All authors
Claude Skills by youlianvr
github.com/youlianvr269 skills0 installs0 views
- Coding StyleUse when writing or reviewing code for clear intent, project conventions, verified APIs/dependencies, coherent scope and maintainability. Ponytail is the main-route simplicity method; this part covers code-level execution and optional complexity diagnostics. No mandatory persona, test quota or fixed report format.Votes: 0GitHub stars: 15
- Cross Platform GotchasUse when writing/editing cross-platform scripts and installers (Python/bash, Linux/macOS/Windows): platform.system() vs sys.platform, regex in raw strings (r"\\.zip" matches literal backslash), FileNotFoundError from subprocess.run, package manager fallback (winget→scoop→choco), Windows registry PATH (fresh binaries not visible to process), bash = WSL stub on Windows (need Git Bash), single source of truth instead of copies. Verified against a real Windows install bug report.Votes: 0GitHub stars: 15
- Debug Incident ProtocolUse for a hung, regressed or silently failing runtime, stale-code suspicion, duplicate exclusive consumers, or a process whose restart must be verified. Covers discriminating facts, bounded hang localization, process ownership, safe recovery and current loaded-code evidence. Testing and refactor methods live in their matching discipline parts.Votes: 0GitHub stars: 15
- FastapiFastAPI and Pydantic conventions for API work: `Annotated` parameters and dependencies, return types and response models, router-level parameters, async versus sync path operations, JSON Lines / SSE / byte streaming, serving a built frontend, and native OpenTelemetry. Use when writing or reviewing a FastAPI app in this workspace.Votes: 0GitHub stars: 15
- Hardening ObservabilityUse when the user wants to: harden service limits/protection ("so it cannot be farmed", "add rate limit"), add metrics/logs/alerts, figure out why metrics lie, fix "database is locked", configure log files without conflicts, conduct a security audit (secrets, admin privileges, mass mailings). Covers: env-limits with safe defaults, metrics (newly_credited, upsert, snapshot), three-tier logging and audit logs, SQLite busy_timeout+WAL, rate-limit at the edge with monotonic, non-blocking event lo...Votes: 0GitHub stars: 15
- Improve Codebase ArchitectureUse to investigate demonstrated architectural friction, compare coherent boundary/interface changes and discuss the best improvement. Follow current project decisions and actual consumers; use a visual report when requested or useful for comparison. No mandatory new glossary, external CDN or unexposed skill/subagent dependency.Votes: 0GitHub stars: 15
- Jsonc Surgical EditEdit JSON/JSONC configs programmatically, WITHOUT losing comments, external content, and formatting: surgical edits by offsets (the pattern microsoft/node-jsonc-parser uses for VS Code settings.json) instead of rewriting the entire file. Use when a script/installer adds, updates, or removes entries in a config (mcp sections, settings, server blocks) and the file contains comments or external (manual) entries that must not be overwritten; when after running an installer "comments/settings disa...Votes: 0GitHub stars: 15
- Langchain RagINVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).Votes: 0GitHub stars: 15
- Llm Cost OptimizerUse proactively whenever LLM API costs come up -- or should. Triggers include: 'my AI costs are too high', 'optimize token usage', 'which model should I use', 'LLM spend is out of control', 'implement prompt caching', 'we're about to launch an AI feature', 'build me an AI endpoint'. Don't wait for an explicit cost complaint -- if someone is building an AI feature, designing an LLM endpoint, or choosing between models, cost architecture belongs in the conversation. Apply immediately when any o...Votes: 0GitHub stars: 15
- Money Path SafetyUse when the user wants to: pay/buy/subscribe, receive or spend a bonus/promo/referral, check balance or limit, get a refund, or when any debit/credit/quota logic changes — even if the request doesn't explicitly mention money ("give me more minutes", "why was it charged twice", "enter promo code"). Checks: idempotency, atomicity, mutation logging, separate buckets, hard gate before expensive work, charge after success, soft delete, compound PK, structured failure. Do not use for pure CRUD wit...Votes: 0GitHub stars: 15
- PonytailMain coding-route simplicity method: understand the requested outcome, question unnecessary work, prefer fitting existing tools/code and standard facilities, then build the smallest clear complete solution. Use for coding, repair, refactoring and dependency choices, especially over-engineering or an explicit ponytail request. Simplicity must preserve capabilities, correctness, verification and the owner's confirmed scope.Votes: 0GitHub stars: 15
- Production First DecisionsUse when a consequential tool, dependency or design choice has unresolved evidence: compare existing solutions and project conventions, research the specific uncertainty, and test the load-bearing claim before adopting it. Includes reuse versus build, small spikes and durable decision rationale. Not a web-search requirement for ordinary implementation details.Votes: 0GitHub stars: 15
- SimplifyImprove clarity and reduce needless complexity after behavior is understood; preserve behavior and keep cleanup separate from correctness fixes.Votes: 0GitHub stars: 15
- Systematic DebuggingUse for bugs, failing checks, regressions or unexpected behavior. Reproduce the symptom, trace the relevant data/control flow, test a specific hypothesis, repair the cause and verify the original path. Scale investigation to the uncertainty; repeated failures require new evidence, not an automatic architecture verdict or a fixed number of permission requests.Votes: 0GitHub stars: 15
- Testing DisciplineUse when writing or reviewing tests, reproducing a bug, checking test sensitivity, isolating storage or external effects, or deciding what verification a change needs. Covers independent expectations, real behavior, controlled doubles, boundary cases and the user-facing usage path. No mandatory implementation order or per-function test quota. Debugging strategy lives in debug-incident-protocol; completion claims in dev's verification-before-completion part.Votes: 0GitHub stars: 15
- Using SuperpowersChoose and compose relevant skills when the workflow or tool route is unclear. Use known routers directly or list `skills/` for discovery; load only matching contracts. No skill invocation before every response and no universal design gate.Votes: 0GitHub stars: 15
- Documentation WriterWriting a Russian school пояснительная записка (ПЗ) that has to survive a jury: the НИР and проект/сайт structures, title page, format profiles, [N, с. X] citations, markdown-to-docx build and the pre-submission review. Use for "написать пояснительную записку", "оформить работу для конкурса", a project or site description, or preparing a school work for submission.Votes: 0GitHub stars: 15
- Pz WriterWrite and format a Russian school пояснительная записка (ПЗ, «записка») — исследовательская работа for contests (district and regional conferences, project defence) or a project/site description: canonical structures for both genres, title page, format profiles (15-page republican НИР standard vs the accepted school sample), [N, с. X] citations, hypothesis/task/evidence alignment, md -> docx generation and the pre-submission review checklist. Use for "написать пояснительную записку", "оформит...Votes: 0GitHub stars: 15
- DocumentsTurning written material into readable documents: markdown to a single-file HTML document, PR reviews and long-form reports, reading Word files, and diagrams. Use when the deliverable is a document rather than a screen: a spec, a report, a review, or a diagram.Votes: 0GitHub stars: 15
- Diagram Generatorgenerate, refine, validate, and render diagrams from natural language, notes, code snippets, schemas, tables, or existing diagram source. use for flowcharts, swimlanes, sequence diagrams, state diagrams, er diagrams, class diagrams, architecture/c4-style diagrams, dependency graphs, gantt charts, mind maps, user journeys, sankey-style flows, org charts, network graphs, and other visual models. supports mermaid by default, graphviz dot for complex graph layout, plantuml for uml-heavy engineeri...Votes: 0GitHub stars: 15
- Markdown Html OrchestratorUse when a user wants to convert any markdown file in their project into a single-file, lightly-interactive HTML — long-form documents (specs, plans, RFCs, reports, explainers), code reviews with diffs and severity-tagged annotations, or slide decks. Triggers on "convert this markdown to HTML", "make this an HTML file", "turn this into an interactive document", "render this report as HTML", "PR writeup as HTML", "slides from this markdown". Forks context to route to one of three converter sub...Votes: 0GitHub stars: 15
- Md DocumentConverts long-form markdown (specs, RFCs, reports, plans, explainers) into a single-file, lightly-interactive HTML document with sticky TOC, scrollspy, search filter, code-copy buttons, and design-system-driven brand tokens. Triggers when the markdown-html-orchestrator classifies an input as DOCUMENT, or when invoked directly via /cs:md-document. Reads the design-system config via config_loader.py and inlines the user's 12 derived CSS custom properties; refuses to render if onboarding hasn't ...Votes: 0GitHub stars: 15
- Md ReviewConverts a markdown PR writeup or code review (one with ```diff fenced blocks and severity-tagged > [!BLOCKER]/[!MAJOR]/[!MINOR]/[!NIT] callouts) into a single-file 2-column HTML review — unified-diff on the left, severity-tagged annotation cards on the right, top jump-nav listing every finding, mandatory named reviewer footer. Triggers when the markdown-html-orchestrator classifies an input as REVIEW, or when invoked directly via /cs:md-review. Refuses without explicit --reviewer (a code rev...Votes: 0GitHub stars: 15
- Read DocsReading .doc/.docx files via python-docx.Votes: 0GitHub stars: 15
- EmailEmail and inbox work: reading, searching, triaging and drafting replies through the host's mail integration, with triage rules and reply preferences kept in the memory tree under root/skill/email.Votes: 0GitHub stars: 15
- Email CoreWork with Gmail for the user through the connected Gmail integration: read, search, thread and send mail. The retired local SMTP/IMAP script (`gmail.py`) is gone — the integration is the only route. Can: send email with attachments, read the inbox with Gmail-query search (from:, subject:, is:unread, dates), open a thread, reply in-thread, pull attachments, create a draft, search contacts. Use this skill when the user asks to: - Send an email / write to someone / write to email - Check mail /...Votes: 0GitHub stars: 15
- Grill MeStress-test a plan or design by interviewing the owner about it: maximize question coverage — every assumption, every edge, every dependency, every implicit decision gets a question. Use whenever planning is needed — a plan or design is about to be locked, a large task is about to start — and on the direct ask "grill me" / "прожарь меня". Batched asks are the norm: cover everything, resolve branch by branch, record confirmed answers at once.Votes: 0GitHub stars: 15
- Ask NodumbLoad when the user asks to invent, discuss, or rework a product/interface: new feature, screen, flow, redesign, concept, UX, navigation principle, product strategy; asks 'what question to ask', 'how to design', 'where to start'; request immediately proposes a solution; options seem equivalent — even if they don't call it design/product task but ask 'invent' or 'redo'. Do not use for executing an agreed solution, targeted visual edit (color, size, font), and technical implementation without a ...Votes: 0GitHub stars: 15
- InterviewAsk one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.Votes: 0GitHub stars: 15
- NodumbLoad MANDATORILY when the cost of error exceeds the cost of a pause: choosing an approach/tool/library/architecture, request for advice/plan/assessment ("how to do/approach", "where to start", "advise", "is it worth it?"), planning refactoring/migration/rewrite/mass edit/redesign, repeat fix (didn't work), request with a ready solution. Triggers even if the user doesn't call it a fork/refactoring. For such requests, do not give advice/plan without loading the skill. NOT for trivialities, simp...Votes: 0GitHub stars: 15
- Jupyter NotebookUse when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.Votes: 0GitHub stars: 15
- Loop BreakerUse when a long task has drifted into a frame the agent built for itself and stopped serving the owner's goal, even though each step checks out — endless sub-proofs of one component, polishing one property past the point it matters, re-planning a plan instead of delivering, or building tools for the tools. The strongest case is an agent that wrote a requirement into its own plan, labelled it as the owner's decision, and now works to satisfy a goal nobody asked for. Also use when the owner ask...Votes: 0GitHub stars: 15
- Detect And BreakUse when a long task has drifted into a frame the agent built for itself and stopped serving the owner's goal, even though each step checks out — endless sub-proofs of one component, polishing one property past the point it matters, re-planning a plan instead of delivering, or building tools for the tools. Also use when the owner asks what the work is for, says it went in circles, or says the agent lost the point. Not for ordinary debugging, where repeated attempts at one bug are expected.Votes: 0GitHub stars: 15
- LoopsRepeating / autonomous work cycles: bounded loop mode ("loop 10 30m <prompt>"), unattended night-shift or heartbeat work with one-task-at-a- time focus, and a library of proven loop prompts. Use when the user asks for autonomous repeated execution — "keep going until done", "work in cycles", "[HEARTBEAT]", "while I sleep", cron-style self-runs. One contract; the parts under parts/ carry the mechanics.Votes: 0GitHub stars: 15
- Autonomous WorkScoped unattended execution for an assigned goal, night shift or heartbeat. Finish coherent units, verify results and keep resumable checkpoints. Respect task budgets and owner boundaries; stop when complete, blocked or asked, rather than inventing endless maintenance. Not an automatic mode for every session.Votes: 0GitHub stars: 15
- Loop LibraryDiscover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions, guardrails, and handoffs. Use when a user asks to analyze a codebase for potential loops, mine coding-thread history for work done more than once, turn repeated engineering work into a loop, find or recommend a published loop, create a recurring agent workflow or automation cadence, turn an outcome into a bounded copy-ready loop, or review an ...Votes: 0GitHub stars: 15
- LoopLoad when the user asks for a repeating autonomous mode: "loop 10 30m <prompt>", "loop 99 6666 <prompt>", "work cycle after cycle", "keep going until it's done", "continue on your own, don't stop", "find new solutions turn after turn", "infinite loop", "autonomous until the result". Each iteration is a full work cycle (re-state → prior knowledge → research → act → verify → checkpoint), the next iteration starts with a NEW angle or hypothesis, and the agent makes its own decisions. Stop: N ite...Votes: 0GitHub stars: 15
- McpWorking with MCP (Model Context Protocol) servers in Freebuff Desktop: discovering tools via native search_mcp_tools / call_mcp_tool, bridging stdio servers via _scripts/mcp-call.py, injecting .env secrets via the root `.env` exporter, repairing broken servers, and building new MCP servers from scratch or OpenAPI specs.Votes: 0GitHub stars: 15
- Mcp Auth HandlerHandle MCP auth keys, insert them when the user says to.Votes: 0GitHub stars: 15
- Mcp Batch Install And RepairBatch install/repair MCP servers, fix native bindings and env.Votes: 0GitHub stars: 15
- Mcp BuilderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when hand-writing MCP servers from scratch to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK) — no OpenAPI contract required. NOT when you already have an OpenAPI contract to convert (use mcp-server-builder).Votes: 0GitHub stars: 15
- Mcp RepairRepair broken MCP: a tool call fails, a server reports "Connection closed", tools that used to exist are gone, a project moved or its venv was rebuilt, junk breaks the stdio stream, or a server answers from the CLI but not from the session. Method: split client / server / environment first, then walk a 5-step ladder (real name → status → logs → CLI reproduction → stdio probe) and fix by category. Use for any "MCP is broken", "the browser tool is not called", "everything broke after the move".Votes: 0GitHub stars: 15
- Mcp UsageUsing MCP (Model Context Protocol) servers to extend agent capabilities. Read the configured MCP source for the current server list — never hardcode it. Use when: add MCP, MCP server, connect MCP, mcp tool, any MCP available, why is my MCP not working, MCP config.Votes: 0GitHub stars: 15
- MediaAudio, image and video work: text-to-speech through an OpenAI-compatible endpoint (with a Russian fallback), audio/video transcription, image generation and editing, quick ffmpeg screenshot demo videos (while HyperFrames handles motion graphics and promos), YouTube transcript/content extraction, and the 4-stage novel-* short-drama pipeline.Votes: 0GitHub stars: 15
- Image GenerationGenerate or edit images from text prompts, or edit an existing image through image-to-image fusion. Multi-provider script (`scripts/generate.py`): OpenAI, Gemini, Seedream, Qwen, MiniMax, LinkAI. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content. Runs on whichever provider key the workspace `.env` holds.Votes: 0GitHub stars: 15
- Novel Art给 AI 短剧出美术设定集（场景 + 叙事道具）：场景的设计意图、一致性锚点、光照时段变体、 空景提示词；道具的戏剧功能、状态变体、尺度参照、白底无手提示词。 产出 art.json + Markdown + 单页评审报告（含导出 JSON）。 为 AI 生成而设计，不是实拍——环境和道具都是生成资产，交付的是让它们跨集长一样的一致性方案； 11 道质量门全部由脚本确定性检查（锚点 3–5、无人无手、白底可抠、尺度短语、提示词英文……）。 有 novel-outline 的 outline.json 就用 seed 预填场景清单与出现集；出图走 codex 内置 $imagegen（可选）。 零依赖、零 API key，用当前会话额度。 Use when asked to 场景设定、出场景、环境设定集、场景一致性、scene bibles for AI short drama。Votes: 0GitHub stars: 15
- Novel Characters从小说或短故事里拆出角色表、人物画像、形象提示词、音色提示词， 并给每个角色出角色设定图（左半身像 + 右全身三视图 + 细节条），产出 JSON + Markdown + 可交互的 report.html。 报告语言可指定（--lang），默认中文，任意语言都支持； 出图风格可指定（--style），默认半写实，也可以出吉卜力动画风。 零依赖、零 API key，用当前会话额度；出图走 codex 内置 $imagegen（可选）。 Use when asked to 拆小说角色、分析人物、生成角色卡、character sheets from a novel。Votes: 0GitHub stars: 15
- Novel Outline把一本小说改编成短剧大纲五件套：改编说明、人物表、爽点表、分集梗概、资产清单， 产出 outline.json + Markdown + 单页评审报告（KPI 带、关键决策、爽点时间轴、调度矩阵、场景概览、质量门）。 13 道质量门全部由脚本确定性检查（角色分档上限、主场景上限随集数动态、爽点间隔≤3集、每集钩子悬念必填……），不靠模型自觉； 支持体检模式：贴一份现成大纲进来，只跑质量门给诊断。 零依赖、零 API key，用当前会话额度。 Use when asked to 改编大纲、短剧大纲、拆大纲、小说转短剧、adaptation outline。Votes: 0GitHub stars: 15
- Novel Script给 AI 短剧写剧本：把 novel-outline 的分集梗概落成结构化的场次 + 节拍流（动作节拍与台词行交替）， 台词逐句带说话人与语气，时长逐集按语速确定性折算。产出 script.json + Markdown + 单页评审报告 （时长仪表 / 分集剧本 / 场次总表 / 按角色聚合的台词本，含导出 JSON）。 剧本管戏，分镜管拍——本 skill 不分镜头、无镜号、不写生成提示词，那些是下一层分镜 skill 的活。 9 道质量门全部由脚本确定性检查（每集时长 ±15%、单句 ≤35 字、说话人合法、钩子悬念落纸、 每场至少一个动作节拍、爽点认领、角色/场景/光照/道具对账上游……）。 有 outline.json 就用 seed 预填每集骨架；给 --art 连光照状态一起对账。 零依赖、零 API key，用当前会话额度。 Use when asked to 写剧本、出剧本、台词、场次、写戏、screenwriting for AI short drama。Votes: 0GitHub stars: 15
- Ru Tts FallbackReliable Russian text-to-speech with voice. edge-tts (Microsoft, free Russian neural voice) flaps — returns empty stream or NoAudioReceived, ~1 in 3 requests fail with 30s+ pause; fallback gTTS (Google) often unavailable or rate-limited (429). Retry with timeout, empty answer = failure, synchronous call timeout via Thread(daemon)+join (NOT asyncio.to_thread — infinite hang), sha1 cache, clean error with cause. Triggers: "tts", "listen", "text-to-speech", "edge-tts", "gTTS", "No audio was rece...Votes: 0GitHub stars: 15