AI & ML

svengoerdes Skill

Generate a resumable shell script that implements ticket-NN.md files sequentially through OpenCode, Claude Code, or Pi. Defaults to OpenCode. Use after to-tickets when the user says "batch implement", "implement tickets", "run tickets through an agent", "generate implement script", or "create orchestration script".

steffencarlsen Bundle

Use for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when they refer to Codex—and for OpenAI APIs/products and ChatGPT Work. Also use for model choice/migration, prompting, SDKs, Responses, Realtime, agents, evals, and Chat/Work/Codex comparisons. Do not use for generic app/software tasks that merely mention Codex.

steffencarlsen Skill

Guide for diagnosing and improving MSBuild project evaluation performance. Only activate in MSBuild/.NET build context. USE FOR: builds slow before any compilation starts, high evaluation time in binlog analysis, expensive glob patterns walking large directories (node_modules, .git, bin/obj), deep import chains (>20 levels), preprocessed output >10K lines indicating heavy evaluation, property functions with file I/O ($([System.IO.File]::ReadAllText(...))), multiple evaluations per project. Covers the 5 MSBuild evaluation phases, glob optimization via DefaultItemExcludes, import chain analysis with /pp preprocessing. DO NOT USE FOR: compilation-time slowness (use build-perf-diagnostics), incremental build issues (use incremental-build), non-MSBuild build systems. INVOKES: binlog MCP server tools (evaluations, evaluation_global_properties, evaluation_properties, imports, properties); falls back to dotnet msbuild -pp:full.xml for preprocessing, /clp:PerformanceSummary.

steffencarlsen Skill

Guide for optimizing MSBuild build parallelism and multi-project scheduling. Only activate in MSBuild/.NET build context. USE FOR: builds not utilizing all CPU cores, speeding up multi-project solutions, evaluating graph build mode (/graph), build time not improving with -m flag, understanding project dependency topology. Note: /maxcpucount default is 1 (sequential) — always use -m for parallel builds. Covers /maxcpucount, graph build for better scheduling and isolation, BuildInParallel on MSBuild task, reducing unnecessary ProjectReferences, solution filters (.slnf) for building subsets. DO NOT USE FOR: single-project builds, incremental build issues (use incremental-build), compilation slowness within a project (use build-perf-diagnostics), non-MSBuild build systems. INVOKES: binlog MCP server tools (expensive_projects, expensive_targets, project_target_times); falls back to dotnet build -m, dotnet build /graph, binlog replay + grep.

steffencarlsen Skill

Guide for optimizing MSBuild incremental builds. Only activate in MSBuild/.NET build context. USE FOR: builds slower than expected on subsequent runs, 'nothing changed but it rebuilds anyway', diagnosing why targets re-execute unnecessarily, fixing broken no-op builds. Covers 8 common causes: missing Inputs/Outputs on custom targets, volatile properties in output paths (timestamps/GUIDs), file writes outside tracked Outputs, missing FileWrites registration, glob changes, Visual Studio Fast Up-to-Date Check (FUTDC) issues. Key diagnostic: look for 'Building target completely' vs 'Skipping target' in binlog. DO NOT USE FOR: first-time build slowness (use build-perf-baseline), parallelism issues (use build-parallelism), evaluation-phase slowness (use eval-performance), non-MSBuild build systems. INVOKES: binlog MCP server tools (overview, search, target details); falls back to dotnet build /bl, binlog replay with diagnostic verbosity.

steffencarlsen Skill

Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath. Only activate in MSBuild/.NET build context. USE FOR: builds failing with 'Cannot create a file when that file already exists', 'The process cannot access the file because it is being used by another process', intermittent build failures that succeed on retry, missing outputs in multi-project builds, multi-targeting builds where project.assets.json conflicts. Diagnoses when multiple projects or TFMs write to the same bin/obj directories due to shared OutputPath, missing AppendTargetFrameworkToOutputPath, or extra global properties like PublishReadyToRun creating redundant evaluations. DO NOT USE FOR: file access errors unrelated to MSBuild (OS-level locking), single-project single-TFM builds, non-MSBuild build systems. INVOKES: binlog MCP server tools (overview, projects, evaluations, properties, double_writes); falls back to dotnet msbuild binlog replay + grep when the MCP is unavailable.

steffencarlsen Bundle

Use when a request involves OSRS Wiki pages or sections, items, shops, drops, quest requirements or readiness, monster forms, live prices, player state, loadouts, or DPS, and before any OSRS Wiki MCP tool call or Wiki scope-boundary answer.

steffencarlsen Skill

Diagnose MSBuild build performance bottlenecks using binary log analysis. Only activate in MSBuild/.NET build context. USE FOR: identifying why builds are slow by analyzing binlog performance summaries, detecting ResolveAssemblyReference (RAR) taking >5s, Roslyn analyzers consuming >30% of Csc time, single targets dominating >50% of build time, node utilization below 80%, excessive Copy tasks, NuGet restore running every build. Covers timeline analysis, Target/Task Performance Summary interpretation, and 7 common bottleneck categories. Use after build-perf-baseline has established measurements. DO NOT USE FOR: establishing initial baselines (use build-perf-baseline first), fixing incremental build issues (use incremental-build), parallelism tuning (use build-parallelism), non-MSBuild build systems. INVOKES: binlog MCP server tools (overview, errors, search, items, properties); falls back to dotnet msbuild binlog replay + grep/cat when the MCP is unavailable.

steffencarlsen Skill

Analyze MSBuild binary logs to diagnose build failures. Only activate in MSBuild/.NET build context. USE FOR: build errors that are unclear from console output, diagnosing cascading failures across multi-project builds, tracing MSBuild target execution order, and generally any MSBuild build issues. Requires an existing .binlog file. DO NOT USE FOR: generating binlogs (use binlog-generation), non-MSBuild build systems. INVOKES: binlog MCP server tools (overview, errors, search, items, properties); falls back to dotnet msbuild binlog replay + grep/cat when the MCP is unavailable.

sergeyitaly Bundle

Reference for the Claude API and Anthropic SDK (models, pricing, streaming, tool use, MCP, agents, caching, migration). Use when the prompt names Claude/Anthropic or for unstated LLM/agent tasks; see "When to use" below for skip rules.

sergeyitaly Skill

Build, wire, and debug a stdio MCP server bundled inside a VS Code extension (claude-skills-deployer pattern). Covers server code, allow-list security, MCP content-response format, premature-exit fix, deployment to ~/.claude/mcp-servers/, registration in ~/.claude.json for Claude/Cursor/Kiro, auto-start on activation, and health dialog integration. Use when adding a new MCP server or debugging "no output" / early-exit failures.

sergeyitaly Skill

Read MCP efficiency hints and fix token-waste patterns. Use when asked about MCP efficiency, token waste, redundant tool calls, or "why is my session so token-heavy". Covers mcp-agent-hints.md, common waste patterns, manual efficiency review, and lazy-mcp.

sergeyitaly Skill

Understand how the prompt-context-watch.js hook controls context grounding and practical focus injection. Use when asked "how does context grounding work", "how do I disable prompt injection", "what does practical focus do", "configuring session size warnings", or when modifying this extension's hook system.

heweidong-ecco Bundle

Grill yourself before acting. Use when a task is multi-step, ambiguous, or irreversible — before touching anything, surface the assumptions you filled in and cite what each one rests on; when you catch yourself about to say "stop and wait", say what you still need instead; and never skip, alter, or silently proceed past what you were actually asked. Skip it for tasks the user can verify at a glance.

laplusdestiny Skill

Helps the agent interact with Vercel CLI to manage deployments, check build/runtime logs, pull environment variables, and inspect deployment status.

laplusdestiny Skill

Helps the agent perform standard Git operations like branch management, staging, committing, pushing, and pulling changes safely, with support for Conventional Commits and strict rules on destructive actions.

sergeyitaly Skill

At the start of a new session, do a cheap check for new or updated official Anthropic skills (github.com/anthropics/skills) and automatically add or update them in skills_library/ (no user prompt). Also use on explicit request ("check for official skill updates", "sync official skills").

sergeyitaly Skill

AUTO-START on new agent session/window (injected by profile-init-watch for Claude, Cursor, Kiro, Copilot) and on new tasks — analyze the prompt and repo, write task-skill-proposals.json, then read top proposed skills before other work. Also register user disagreement into skill-feedback.jsonl when the user says no, not, wrong, stop, or disagrees with agent output.

jordyzomer Skill

Externalize working memory and logical state into the lemmalog Datalog engine (MCP). Use for ANY multi-step task where state should outlive one context window or span agents: long investigations, debugging sessions, audits, multi-agent searches, systematic explorations, planning with many interdependent constraints, anything needing provenance for its conclusions. Trigger when lemmalog_ MCP tools are available and the task involves accumulating verified facts, tracking hypotheses or status over time, or repeatedly re-deriving the same relationships.

aartiq Skill

Triage a ServiceNow incident or a queue of incidents using NowAIKit MCP tools — gather context, find similar past incidents, suggest a resolution, set priority, and assign. Use when the user asks to triage, investigate, prioritize, or work an incident (by number or as a batch).

aartiq Skill

Audit ServiceNow CMDB health using NowAIKit MCP tools — find duplicate, orphaned, and stale CIs, score completeness, and propose remediation. Use when the user asks to check CMDB health, data quality, CSDM conformance, or clean up the CMDB.

laplusdestiny Skill

Collaborates with the Antigravity CLI (`agy`) as either an independent second opinion or a task delegate for work Antigravity is better suited for — large-context/codebase-wide analysis, multimodal reading of screenshots/mockups/PDFs, browser-driven UI verification, or large parallel multi-agent task decomposition. Use only when the user explicitly asks for Antigravity's opinion or asks to delegate/hand off a task to it, or when Claude identifies a strong fit and proposes delegating (still confirming with the user before anything that changes files).

ai-scarlett Bundle

Convert natural-language or structured briefs into plans, source, audits, packages, releases, DSH STORE catalog candidates, public artifacts, installations, or verification for standard non-destructive DeepSeek Harness (DSH) plugins. Use for DSH/Cordis Host plugins, model Tools and card contracts, Browser Clients, Skill adapters, ApiProxy bridges, marketplace listing failures/submissions, Profile lifecycle managers, fixed releases, public distribution, and third-party compatibility requests. Normalize goals, problems, capabilities, data, mutations, Tool presentation, UI, external dependencies, constraints, delivery, marketplace intent, and acceptance; apply safe defaults; enforce host, card, and marketplace preflight, quantified gates, disposable tests, official CLI-only package changes, licensed immutable distribution, separate repository/catalog/Profile acceptance, and evidence-based status.

yoruuuchan Bundle

将一句视频创意或既有视觉参考推进为风格锁定、分镜、AI 参考图、Blender MCP 建模与摄像机、低负载可断点渲染、只读渲染与剪辑监控页、DaVinci Resolve MCP 或脚本 API 剪辑，以及经过媒体校验的 4K 30 fps H.265 Rec.709 MP4。支持自主创作、共同创作和参考复刻三种模式。用于制作 3D 短片、竖屏氛围片、产品或概念视频，把想法、参考图、Blender、达芬奇串成可重复工作流，或为长时间渲染与剪辑建立安全进度页面时。

yuuhann1999 Skill

Create, find, inspect, update, or delete Codex Storyboard projects directly through MCP. Use when the user asks Codex to write a new video script or storyboard into the local storyboard app, add or revise shots, rename a project, change its aspect ratio, find an existing project, or delete one without browser automation.

kanthalas Skill

Use when the user wants to create, scaffold, or review a new Agent Skill (a SKILL.md-based reusable capability for Claude, Cursor, Codex, or any agentskills.io-compliant agent). Not for general questions about what skills are, and not for writing regular prompts or one-off instructions.

zeromountain Bundle

Install and run Orca multi-model role orchestration: Claude Fable 5.1 (architect), Claude Opus 5 (reviewer), GPT-6 Astra via Codex (executor), Grok 4.6 (thrifty), Antigravity Gemini 3.7 Flash Medium (ui, fallback on rate/session limits). Raster image generation/edit routes to executor with Codex $imagegen; if the image brief is ambiguous, ask the user first. Also runs a four-model idea debate (Claude, Codex, Grok, Gemini propose, critique anonymously, and converge on a niche) for brainstorming and idea refinement. Use whenever the user wants model role separation in Orca Agent IDE, multi-model routing, role workers, bootstrap roles, dispatch by role, plan-execute-review DAGs, image generation / imagegen / 이미지 생성, limit failover to agy/Gemini Flash, multi-model debate, idea debate, or mentions Fable/Astra/Grok role split, orca-role-orchestration, /orca-role-orchestration, "역할 오케스트레이션", "모델별 역할 분리", "architect executor thrifty", "fallback Gemini Flash", "아이디어 토론", "브레인스토밍", "아이디어 구체화", or "니치 찾기". Prefer this s

kimi0hhhh Bundle

市场调研 SOP（多 Agent 并行）：界定命题 → 三路并行调研 → 财务建模 → 综合裁决 → 交付。当用户提出「做市场调研」「调研某行业/品类/闭环」「评估这个生意能不能做」「算算投入和回本」「可行性分析」这类需求时加载；即使用户没说「调研」二字，只要目标是为商业决策收集市场证据并给出可行性结论，也应触发。单点事实问答与纯技术方案调研不加载本 SOP。

ayush-helfie Bundle

Multi-agent, evidence-driven senior review of Android/Kotlin pull requests. Use this whenever someone shares a mobile-repo PR link, asks for a code review of Android, Kotlin, Jetpack Compose, coroutines, Flow, Room, WorkManager, Hilt/Dagger, or Gradle changes, asks "can you look at my PR", "review this diff", "is this ready to merge", or wants a second opinion on mobile architecture, naming, or scope - even when they never say the word "review". Also use it when asked whether a mobile PR is correct, complete, necessary, idiomatic, or consistent with the existing codebase.

notorious-d-e-v Bundle

Delegate implementation, debugging, tests, and exploration from GPT-6 Astra to GPT-5.6 Sol in Codex, with task-appropriate effort. Skip in other-model sessions.

samraddhashrivastavatech Skill

Operate, build, validate, test, debug, and administer n8n through n8n-full-mcp and the official n8n MCP. Use for workflows, nodes, expressions, executions, credentials, data tables, agents, projects, folders, tags, variables, triggers, webhooks, packages, online/local/offline n8n, and capability diagnosis. Requires exact user approval immediately before every consequential operation.

samraddhashrivastavatech Bundle

Universal Android phone/device control through the android-control MCP server. Lists, connects, and drives Android devices — taps, swipes, typing, keys, screenshots, screen recording, UI hierarchy, apps, files, intents, shell, messaging, multi-device fleets, recovery, and the remote-touchpad companion. Use for ANY request about an Android phone, tablet, emulator, or adb device.

samraddhashrivastavatech Skill

Blender Animation Knowledge Graph — complete standalone ecosystem for imagining, designing, modeling, sculpting, lookdev, rigging, animating, simulating, and finishing any character/creature/world/film in Blender 4.x. Use when user wants to build/model/rig/animate/render a character, creature, animation, short film, world, grease-pencil, or asks blender, modeling, sculpting, topology, UV, materials, hair, cloth, rigging, animation, simulation, VFX, cinematography, lighting, render, compositing. Routes to 19 BAKG skills via bakg-orchestrator.

ilog3 Skill

Use for education program evaluation, curriculum evaluation, platform/tool evaluation, teacher training evaluation, school reform evaluation, and implementation/effectiveness studies. Produces logic model, evaluation questions, indicators, data plan, analysis plan, and evaluation-report/paper structure.

ilog3 Skill

Use when identifying independent variables, dependent variables, mediators, moderators, controls, constructs, indicators, instruments, and operational definitions from education research topics, papers, PDFs, Zotero libraries, survey plans, or literature review notes. Supports Elicit-style extraction, PDF RAG, and structured variable tables.

ilog3 Bundle

Design, conduct, analyze, write, and appraise qualitative social-science research using Chen Xiangming's 质的研究方法与社会科学研究. Use when aligning qualitative questions with epistemology and methods; building an interactive design; choosing purposive samples; negotiating researcher–participant relations and field entry; conducting interviews, focus groups, observation, or artifact analysis; coding and building contextualized interpretations or grounded theory; writing thick, reflexive accounts; or evaluating validity, inference, ethics, action research, and qualitative–quantitative combinations. Keep claims situated, make the researcher's role visible, and do not turn flexible inquiry into an unprincipled or mechanical recipe.