AGENT SKILLS · ÉQUIPEMENT DE MISSION
Des Agent Skills utiles classés selon leur usage réel
Comparez les Skills vérifiés par fonction, contenu, installations et fiabilité de la source avant de les ajouter.
- PÉRIMÈTRE
- VÉRIFIÉ
- Skills
- 22 662
- dépôts
- 3481
- dernière synchronisation
- 31 oct. 2026
chaiwithjaidavinci-resolve-social-editor
Plan, analyze, and build professional DaVinci Resolve social edits from multicam video/audio folders, podcast/interview footage, vertical 9:16 deliverables, branded social promos, burned-in captions, B-roll/overlay coverage, Resolve timelines, FCPXML/EDL handoff, or FFmpeg preview renders. Use when Codex must avoid jump cuts, preserve narrative coherence, keep the speaker in frame, balance dialogue/music, create reviewable edit decisions, or automate Resolve media/timeline setup.
- Installations / 1h
- 1
- GitHub Stars
- 26
- Mis à jour
- 17 mai
appiumsetup
Route and coordinate one or more Appium driver setup requests by handing UiAutomator2, Espresso, Chromium, Gecko, Mac2, Safari, or XCUITest to its dedicated setup Skill and collecting multi-driver completion. Use for Appium setup requests with no driver, one named driver, or multiple named drivers. Do not perform driver-specific setup in this Skill; select the exact child Skill and hand off. Do not use for an existing failing session or command; use appium-troubleshooting instead.
- Installations / 1h
- 1
- GitHub Stars
- 19
- Mis à jour
- 6 sept.
mercatorprojacademic-writing
学术写作一体化技能，含两种模式。(1) 格式化/润色：段落级学术润色、术语统一、公式规范化、逻辑优化，输出到草稿目录；(2) 人味化：中英文人味化改写、减弱模板化表述，可选检测脚本。对论文正文进行润色或改写时，默认应用 humanizer-zh 风格规则。默认输出目录见仓库根 README.md；学术诚信约定见仓库根 README.md。
- Installations / 1h
- 1
- GitHub Stars
- 8
- Mis à jour
- 10 oct.
mercatorprojchapter-structure-refactor
智能章节结构重构技能，针对学术论文整个章节的写作思路、逻辑架构、内容组织进行深度分析与系统性重构。通过分析章节意图、解构句子含义、重新梳理写作逻辑，对章节进行学术级整体改写。适用于章节逻辑主线不清晰、组织混乱、表达不规范、素材利用不充分等场景；常见于方法章、模型章、实验/案例章等需要整体重塑的篇幅。
- Installations / 1h
- 1
- GitHub Stars
- 8
- Mis à jour
- 10 oct.
mercatorprojformula-normalizer
智能公式规范化技能，提供数学公式格式标准化、符号一致性检查、公式风格转换等功能，以及学位论文中经典算法对比描述的通用模板生成。适用于：Markdown文档中数学公式的规范化处理、全文符号一致性检查、算法对比描述的学术写作等场景。
- Installations / 1h
- 1
- GitHub Stars
- 8
- Mis à jour
- 10 oct.
mercatorprojthesis-reviewer
学位论文系统性评审与语义审查技能。以研究生导师或盲审专家视角，对学位论文进行全面质量检查（选题综述、理论方法、工作量成果、逻辑结构、写作规范）以及语义级精审（语义重复、语义冗余、术语冲突、表述不一致、跨章重复、衔接断裂）；全文或章节级审查时默认执行 AI 痕迹检查（humanizer-zh 模式），与语义精审、宏观评审一并输出。跨章清单见 references/review-checklist.md。学术诚信约定见仓库根 README.md。
- Installations / 1h
- 1
- GitHub Stars
- 8
- Mis à jour
- 10 oct.
stark-ai-dejev-capability-advisor
Recommend available skills or MCP tools using TypeSafe Jev, or explicitly choose one next skill. Use when the user requests capability advice, candidate inspection, selection evaluation, or reusable host integration. Native client selection remains the default and fallback.
- Installations / 1h
- 1
- GitHub Stars
- 8
- Mis à jour
- 13 oct.
agent-easy-useto-ios-run
Resolve one USB iOS device or running simulator, connect its App runtime with MCP-managed idempotent loading, and execute exactly one supplied operation.
- Installations / 1h
- 1
- GitHub Stars
- 7
- Mis à jour
- 17 sept.
afrxoroblox-dev
How Roblox behaves at runtime. Use whenever writing, reviewing, or debugging server/client Roblox code that touches services, Instances, replication, RemoteEvents/Functions, character lifecycle, physics, DataStore, or platform caveats. Engine layer only — language rules live in luau-expert; UI libraries live in roblox-ui; Rojo/Wally workflow lives in roblox-toolchain.
- Installations / 1h
- 1
- GitHub Stars
- 5
- Mis à jour
- 26 avr.
afrxoroblox-toolchain
Filesystem-based Roblox development with Rojo + Wally + Luau LSP + StyLua + selene. Use when setting up, modifying, or debugging .project.json sync, package manifests, toolchain pinning, sourcemap regen, editor integration, CI builds, or any filesystem-to-DataModel question. Tooling layer only — language rules live in luau-expert; runtime behavior lives in roblox-dev; UI libraries live in roblox-ui.
- Installations / 1h
- 1
- GitHub Stars
- 5
- Mis à jour
- 26 avr.
afrxoroblox-ui
Building Roblox UI — engine primitives (GuiObjects, UDim2, AnchorPoint, layouts, inputs, containers) plus the Fusion 0.3 reactive framework. Use when writing, reviewing, or debugging UI components, sizing/positioning, layout structures, input handling, render order, or component lifecycle. UI layer only — engine semantics live in roblox-dev; language rules live in luau-expert; Rojo/Wally workflow lives in roblox-toolchain.
- Installations / 1h
- 1
- GitHub Stars
- 5
- Mis à jour
- 26 avr.
fortawesomeadd-icon
Add a Font Awesome icon to the user's project, generating the correct code for their integration method
- Installations / 1h
- 1
- GitHub Stars
- 4
- Mis à jour
- 2 juil.
qu-skillsai-social-media-content
Create AI-powered social media content for TikTok, Instagram, YouTube, Twitter/X. Generate: images, videos, reels, shorts, thumbnails, captions, hashtags. Tools: FLUX, Veo, Seedance, Wan, Kokoro TTS, Claude for copywriting. Use for: content creators, social media managers, influencers, brands. Triggers: social media content, tiktok, instagram reels, youtube shorts, twitter post, content creator, ai influencer, social content, reels, shorts, viral content, thumbnail generator, caption generator,
- Installations / 1h
- 1
- GitHub Stars
- 3
- Mis à jour
- 2 sept.
qu-skillsbackground-removal
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-commerce, transparent PNGs, photo editing. Triggers: remove background, background removal, remove bg, transparent background, cut out image, background remover, rembg, product photo editing, cutout, transparent png, bg removal, photo cutout
- Installations / 1h
- 1
- GitHub Stars
- 3
- Mis à jour
- 2 sept.
fandhe-aicreate-skill
新規スキルを skills/ /SKILL.md として scaffold する。命名・配置の重複確認、SKILL.md 作成、 symlink 設定、品質チェック、CLAUDE.md 反映までを一貫して自動化。「スキル作って」「新しいスキルを追加」 「create-skill」などで使用。Agent 定義の追加は create-agent、ドキュメント更新は update-docs を参照。
- Installations / 1h
- 1
- GitHub Stars
- 2
- Mis à jour
- 14 oct.
paulanunes85oc-cli
OpenShift CLI operations for ARO cluster management
- Installations / 1h
- 1
- GitHub Stars
- 2
- Mis à jour
- 10 avr.
sylphxaiaccessibility-conformance
Assess whether disabled users can complete the selected tasks, and what the current results support saying about conformance. Use when the user asks to review accessibility, audit a conformance claim, or check a VPAT or accessibility statement. Do not use to design the system under review or to fix accessibility defects.
- Installations / 1h
- 1
- GitHub Stars
- 2
- Mis à jour
- 3 oct.
sylphxaiaccount-recovery
Assess account recovery — alternative authentication, recovery proof, takeover handling, and enterprise operations. Use when the user asks to review password reset, recovery flows, account takeover handling, or SSO recovery. Do not use to design the recovery flow.
- Installations / 1h
- 1
- GitHub Stars
- 2
- Mis à jour
- 3 oct.
sylphxaianalyze-causal-inference
Estimate a causal effect with an explicit estimand, identification assumptions, design, diagnostics, and sensitivity. Use when the user asks whether a change caused an outcome, for difference-in-differences, IV, or target-trial emulation. Do not use to register a product experiment, forecast an unresolved future event, or critique a present explanation.
- Installations / 1h
- 1
- GitHub Stars
- 2
- Mis à jour
- 3 oct.
sylphxaianalyze-critically
Stress-test a claim, plan, diagnosis, or design by writing rejection conditions before interpreting the evidence. Use when the user asks to critique, steelman, red-team, find the kill criterion, or what would change your mind. Do not use for a domain go/no-go review, a causal effect estimate, a resolvable forecast, or ordinary implementation.
- Installations / 1h
- 1
- GitHub Stars
- 2
- Mis à jour
- 3 oct.
sylphxaianalyze-system-dynamics
Explain behavior over time through stocks, flows, feedback, delays, and adaptive actors. Use for growth, decline, oscillation, bottlenecks, or policy resistance. Do not use to estimate a single causal effect, register an experiment, or forecast a scoreable event without a dynamic structure.
- Installations / 1h
- 1
- GitHub Stars
- 2
- Mis à jour
- 3 oct.
sylphxaiauthor-skill
Write or revise agent-facing instructions: an Agent Skill, CLAUDE.md, AGENTS.md, system prompt, subagent prompt, or reusable prompt. Use when creating a skill, writing a subagent, tightening a trigger, encoding a gotcha, rightsizing CLAUDE.md, or rewriting prompts that still use MUST/NEVER recipes a capable model no longer needs. Do not use for user-facing product copy, store listings, or status updates.
- Installations / 1h
- 1
- GitHub Stars
- 2
- Mis à jour
- 3 oct.
sylphxaibuild-product
Build a missing product capability end to end on a real user path. Use when an accepted direction needs a usable slice across code, interface, data, and delivery, especially when it involves events, webhooks, queues, entitlements, billing state, or sync between systems. Use the product's current identity, storage, job, and event providers; do not invent a second runtime.
- Installations / 1h
- 1
- GitHub Stars
- 2
- Mis à jour
- 3 oct.
sylphxaidesign-ad-monetization
Design in-product ad placements and rewarded-ad grants. Use when the user asks about rewarded ads, mediation, ad-free purchase, or interrupting the core loop. Do not use for buyer checkout or store listings.
- Installations / 1h
- 1
- GitHub Stars
- 2
- Mis à jour
- 3 oct.