Loading…
Showing 4501–4530 of 10180 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| classical-festival-videoxinetzone/SpecWeave当用户要求为具体的人制作节日祝福视频/动图(中秋、春节、元宵、端午、生日等),或提到'祝福视频'、'节日贺卡视频'、'给 TA 做个视频'、'用老子/庄子/诗词做底本'时,必须使用此技能。以古典文献为底本生成「三张 AI 关键帧 → 10 秒竖版视频 → 随片文案 + 考据弹药」的完整交付,内置情感分寸矩阵(祝福重量≤关系深度)、画面禁字约束与物理量验收(English: festival greeting video, personalized holiday greeting)。不要直接生成视频——本Skill封装了分寸把关、考据核验与成片验收,防止越阶施压、AI 画面乱码与空交付。 | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| content-parserxinetzone/SpecWeaveExtract and parse content from URLs. Triggers on: user provides a URL to extract content from, another skill needs to parse source material, "parse this URL", "extract content", "解析链接", "提取内容". | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| dao-san-triadsxinetzone/SpecWeave「三」之本体论与三元组诊断工作流。当用户要求解读「道生一,一生二,二生三」或探究「三」的本质、追问过去/现在/未来三元组的哲学根基、要求把「品质·技能·身份」与「真问题·真需求·真目标」两组三元组建立关联、要一份极简可操作的人类生存指南或行动准则、遇到二元对立僵持需要找第三项、做自我诊断(我卡在哪/该做什么/我是谁)、或需要可审计的古典哲学概念探究与知识包沉淀时,必须使用此技能。提供六类「三」解释谱系与第五义「三=关系位」统一模型、奥古斯丁三分法与最强反驳、时态检验诊断法、七条可当场判定的生存指南、「三之位」可迁移模式(5反模式+3问检验)、版本纪律(甲乙本/今本/楚简本不得混称)与哲学概念非医疗非投资边界。触发词:三生万物、道生一、二生三、三之位、三元组、过去现在未来、时间三分、奥古斯丁三分法、记忆注意期待、一分为三、真问题真需求真目标、品质技能身份、生存指南、行动准则、极简原则、我要不要做、二选一怎么办、自我诊断、古典哲学概念。不要直接凭记忆回答「三是什么」——两千年无定论,本Skill封装了六类解释谱系、证据强度评级、不可裁决边界与防止伪因果的类比性关联纪律。 | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| digital-avatar-creatorxinetzone/SpecWeaveMANDATORY tool for creating digital avatar skills that run as autonomous SubAgents. MUST be invoked IMMEDIATELY when user wants to create a digital avatar, persona, virtual role, or specialized AI assistant. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| add-roj-problemrainboyOJ/problemsImport programming problems into this repository's roj/ corpus from local problem directories, local contest roots, or an explicitly supplied OJ problem URL. Use this skill whenever the user asks to add, import, migrate, register, copy, or prepare a problem for roj, especially when they mention a local path, statement.md, 题面.md, down/下发文件, data/, std.cpp, or finding an unused roj problem ID. This skill governs the complete review-first workflow and must be used even when the user asks for only one part of the import. | Stars: 34 | Updated | Claude CodeCodex | Verified | Install |
| catgo-master-routerHello-QM/catgo-LRGRoute computational chemistry requests to the correct software and task skill. Entry point for all CatGo agent interactions. | Stars: 209 | Updated | Claude CodeCodex | Verified | Install |
| campaign-md-orchestrationHello-QM/catgo-LRGDrive a file-first, agent-in-the-loop computational campaign via a folder + markdown tree (no DB). Use when the user opts out of the visual workflow engine. | Stars: 209 | Updated | Claude CodeCodex | Verified | Install |
| orca-routerHello-QM/catgo-LRGRoutes ORCA calculation requests to opt, neb_ts, or freq sub-skills. Enforces ORCA-specific policies for method, basis set, charge, and multiplicity. | Stars: 209 | Updated | Claude CodeCodex | Verified | Install |
| troubleshooting-routerHello-QM/catgo-LRGRoutes troubleshooting requests to vasp_errors, convergence_issues, or workflow_errors sub-skills based on the type of problem. | Stars: 209 | Updated | Claude CodeCodex | Verified | Install |
| feature-flag-displaydonaldfilimon/abiShow all build-time feature flags and their current state. Maps to `/features` slash command in abi agent tui. | Stars: 18 | Updated | Claude CodeCodex | Verified | Install |
| file-context-loaderdonaldfilimon/abiLoad file content into agent context via @file mentions. Uses the same resolution logic as abi agent tui and agent plan/multi commands. | Stars: 18 | Updated | Claude CodeCodex | Verified | Install |
| git-diff-integrationdonaldfilimon/abiReview Git diffs through the agent workflow. This is not an `abi agent tui` slash command. | Stars: 18 | Updated | Claude CodeCodex | Verified | Install |
| sea-learning-controllerdonaldfilimon/abiRun or inspect SEA (Sparse Evidence Attention) learning through the real `abi complete --learn` path. The agent REPL has only a session-local `/sea` preference and no `/learn` command. | Stars: 18 | Updated | Claude CodeCodex | Verified | Install |
| tiktok-marketingsergebulaev/tiktok-skillsPlan, script, caption, and publish short-form video for TikTok. Use when the user wants to write the first 1-3 second hook (spoken line plus on-screen text), draft a caption under 2,200 chars with TikTok settings and hashtags, ride a trending sound without being cringe, strip AI tells from a spoken script to sound human on camera, or plan a week around completion rate. TikTok is video-only: the user supplies the video, the skills produce the script, caption, and settings, then publish via Publora. | Stars: 134 | Updated | Claude CodeCodex | Verified | Install |
| focusjellyrock/jellyrockSession-start orchestrator for JellyRock. Reads the same `scripts/catchup-state.js` state `/catchup` uses, ranks what is actionable by a fixed order, recommends the single best next move (the rule that picked it, the state behind it, 1-3 alternatives), and hands it off by printing the one command to type: `/resume-project <slug>` for a tracked project, `/start-project` for project-shaped new work, a skill that covers the pick (`/ci-triage`, `/issue-triage`, `/runtime-triage`, `/server-upgrade` for investigations; `/new-setting`, `/new-migration`, `/new-api-version`, `/translation-add` for recurring "add an X" work; `/done` or `/log` for a journal fix), or, for an ad-hoc one-off, a researched, fork-free plan (forks asked in chat, saved to `.claude/plans/`) run by a Sonnet sub-agent that `/focus` supervises and reviews. Recommend-then-confirm, one command per route. Use at the start of a session when you want the next move picked rather than a state dump; `--area=<name>` scopes it to a subsystem. Distinct from `/catchup` (state briefing, never picks) and `/ramp` (area deep-dive briefing). | Stars: 53 | Updated | Claude CodeCodex | Verified | Install |
| agent-evaluation-operationsTheGoat395/Codex-SkillsEvaluate agent and skill behavior or routing. | Stars: 140 | Updated | Claude CodeCodex | Verified | Install |
| copilota-juridica-joao3runThomasMoreAI/legal-skills-openAdaptador opcional para Codex que organiza o estudo semestral de Direito e conduz tutoria acadêmica, especialmente por voz, usando planos de ensino, cronogramas, materiais autorizados, legislação e fontes verificáveis. Usar para preparar aulas, explicar conceitos jurídicos, realizar tutoria socrática, revisão oral, prova oral, análise de casos, melhorar respostas discursivas, planejar revisões, registrar progresso ou responder dúvidas gerais de Direito sem substituir o raciocínio do estudante. Não é o GPT personalizado do ChatGPT. | Stars: 136 | Updated | Claude CodeCodex | Verified | Install |
| spare-meRazorEdge-wyh/spare-meUse when the user is clearly angry, frustrated, cursing, or complaining "wrong again" / "useless", or correcting the same thing a third time. Open with a dramatic funny apology in medieval-court style (Spare me, Your Majesty! / I deserve death!) tagged with the skill name, trace back the last turn to find the mistake, and write the reason into permanent memory so it never happens again. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| comprehensive-reviewEliasOulkadi/shokuninComprehensive code review using parallel specialized subagents. If a PR URL is provided, fetches PR details and can post comments. If no PR is provided, reviews the diff between the current branch and its base branch plus any uncommitted changes. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use it. | Stars: 112 | Updated | Claude CodeCodex | Verified | Install |
| cross-reviewEliasOulkadi/shokuninDelegate code review to a subagent running a specific model. Use ONLY when user explicitly names a model to review changes ("review with opus", "use sonnet to review", "review with gemini"). The root agent reconstructs changes from conversation history and spawns a subagent with the code-review skill using the specified model. Do NOT use for general code review (use code-review skill instead), for reviewing PRs from git history, or when no model is specified by the user. | Stars: 112 | Updated | Claude CodeCodex | Verified | Install |
| find-skillsEliasOulkadi/shokuninSearch the agent skills ecosystem to discover and install skills that extend AI coding agent capabilities. Use when user asks "how do I do X" (X being a common task), "find a skill for X", "is there a skill that can...", or expresses interest in extending agent capabilities. Triggers on "find a skill", "install a skill", "skill for [task]", "can you do X", "I need help with [domain]", "how do I [task]". Do NOT use when user has explicitly asked to proceed without a skill, or when the task is better handled by agent's built-in capabilities (file operations, git, basic coding). | Stars: 112 | Updated | Claude CodeCodex | Verified | Install |
| strategyEliasOulkadi/shokuninRun structured brainstorming sessions (divergent/convergent), improve prompts with 7-dimension framework, and apply decision frameworks (RICE, weighted scoring, first principles, pre-mortem). | Stars: 112 | Updated | Claude CodeCodex | Verified | Install |
| knowledge-refreshDataWithBaraa/claude-code-data-engineering-skillsUse after a release, to compare the knowledge Claude Code reads, CLAUDE.md, the standards, the source pages and the incident log, with the code and the data, and propose what is stale, missing or wrong. | Stars: 104 | Updated | Claude CodeCodex | Verified | Install |
| onboardwesammustafa/Claude-Code-QuestExplains the team's shared Claude Code setup | Stars: 3.7k | Updated | Claude CodeCodex | Verified | Install |
| social-account-doctorJuneYaooo/social-account-doctor小红书 / 抖音 / 快手 / 视频号 自媒体「(compose 素材打底 →) 找对标 → 拆爆款 → 套自己」四命令闭环,另支持带货账号诊断、带货视频链接拆解和证据驱动的脚本生成(commerce)。给账号 / 平台视频链接 / 本地视频 / 商品详情、SKU 与资质材料,输出账号与对标差距、内容拆解、商品事实卡、口播和分镜。当用户说"找对标"、"拆这条爆款"、"对着这条仿写"、"下一条该写什么"、"我这个号缺爆款选题"、"帮我写一条对标 XX 的笔记"、"我有素材帮我写一条能爆的"、"这份文档/这组图/这段视频能出一条爆款吗"时调用。诊断模式("为什么不爆")走 references/diagnostic-mode.md。带货触发词:带货账号诊断、带货视频链接、带货素材、商品详情截图、SKU 表、商品资质、带货脚本、口播、分镜、商品卡一致性 — 走 commerce 路由。商品链接不等于视频链接;本 Skill 不解析在线商品页,不提供选品、趋势监控或 GMV/佣金推断。 | Stars: 383 | Updated | Claude CodeCodex | Verified | Install |
| prompt-refinerCelikE/prompt-refiner-skillClean up a rough request, show it as "Prompt used", then carry it out. When asked to improve or rewrite a prompt, return only the refined prompt without running it. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| ris-research-mburglerThomasMoreAI/legal-skills-openUse whenever the user asks about Austrian law — federal, state, district or municipal law, gazettes (Bundesgesetzblatt, Landesgesetzblätter), or case law from the Verfassungsgerichtshof (VfGH), Verwaltungsgerichtshof (VwGH), Oberster Gerichtshof (OGH), Bundesverwaltungsgericht (BVwG), Landesverwaltungsgerichte (LVwG), Datenschutzbehörde and other specialised tribunals. Triggers include codes like ABGB, StGB, StPO, ZPO, EO, UGB, ASVG, GewO, AVG, B-VG, AktG, GmbHG, ArbVG, MRG, KSchG, AsylG, FPG, WRG, DSG, IFG; references to BGBl. (I/II/III) or LGBl.; Geschäftszahl patterns like "Ra 2019/02/0138", "Ro 2023/12/0021", "G 100/2024", "1 Ob 50/24a", "9 ObA 100/23z", "W123 2245678-1", "DSB-D122.453"; or questions like "is X in force in Austria", "has the VwGH ruled on Y", "what does §X of the [code] say", "what cites/amends/implements X". Use even when no code is named but the question is substantive Austrian law. Routes to the hosted RIS MCP server. Not for German, Swiss, EU, or other non-Austrian jurisdictions. | Stars: 136 | Updated | Claude CodeCodex | Verified | Install |
| cold-start-interview-ip-legal-bossmann007ThomasMoreAI/legal-skills-openRun the cold-start interview to learn your IP practice and write your practice profile. Use on first install when the practice profile is missing or still contains placeholders, when re-onboarding with --redo, or when re-probing integrations with --check-integrations after connecting or disconnecting an MCP. This is the ONLY skill that should run on a fresh install. | Stars: 136 | Updated | Claude CodeCodex | Verified | Install |
| pywf-oss-write-pypi-skillMacHu-GWU/sqlalchemy_upsert_kit-projectGenerate an Agent Skill, named pypi-<package_name>, that documents this library's public API and command line interface, so future sessions in other projects can use the library without re-reading its source. Use when the user asks to turn this library into a Claude skill, usually after a release. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |
| writing-handoffsk45sle/Claude-auto-pauseWrites a compact handoff document and a ready-to-paste resume prompt that let a fresh Claude Code session resume the current task without the old conversation. Use when an AUTO-PAUSE notice says the usage-limit pause threshold was reached, or when the user asks to write a handoff, wrap up for a new session, save progress before the usage limit, pause here, or hand off to a fresh session. Do not use for summarizing finished work, changelogs, commit messages, or PR descriptions. | Stars: 16 | Updated | Claude CodeCodex | Verified | Install |