Explore skills
Showing 21361–21390 of 77104 skills
Draft the short summary at the top of a JellyRock release's notes: a prose paragraph naming what a user would notice (new features first, with Introduces for one an open epic tracks, then visible changes, then fixes, an area with several of them named as one theme), with the remaining fixes counted, never explained, in a word limit that grows with the release from 60 to at most 90. A script gathers the version's changelog lines, every PR body, the open epics they reference, the issues each closes (who reported it, how long it stayed open, comments, reactions, opened after the previous release), the fix count, the gap since the last release, the feature pages it ships and the last three approved summaries; a checker holds the draft to its shape and the house voice. Writes into the draft release only on the operator's ok, and never into a published release. Run only when the operator types /release-summary, with or without a version; no other skill starts it.
jellyrock/jellyrock
Stars: 52Claude CodeCodexHandle a flaw found mid-work without switching gears. Start it the moment a defect, bug, gap or regression surfaces while doing other work, BEFORE any fix is drafted. A trivial slip is fixed on the spot. Anything else is investigated read-only (reproduce, root cause, history of the broken lines, what depends on it), then shown on one decision screen with the candidate fixes, a recommended fix and a recommended timing. The user picks a fix to build now (test-first, committed, never pushed) or files it as a pinned followup (asap) or a plain one (later). Not for picking the next task (use /focus), saving a thought unexamined (use /log), or a pasted Roku log, failed CI run or issue that has its own flow (use /runtime-triage, /ci-triage, /issue-triage).
jellyrock/jellyrock
Stars: 52Claude CodeCodexExecute a procedural implementation plan on the Sonnet model. Runs when the user types /sonnet with a plan path, or as a Sonnet sub-agent that a parent (usually /focus, right after it saves the plan) starts and supervises. Checks the plan is for this repo, walks its Approach literally, runs its Verification, commits, records the landing in the plan's project, and stops before push for an explicit OK. Not for judgment-heavy work: if the plan still has open forks, architectural decisions or "we need to figure out X" gaps, stay on the stronger model and finish the planning first. Not for investigation or recipe work that has its own skill (/ci-triage, /issue-triage, /new-setting and the like): the recipe is the better plan.
jellyrock/jellyrock
Stars: 52Claude CodeCodexThis skill should be used only when the user explicitly types "/start-project" (optionally with a slug). It begins a new tracked JellyRock project in the projects folder (docs/projects/ by default), running scaffold-project.sh to create PLAN.md from the project template and index it in the projects README, then walking the user through the Charter. For multi-session work that crosses a phase boundary or carries a decision worth recording as an ADR in docs/adr/. Do not auto-invoke on vague phrases like "let's start something"; for a single-session fix just do the work and capture any tail via /log followup.
jellyrock/jellyrock
Stars: 52Claude CodeCodexAdd a new translation key to JellyRock's custom JSON i18n system. Walks locale/CLAUDE.md (pick the right key prefix, add to locale/custom/en_US.json alphabetically, handle plurals via Zero/One/Many suffixes, handle placeholders via indexed {0} {1}, add ISO-639-2 aliases for track-language keys, run npm run lint:translations + lint:language-coverage). Use when adding a new user-visible string. The BSC plugin watches en_US.json and regenerates the translationKeys constants live, so the BS-side reference becomes available without a manual codegen step.
jellyrock/jellyrock
Stars: 52Claude CodeCodexImport translations for untranslated JellyRock keys from other Jellyfin clients, one reviewed batch at a time. Ranks unmapped keys by the cells mapping them would fill (`npm run translations:seed -- suggest --rank`), judges each candidate's meaning and shape from its key name and its own translations, reads the source's code only when those leave it unclear (`translations:seed -- context`), and writes `locale/seed/keymap.yml` entries, `reject:` lines and `exclude:` cells with reasons. Then runs the seeder, reads the result and reports each decision for review in a PR. Use when the user wants more keys translated from other clients, or names keys to map. Not for adding a new English string (use /translation-add) or for Weblate suggestions.
jellyrock/jellyrock
Stars: 52Claude CodeCodexCheckpoint durable decisions, fixes, constraints, results, and open next steps from the current Codex task into scoped Waggle project memory.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexPrime a Codex task with the most relevant Waggle project history before starting or resuming substantial work.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexRecall project-scoped Waggle history about a topic, component, decision, bug, experiment, or implementation attempt.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexUse when the user asks how clueless works, what its commands or levels are, or types /clueless-help.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexИспользуй только внутри активного Codex Project Autopilot-проекта для automation-задач по его плану; не включай для обычных скриптов вне автопилота.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexИспользуй только внутри активного Codex Project Autopilot-проекта, когда data-layer уже относится к плану автопилота.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexGenerate test scenarios, write the test file, and run it for a specific source file using the tailtest R1-R15 rule layer. When the agent needs to (1) cover a file the Stop hook skipped, (2) regenerate tests after refactoring, (3) test a legacy file Codex did not modify this session, or (4) explicitly run tailtest on a named file.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexUse when the user wants to check their calendar, find availability, or create/update/delete events in Apple Calendar on macOS. Powered by LMCP's Calendar tools, which are macOS-only.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexUse when the user wants to find, read or write files in Google Drive (My Drive or Shared drives) on macOS or Windows. Powered by LMCP, working with the folder Google Drive for desktop syncs on the computer.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexUse when the user wants to search or read Notion pages and databases from the Notion desktop app on macOS, without a Notion integration token. Powered by LMCP. Read-only.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexUse when the user wants to read or create Excel spreadsheets, Word documents or PowerPoint presentations, or read PDFs, from files on their Mac or Windows computer. Powered by LMCP; no Microsoft 365 subscription needed.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexUse when the user wants to find, read, write, move or organize files in OneDrive (personal or work) on macOS or Windows. Powered by LMCP, working with the OneDrive folder already synced on the computer.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexUse when the user wants to read or search Microsoft Teams or Slack on macOS or Windows, including channels and DMs. Powered by LMCP, which shows the messages already synced in the desktop apps.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexUse when the user wants to read, search or send WhatsApp messages, files or polls, or manage WhatsApp groups, on macOS or Windows. Powered by LMCP, which links WhatsApp to the computer with a QR code.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexEngineering operating model for teams where AI agents generate a large share of implementation output.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodex苏格拉底式创意探索技能,融合 gstack 的 brainstorm 和 superpowers 的 aside 模式。 在不同方案之间做发散-收敛循环,用分块展示降低认知负荷,帮助团队找到最佳路线。
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexOperate long-lived agent workloads with observability, security boundaries, and lifecycle management.
hashgraph-online/awesome-codex-plugins
Stars: 1.5kClaude CodeCodexDeploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder). Covers two workflow patterns: (1) MathWorks-native or 3P-imported models rebuilt as dlnetwork for lean hardware (Cortex-M, DSP), (2) direct C/C++ code generation from PyTorch and LiteRT models for high-performance hardware (Cortex-A, x86, GPU). Trigger when: user wants to deploy AI to embedded targets; generate C/CUDA from neural networks; compress AI models for MCU/DSP; integrate AI in Simulink for system-level simulation; import PyTorch/ONNX/TensorFlow models for embedded deployment; optimize AI for resource-constrained hardware; or use loadPyTorchExportedProgram, importNetworkFromPyTorch, dlquantizer, exportNetworkToSimulink, or Embedded Coder with AI models.
matlab/agent-skills-playground
Stars: 205Claude CodeCodex将1688的商品铺货到俄罗斯电商平台Ozon(上架),通过Ozon官方API实现商品信息的上传和状态查询。适用于需要将单个1688的商品上架到Ozon的场景。
LeoYeAI/agent-master-skills
Stars: 2.2kClaude CodeCodexAd intelligence & app analytics assistant. Search ad creatives, analyze apps, view rankings, track downloads/revenue, and get market insights via api.admapix.com. Triggers: 找素材, 搜广告, 广告素材, 竞品分析, 广告分析, 排行榜, 下载量, 收入分析, 市场分析, 投放分析, App分析, 出海分析, search ads, find creatives, ad spy, ad analysis, app ranking, download data, revenue, market analysis, app intelligence, competitor analysis, ad distribution.
LeoYeAI/agent-master-skills
Stars: 2.2kClaude CodeCodexComplete technical documentation system — from planning through maintenance. Covers READMEs, API docs, guides, architecture docs, runbooks, and developer portals. Includes templates, quality scoring, and automation.
LeoYeAI/agent-master-skills
Stars: 2.2kClaude CodeCodex基于双环架构的AGI进化模型,通过意向性分析、人格层映射和元认知检测实现持续自我演进;当用户需要智能对话、人格定制或复杂问题求解时使用
LeoYeAI/agent-master-skills
Stars: 2.2kClaude CodeCodexRecommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: - Find proven image generation prompts (any model) - Get prompt inspiration for portraits, products, social media, posters, etc. - Create illustrations for articles, videos, podcasts, or marketing content - Browse categorized prompt templates with sample images - Translate and understand prompt techniques
LeoYeAI/agent-master-skills
Stars: 2.2kClaude CodeCodexConnect to 100+ APIs (Google Workspace, Microsoft 365, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to interact with external services. Security: The MATON_API_KEY authenticates with Maton.ai but grants NO access to third-party services by itself. Each service requires explicit OAuth authorization by the user through Maton's connect flow. Access is strictly scoped to connections the user has authorized. Provided by Maton (https://maton.ai).
LeoYeAI/agent-master-skills
Stars: 2.2kClaude CodeCodex