Loading…
Showing 7081–7110 of 10180 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| director-skillXAzer-R/azer-feilian-director导演执行技能(极速版·含分镜)。用于剧本分析、剧情拆解、镜头设计,并直接产出可用的视频提示词 production(提示词卡片 + 人物清单 + 场景清单 + 薄后期参考)。适配任意题材的影视短片 / 微短剧。 | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| keyframe-review-skillXAzer-R/azer-feilian-director参考图(设定图)Go/No-Go 审图清单。用户在 Nano Banana Pro 等文生图工具出参考图后手工审核阶段使用。提供逐项检查清单+判定规则+反馈模板,供用户快速识别人物/场景设定图是否合格·不合格时反馈导演调整提示词重抽。适配任意题材的影视短片 / 微短剧。 | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| long-take-skillXAzer-R/azer-feilian-director创意转场方法论。AI 视频帧天然对不齐,创意转场(尤其遮挡)是唯一可靠的跨片段缝合手段,同时也是强大的叙事工具——场景切换、时间跳转、角色替换、情绪转折。导演在镜头表设计转场创意并在提示词中执行。适配任意题材的影视短片 / 微短剧。 | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| storyboard-skillXAzer-R/azer-feilian-director提示词翻译手册(极速版·导演执行层)。导演在镜头表基础上把动作链/运镜/焦点翻译并组装为可用的视频提示词卡片——情绪核心翻译、运镜翻译表、焦点翻译、复合镜头模式。无模型选择、无线稿、无风格前缀(风格归服化道)。适配任意题材的影视短片 / 微短剧。 | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| weederoliverweissl/context-gardenMeasure and reduce a Skill's token footprint (always-loaded description + on-trigger SKILL.md body) without regressing routing accuracy or losing instructions. Use when a SKILL.md feels oversized, repeats rules, or has a vague description that might mis-route. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| supergoalcskwork/supergoal-skillRoute objective-driven development, verification, planning, "teach/explain", codebase learning, and skill evaluation through the Supergoal workflow. Use when Supergoal is requested or an autonomous delivery workflow is needed. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| qstack-update-plan-assetshani-q/qstackRefresh a repository's shared QStack plan template from the installed qstack-plan-to-html template without rewriting any plan or execution record. Use when plan board styles or scripts are stale, when qstack/compound_engineering/plans/.template/v1 differs from the installed skill, or automatically from /qstack-plan-to-html after it finds an older shared template. Requires qstack-plan-to-html, which owns the source. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| ai-festival-postergetedgehq/skillsTurn someone's real AI usage into a desert festival lineup poster, painted in Python. Scans local Claude Code and Codex session logs (plus an optional ChatGPT export), counts the sessions in which each tool, model and MCP server was actually used, books the most-used as headliners across three days (Build, Think, Create), and paints a dusk scene with brush strokes. No image model and no invented acts or numbers. Use for "make my AI festival poster", "Instafest for my AI tools", "my AI usage as a lineup". | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| clone-my-voicegetedgehq/skillsCreate a private local writing skill from a user's own representative writing samples. Use when the user asks an agent to learn or clone their voice for future DMs, posts, emails, or other writing. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| handoffsnapsynapse/skill-provenanceGenerate a handoff note summarizing skill project state for a future session or collaborator. Use when crossing a non-persistent boundary (e.g., Chat upload), ending a session that made significant decisions, or when the user explicitly asks for a handoff note. Triggers on: "generate a handoff", "write a handoff note", "summarize for next session", "prepare handoff", "what should the next session know". | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| opensnapsynapse/skill-provenanceVerify a skill bundle's integrity when opening a project. Use when loading a skill project directory and you need to check file completeness, verify SHA-256 hashes against MANIFEST.yaml, detect stale files, review recent changes, or understand what state the bundle is in before starting work. Triggers on: "open this skill", "verify the bundle", "check what changed", "is everything up to date", "load this project". | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| extract-knowledgeDisentinel/grafemaExtract knowledge (decisions, facts, session metadata) from the current Claude Code session into the Grafema Knowledge Base. Run after completing a task or at any point when substantive knowledge was produced. Follows runbook _ai/runbooks/02-claude-sessions.md. | Stars: 35 | Updated | Claude CodeCodex | Verified | Install |
| skiphow-bugmzored/SkipHowFind and fix a reported defect at its cause, including the sibling paths that share that cause. Use for bug fixes and recurring failures; a diagnosis-only request stays read-only. If context was compacted while this workflow governed, reopen this file and the SkipHow CTO skill before the next consequential action. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| skiphow-fast-fixesmzored/SkipHowCoordinate a live stream of local fixes and feedback before delivery, across interfaces, services, scripts, configuration, and artifacts. Use for bounded changes that may arrive while others run, with proportional delegation, focused checks, and recoverable shown results. A request to ship uses the delivery workflow. If context was compacted while this workflow governed, reopen this file and the SkipHow CTO skill before the next consequential action. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| skiphow-longrunmzored/SkipHowDeliver an accepted epic, milestone, or issue set through delegated slices that the CTO sequences, reviews in proportion to consequence, integrates, and carries to the agreed destination. Use for sustained execution and resumes of tracked work. If context was compacted while this workflow governed, reopen this file and the SkipHow CTO skill before the next consequential action. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| claude-apiValentinNikolaev/agent-skillsBuild Claude API clients; not Agent SDK, other providers, or read-only review. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| review-retrospectiveValentinNikolaev/agent-skillsAnalyze completed code or prose review runs, verified feedback, upstream misses, timing, and limit usage. Propose project lessons, skill improvements, or model changes without silently applying them. | Stars: 1 | Updated | Claude CodeCodex | Verified | Install |
| x9-onboardingxonika9/agent-skillsUse after installing or updating `x9-*` skills to check their readiness and compare the current harness with the bundled x9 configuration profile — «проверь готовность x9-скиллов», «настрой Codex как у автора», "check installed x9 skills", "apply the recommended harness settings". Do not use for general environment diagnosis, account authorization, or unrelated configuration editing. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| ask-mattZenUml/conf-appAsk which skill or flow fits your situation. A router over the skills in this repo. | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| code-reviewZenUml/conf-appReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". | Stars: 2 | Updated | Claude CodeCodex | Verified | Install |
| api-versioning-policysamber/developer-platform-skillsDefine the versioning and deprecation policy for an API - version scheme choice (URI path, header, date-based account-pinned, or deliberate no-versioning), a written breaking-change definition, deprecation notice windows by audience, sunset communication (RFC 9745 Deprecation and RFC 8594 Sunset headers), enforcement at the sunset date (fall-forward vs hard cutoff), and breaking-change governance, with REST version-and-sunset and GraphQL continuous schema evolution treated as separate policies. Use whenever the user mentions API versioning, /v2, breaking changes, deprecation, sunset dates, or migration windows - even if they never say "versioning policy". Client SDK versioning is plain SemVer and belongs to samber/developer-platform-skills@sdk-portfolio-strategy. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| atlassian-marketplace-playbooksamber/developer-platform-skillsTakes a B2B SaaS vendor's Jira, Confluence or Jira Service Management app onto the Atlassian Marketplace and keeps it there - Forge vs Connect, Free vs Paid via Atlassian for a connector to a paid SaaS, payment-model locks, pricing and revenue share, approval prerequisites, major versions needing review and admin consent, Connect-to-Forge migration, Enterprise Certified (successor to Cloud Fortified), bug-fix SLAs. Use whenever a vendor mentions listing on the Atlassian Marketplace, a Marketplace Forge or Connect app, a stalled ECOHELP review, or applying for Cloud Fortified. Do NOT use for listing copy or search rank (use samber/developer-platform-skills@integration-listing-optimization), for Forge code, internal-only apps, Bitbucket, Compass or Trello apps, or buyers vetting apps. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| github-marketplace-playbooksamber/developer-platform-skillsGets a vendor's GitHub App or GitHub Action listed on GitHub Marketplace and, for apps, selling there - free vs paid listing, publisher verification, marketplace_purchase billing duties, immutable pricing plans, enterprise buyers Marketplace cannot bill, the verified creator badge, delisting. Use whenever a vendor mentions GitHub Marketplace, listing a GitHub App, Marketplace paid plans, or selling through GitHub billing. Publisher side only; not for buying or allowlisting Marketplace apps as a customer. Do NOT use for building the action (use samber/developer-platform-skills@github-action-offering), repository growth (use samber/developer-platform-skills@github-engagement-playbook), or launch announcements (use samber/developer-platform-skills@app-marketplace-launch-marketing). | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| hubspot-marketplace-playbooksamber/developer-platform-skillsGets a B2B SaaS vendor's app listed on the HubSpot Marketplace and keeps it there - the three-active-install gate, the 25-install cap on unlisted apps, apps HubSpot refuses, scopes and the Shared data table, Draft bounces, review timelines, version deadlines, AI connector and MCP rules, App Certification, Technology Partner tiers. Use whenever a vendor mentions listing or certifying its app on HubSpot, a listing sent back to Draft, or HubSpot technology partner tiers. Do NOT use for listing copy or install conversion (use samber/developer-platform-skills@integration-listing-optimization), for running your own marketplace (use samber/developer-platform-skills@app-marketplace-review), for CMS themes, for admins vetting another vendor's app, or for CRM admin, API code or agency work. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| public-roadmap-strategysamber/developer-platform-skillsDecides whether and how a developer platform or API company publishes its roadmap to customers or the public - posture (none, NDA briefings, direction page, horizon roadmap, dated quarters), commitment vocabulary, what never goes public, disclaimers and sales citation rules, voting boards, and slipped or cancelled items. Use whenever the user mentions a public roadmap, a GitHub roadmap repo, a feature voting board, roadmap dates, sales promising unbuilt features, or a delayed roadmap item - even if they only say "customers keep asking what's coming". Not internal roadmap planning or prioritization. Do NOT use for triaging feature requests - use samber/developer-relations-skills@developer-feedback-loop; for deprecation notices use samber/developer-platform-skills@api-versioning-policy. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| crear-agentepappcorn/universeTe guía para crear TU propio agente: un ayudante de IA con un trabajo claro, que sabe dónde buscar la información y qué no debe hacer nunca. Primero te entrevista y después escribe el agente contigo. En Claude Code crea el archivo del subagente en `.claude/agents/`; en Claude Desktop o claude.ai arma el equivalente (un Proyecto con instrucciones, conocimiento y skills). Úsala cuando digas "quiero crear un agente", "hazme un asistente para X", "necesito un ayudante que se encargue de Y", "configurar mi IA", "make me an agent", "crear un subagente", o pidas mejorar un agente que ya tienes, incluso si describes el trabajo sin decir la palabra agente. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| crear-skillpappcorn/universeTe guía para enseñarle a TU Claude una tarea repetitiva, creando una skill propia. Te entrevista sobre la tarea que haces siempre igual, escribe contigo el archivo SKILL.md (con una buena descripción para que Claude la use sola), y te dice cómo instalarla en Claude Desktop (como .zip) o en Claude Code (carpeta .claude/skills/). Úsala cuando digas "quiero crear una skill", "enséñale a Claude a hacer X", "esto lo hago siempre igual y quiero automatizarlo", "cómo hago que Claude recuerde mi formato", "make me a skill", "convierte este proceso en una skill", o cuando describas una tarea que repites cada semana, aunque no digas la palabra skill. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| odwSuraj1235/open-dynamic-workflowsDynamic multi-agent workflows for Zed Agent and zcode. Use when the user says "ultracode", "workflow:", "/deep-research", or wants broad multi-file work with planning, parallel execution, verification, or crash-resume. | Stars: 50 | Updated | Claude CodeCodex | Verified | Install |
| ultracodeSuraj1235/open-dynamic-workflowsUltracode-style dynamic workflows for Zed Agent and zcode. Use when the user says "ultracode", "workflow:", "/deep-research", or wants broad multi-file work with planning, parallel execution, verification, or crash-resume. | Stars: 50 | Updated | Claude CodeCodex | Verified | Install |
| plant-trait-target-deriverbioepic-data/ecosim-agentUse this skill when you need to derive, from web-sourced evidence, typical values for a named plant's annual GPP, LAI, specific LAI or specific leaf area, Rubisco Vcmax at 25oC, Jmax at 25oC, root-to-shoot ratio, rooting depth, leaf protein nitrogen, and leaf chlorophyll nitrogen. | Stars: 3 | Updated | Claude CodeCodex | Verified | Install |