Showing 6061–6090 of 15647 skills
Install, configure, and register a desktop application, its FreeDesktop .desktop entry, and icon on GNOME Linux, with support for desktop shortcuts, GNOME Shell favorites, icon caching, and validation.
nddipiazza/robos
Generate background maps, dungeons, battle backdrops, character sprites and menu screens for a parsed JRPG kgraph with a Gemini image model, using the collected resources as references.
nddipiazza/robos
Parse one or more folders of classic JRPG resources that a person collected (walkthroughs, screenshots, maps, sprite sheets) into a RobOS kgraph with the JRPG schema, and report what is still missing.
nddipiazza/robos
Compute semantic blast radius diff comparing World 1 (Production main) against World 2 (feature branch or uncommitted changes).
nddipiazza/robos
Export the Knowledge Graph or specific packages into standard semantic linked-data formats (JSON-LD 1.1, Turtle .ttl, N-Triples).
nddipiazza/robos
Query Knowledge Graph nodes by RDF type, package, dependencies, or trace connection paths between two entities.
nddipiazza/robos
Update properties, contracts, dependencies, or tags on an existing Knowledge Graph node with automatic SHACL re-validation.
nddipiazza/robos
Validate supported RobOS shape constraints and, for explicit workspaces, structure and references.
nddipiazza/robos
Answer where the user left off in a TV show or movie across all their computers ("what season of The Office did we leave off on?", "have we seen Dune?", "what are we watching?"), list Movie Player and Audio Player history, mark episodes or seasons watched, play the next episode, and sync the libraries and history with the RobOS backup vault on Google Drive.
nddipiazza/robos
太上老君炼丹炉总控台。用柳爷做自媒体的思路帮创作者把别人的爆款和自己的经历炼成自己的视频:读懂用户此刻在哪、这次要交出什么,再按需调用访谈、找对标拆爆款、选题、系列策划、开头结构、成稿、标题、复盘、变现承接。用户想拍视频但不知道拍什么、手里有参考不知怎么用、有题没稿、要改标题或开头、发了效果不对、替老板或客户做号时使用。
liuhaisi2026212-maker/taishang-laojun
看火:选题判断。从用户的经历、场景、参考或热点里判断能拍什么,给出少量私人定制、带理由的方向并推荐一个;也用于判断一个已有选题值不值得拍、会招来什么人。用户不知道拍什么、手里有热点或参考想找切入点、想知道某个选题行不行时使用。
liuhaisi2026212-maker/taishang-laojun
成丹:变现承接。用户明确想变现、接活、做产品或开源项目、处理“来的人不对”的商业问题时使用。区分曝光、需求与成交,看清展示的东西招来了谁,设计一个能兑现、合规、可小范围验证的交付和承接路径;不保证收益。
liuhaisi2026212-maker/taishang-laojun
开炉:开头与结构。给已选的主题或真实现场设计第一句话、紧接着的证据画面、中段推进和收尾,说清每一步观众在想什么、为什么这样排;也用于拍完之后按素材定剪辑顺序。用户有选题想定开头和拍法、想改开头、拍完不知怎么剪时使用。
liuhaisi2026212-maker/taishang-laojun
回炉:完整成稿与改稿。把用户的素材或参考观点写成可以直接念的完整逐字稿,也修改已有稿件和 AI 初稿;从“我要表达什么”出发借观点,不照搬别人的脉络。用户要完整口播稿、要改稿、要把别人的爆款改成自己的时使用。
liuhaisi2026212-maker/taishang-laojun
选材:找对标、拆爆款。炼丹炉的原料关:按用户的条件找对标,把一条爆款拆开看它为什么爆,再用复读、客户、替换三关掂量它到用户手里还成不成立,定出借哪个机制、换掉什么、用用户的哪件事接住。也用于判断该用哪个 AI 工具。用户刷到一条爆款想拍成自己的、在找对标、不知道该学谁时使用。
liuhaisi2026212-maker/taishang-laojun
丹方:系列策划。帮用户设计一个能一期一期拍下去的系列:每期固定什么、换什么,素材从哪来、能撑多久,会招来什么人,第一期怎么拍,拍几期看什么信号决定继续还是换。用户想持续更新但不知道拍什么、账号内容东一条西一条、拍了几条就断更、想做出“看他就够了”的固定栏目时使用;一条视频刚爆了、不知道下一条怎么接时也用。
liuhaisi2026212-maker/taishang-laojun
Advising protocol on top of answer-from-corpus. Before answering a how-to or improvement question, checks whether it's the question worth answering (does the asker's structure, situation or goal even support the answer they're asking for?), names the one fact the advice hinges on, and asks grounded framing questions round by round, reading each reply as evidence, until it has that fact or the user opts out; then answers through answer-from-corpus with what it learned, and closes by teaching the check it ran. Use when someone asks how to improve, adopt or roll out a practice ("how do I improve my user stories? I hear to write them vertically?"), or asks how to get people to change. Use answer-from-corpus instead for named lookups, survey questions, or "just answer".
chrisgagne/grounded-forge
Runs the 9-pass ingestion protocol against a single source dropped in {corpus-root}/sources/ingest/, producing a .source.md sidecar, the converted markdown, a deep reference, a light reference, one distillation per applicable task axis, and index and image updates. On success, the input source is removed from sources/ingest/.
chrisgagne/grounded-forge
Make an approved GooseWorks video when an answer's next_step gives its command.
gooseworks-ai/goose-skills
Use when submitting the owner's product to free AI/tool directories: the owner names a success count, you keep going until that many succeed or the queue runs out; skip paid and reciprocal-link listings; log every attempt.
Pluviobyte/saas-growth-agents
Write a paste-ready X post about one WongStack area (memory, the change loop, mini apps, browsing), or write or rewrite a site attachment with `attachment <slug>`; only when a person types it. Posts nothing.
matthewwong525/WongStack
用于遇到缺陷、测试失败或异常行为,且必须在提出修复方案前调查根因的场景。未经根因分析不得只修复表象。
huangwb8/skills
Do a task end-to-end — implement, PR, CI loop, ship. ONLY invoke when the user explicitly types `/do` or `$do`; never auto-select from a natural-language request, even one that sounds like an end-to-end task.
srid/drishti
Use when sending chat completions through liter-llm and routing to a specific provider via the `provider/model` prefix. Covers the chat call shape, provider routing, model_hint, message roles, and error categories.
xberg-io/liter-llm
Use when generating embeddings, calling the 12 web-search providers, or running OCR over documents with the 4 OCR providers through liter-llm. Covers embed, search, and ocr methods plus reranking.
xberg-io/liter-llm
Use when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chat_stream, delta handling, and null-content chunks.
xberg-io/liter-llm
Use when defining functions/tools for an LLM to call through liter-llm, or requesting structured JSON outputs. Covers tool schemas, tool_calls handling, and response formats.
xberg-io/liter-llm
dgiot/dgiot
Generates and edits digital 3D assets with the Meshy CLI: text-to-3D and image-to-3D models, texturing, remeshing and LODs, UV unwrapping, format conversion (GLB, FBX, OBJ, USDZ, STL, 3MF, Blender), rigging, animation, motion clips from text and reference images. Use when the user asks to make, texture, rig, animate or convert a 3D model or game asset. For physical 3D printing use meshy-3d-printing.
meshy-dev/meshy-3d-agent
Generates and prepares models for physical 3D printing with the Meshy CLI: white and multicolor prints (3MF, STL, OBJ), printability analysis and repair, splitting into parts, Creative Lab products such as figures, lamps and keychains, sizing, and slicer handoff (Bambu Studio, OrcaSlicer, PrusaSlicer, Cura). Use when the user wants something 3D-printed or asks for print or slicer files.
meshy-dev/meshy-3d-agent