bộ kỹ năng chuyên sâu soạn thảo, dựng khuôn và thẩm định thể thức văn bản hành chính theo Nghị định 30/2020/NĐ-CP với bộ thẩm định thể thức tự động và quy trình tự kiểm tra khép kín.
TheDevio/ND30_Skills
Explains a topic in plain, literal language for someone who knows nothing about it. Use when someone new to a topic asks for an explanation from the basics.
coder-xieshijie/dev-skills
Recipe-development authority for turning a craving, ingredient set or vague meal idea into one coherent dish and method. Use for new recipe creation when no existing named-dish/cuisine owner already supplies the needed specification, or when the user asks for an original composed recipe.
DedInc/chef-agentic-skills
在遇到模型精度问题,需要分析定位时使用。典型的精度问题包括回复输出中有乱码或重复、精度测评不达标等。
kali20gakki/msAgent
Use when the user wants the AI's retro recommendations prepared and posted into TeamRetro — "post the AI's recommendations to TeamRetro", "prep our TeamRetro retro with the AI's findings", "park the top fixes for next retro", "add the AI's feedback to Friday's retro". Do NOT use for general TeamRetro administration (creating retros, health checks, teams, or managing existing items), and not for a tool-agnostic summary the user brings to their retro themselves — that's ai-retro-brief.
TeamRetroHQ/teamretro-skills
Seedance 2.5 视频生成全流程。先把需求澄清成参数(时长/画幅/机位类型/跟随方式/要不要切镜),再用 scene.json 引擎生成白模参考视频(渲染前有几何体检),也能从用户给的照片反解出白模,最后按官方规范生成与白模严格对齐的提示词。
alchaincyf/seedance-skill
把 DSH 在 Windows 上的命令执行环境补齐:真 bash 当执行器(默认装 niubash,受限沙箱也可用;也可选 PortableGit)+ PowerShell 7 便携版。新机器无 bash、或只有 PowerShell 5.1 时使用。已有可用 shell 时先用手上的,装完再问要不要升级。不需要管理员。
gosutry/dsh-windows-shell-toolchain
Build private cases from failed or suspicious ordinary AI Chat modifications, fix them, complete layered case validation, and run historical regression; use for continuous improvement. Use ai-chat-regression only to replay existing cases.
ZenUml/conf-app
Read-only screening of customer installs, uninstalls, new license candidates, subscription changes, cancellations and approaching or passed deadlines. Use when asked what changed recently, who installed/uninstalled, or which customer states deserve investigation. Covers existing and prospective customers and reports evidence without initiating follow-up.
ZenUml/conf-app
Diagnose an Atlassian "Forge Functions usage" alert (free tier 100,000 GB-seconds/month per app) — find which function or trigger is burning compute, using the Developer console's own metrics. Use when a Forge usage alert fires, when asked why GB-seconds are high, which tenant is heavy, or whether a trigger/resolver is billable. Triggers on "Forge Functions usage", "GB-seconds", "usage alert", "why is compute high", "Forge billing".
ZenUml/conf-app
donaldfilimon/abi
donaldfilimon/abi
Recall and write source-attributed local memory.
docmancer/docmancer
PostHog integration for React Router v6 applications
rkmahale17/rulcode.com
基于可审计 A 股数据执行首板隔夜模拟策略的决策技能。用于评估当日首板赚钱效应、筛选首板候选、生成带证据的 BUY、WATCH 或 NO_TRADE 决策并制定 T+1 退出计划。当用户需要评估首板赚钱效应、做首板留仓决策、制定隔夜打板策略或复盘首板案例时触发(包含触发词:首板隔夜, 首板候选, 今晚要不要留首板, 隔夜打板, 涨停首板, first board overnight)。
Fize/mmtickerlab
把批量任务拆成「强模型规划 + 低成本模型并行执行」的分层工作流:省钱靠降档,提速靠并行。需具备可降档的多档模型,或可并行派发的子代理;两者皆无时不要安装。当任务包含可重复单元(批量改写、逐条检查、字段提取、多份分别生成、大批量整理)且产物对错可判定时使用。单一连续产出、需要整体立意判断、或用户明确要求全力输出时不适用。旧中文名:快省双全·快省·分层执行(检索用)。
dseasea-byte/turbo-save
Assistente de pesquisa informativa, sem credenciais profissionais, sobre em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao pe
ranbot-ai/awesome-skills
Apoio a pesquisa juridica brasileira, organizacao de fatos e minutas, com verificacao em fontes oficiais e revisao profissional para casos concretos.
ranbot-ai/awesome-skills
Convert photos (people, pets, objects, logos) into 4 animated GIF stickers with captions. Use when: user wants to create cartoon stickers, GIF expressions, emoji packs, animated avatars, or convert photos to Funko Pop / Pop Mart blind box style animations. Triggers: sticker, GIF, cartoon, emoji, expression pack, avatar animation.
martgueritainaccurate875/skills
Edit and proofread Japanese speech-to-text transcripts from interviews, podcasts, lectures, classes, webinars, meetings, and videos while preserving every speaker's words, sequence, tone, and primary information without summarizing. Use when cleaning ASR or AI transcription errors, correcting punctuation and grammar, formatting dialogue and speakers, restoring supported conversational nuance, or verifying the spelling and existence of technical terms, proper nouns, product names, and field-specific jargon.
nob-git-dev/agent-skills
与えられた日本語テキストを、編集工学の10アプローチ/10メソッドに基づいて、事実と書き手の声を保ちながら新しい関係・見方・価値・物語を持つナレッジへ編集する。文章のリライト、企画書・解説文・ブランド文・スピーチ・記事の価値向上、視点転換、構成再設計、編集プロセスの説明や比較が必要なときに使う。
nob-git-dev/agent-skills
Edit and proofread Japanese speech-to-text transcripts from interviews, podcasts, lectures, classes, webinars, meetings, and videos while preserving every speaker's words, sequence, tone, and primary information without summarizing. Use when cleaning ASR or AI transcription errors, correcting punctuation and grammar, formatting dialogue and speakers, restoring supported conversational nuance, or verifying the spelling and existence of technical terms, proper nouns, product names, and field-specific jargon.
nob-git-dev/agent-skills
与えられた日本語テキストを、編集工学の10アプローチ/10メソッドに基づいて、事実と書き手の声を保ちながら新しい関係・見方・価値・物語を持つナレッジへ編集する。文章のリライト、企画書・解説文・ブランド文・スピーチ・記事の価値向上、視点転換、構成再設計、編集プロセスの説明や比較が必要なときに使う。
nob-git-dev/agent-skills
Use when 高教社杯/CUMCM 数学建模论文需要检查官方规则、匿名性、AI 使用披露、页数、附录/支撑材料、代码复现、提交清单或最终提交就绪状态。
capwitf/My-MathModeling-skills
Use when 高教社杯/CUMCM 数学建模论文、摘要、正文、表图、附录、登记表、结论、数值、单位、场景标签、可行性措辞或提交包需要跨材料一致性审查。
capwitf/My-MathModeling-skills