AI & ML

biswaviraj Bundle

Use when CI is failing on a branch/PR and the user wants it driven back to green — "fix the failing CI", "CI is red, sort it out", "make the checks pass", "loop until CI is green". Pulls the real error from the failing GitHub Actions logs, reproduces it locally, fixes the confident failures, pushes once, and re-watches until green. The red-CI twin of reviewloop.

biswaviraj Bundle

Use when the user wants a daily standup update written for them — "what did I do yesterday", "write my standup", "summarize my work since Friday", "what did I ship this week". Pulls the user's own merged/opened/reviewed PRs across the org and renders a paste-ready Done / Today / Blockers block.

biswaviraj Bundle

Use when a PR has feedback from MORE than one reviewer — any mix of bots (Greptile, CodeRabbit, Copilot, linters) and human teammates — and the user wants every reviewer driven to a clear state, not just one specific bot. Use when the user says "clear all the reviews", "address every reviewer", "loop until the PR is clean", or wants bot reviews re-triggered and re-checked automatically.

ceobefa333 Bundle

Create, redesign, and iteratively improve publication-ready scientific model diagrams, architecture figures, method frameworks, neural-network pipelines, and research infographics from papers, sketches, screenshots, or textual model descriptions. Use when Codex needs to analyze scientific logic, preserve equations and dimensions, design a coherent layout and color system, generate or edit a reference image, correct scientifically misleading icons or plots, or produce a structured prompt/specification for later editable vector or Visio reconstruction. This skill covers the pre-Visio design and prompting phase, not GUI drawing execution.

kaelio Bundle

Installs and configures ktx, the open-source context layer for data agents — runs ktx setup non-interactively with hidden CLI flags, configures database connections and embeddings, installs agent integration, and verifies readiness. Use when the user asks an agent to add ktx to a project, connect data sources, install agent rules, ingest schema, or troubleshoot a local ktx install.

kaelio Skill

ktx's knowledge base - wiki pages for durable, reusable business knowledge. Covers capture workflow for user preferences, metric definitions, organizational conventions, and cross-references between wiki pages and semantic-layer sources. Loaded by the post-turn memory-agent only. The research agent reads wiki via `wiki_read`/`wiki_search` but does not write it.

konete326 Bundle

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

lazily01 Bundle

Product manager that decomposes requirements into actionable tasks with priorities and dependencies

mohamed-el-sharqawy Bundle

Turn any coding agent into a structured personal tutor with a markdown knowledge vault. Interviews the learner to build a personal learning profile (how they think, which explanations they receive best, tone and pace preferences), builds a phased plan shaped by that profile, writes complete lesson notes in the learner's own style (with diagrams and self-check questions), quizzes with honest non-inflated feedback, schedules spaced-repetition reviews, and tracks progress on a dashboard. Use when the user wants to learn a new subject in depth, continue a learning plan, be tutored or quizzed, or seriously study any topic.

mohamed-el-sharqawy Skill

Spaced-repetition review sessions and retention tracking for subjects learned with the agent-tutor skill. Recall-first practice over lesson notes, adaptive FSRS-style interval scheduling (uncapped by default), honest retention verdicts, and a mixed mini-quiz per session. Use when the user wants to revise or practice old topics, check what they remember, or when the dashboard shows notes up for review.

nvidia-ai-blueprints Bundle

Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.

nvidia-ai-blueprints Bundle

Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).

noesisvision Skill

Design, refactor, analyze, and review code by applying the principles and patterns of tactical domain-driven design. Triggers on: domain modeling, aggregate design, 'entity', 'value object', 'repository', 'bounded context', 'domain event', 'domain service', code touching domain/ directories, rich domain model discussions.

pandelisz Bundle

Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.

razshy Skill

Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing, models, streaming), and Claude.ai (Pro vs Team vs Enterprise plans, feature limits). Trigger this even for coding tasks that use the Anthropic SDK, content creation mentioning Claude capabilities or pricing, or LLM provider comparisons. Any time you would otherwise rely on memory for Anthropic product details, verify here instead — your training data may be outdated or wrong.

szoloth Bundle

Expert prompt engineering for AI systems. Use when the user wants to write or review prompts for AI, create instructions for AI systems, build system prompts, review or improve existing prompts, optimize AI instructions, or create any form of written communication intended for AI consumption (Claude, GPT, or other LLMs).

taosheng777 Bundle

个人投资分析（双档）。常规档：主线论证（提名答辩/主线体检/退潮复核）、单标的与板块速查、持仓体检，给状态层+信号判定+纪律护栏+危险信号。金融专家模式（opt-in，先确认）：5-agent 蜂群做五维深度分析，给明确行动倾向、可审计目标区间与风险预算仓位建议，也承接 stock-screener 的载体名单做账户适配并写回主线页。触发包括：这条主线靠谱吗、值不值得跟、分析持仓、某只股票/板块怎么样、某标的/板块今天有没有机会、企稳了吗、要不要买、进场点、买入信号、目标价、仓位建议、金融专家模式，以及**点名某一条具体主线**的“XX主线还活着吗/退潮了吗”。**不点名主线的泛问（“主线还活着吗”）和任何日更「复盘」都归 stock-daily，不进本 skill。**

verasuperhub Bundle

Full CFA skill for measurement-model evaluation. Extends the initial CFA fit with reliability, convergent/discriminant validity, alternative-model comparison, modification-index review, subgroup invariance testing, and manuscript-ready methods/results. Trigger after vera-data-cfa-reviewing completes and its PART 0–2 artifacts are present (see ../../CROSS-SKILL-INTERFACE.md). If invoked directly without those artifacts, halts and prompts the user to run testing first or supply equivalent PART 0–2 code.

verasuperhub Bundle

Full SEM analysis skill. Extends the initial structural model with indirect effects, alternative-path comparison, multigroup testing, residual review, and manuscript-ready methods/results. Trigger after vera-data-path-reviewing completes and its PART 0–2 artifacts are present (see ../../CROSS-SKILL-INTERFACE.md). If invoked directly without those artifacts, halts and prompts the user to run testing first or supply equivalent PART 0–2 code.

prime-radiant-inc Skill

Use when designing, running, or diagnosing Evener tool-fluency experiments for a real built-in, plugin, or newly added tool. Covers probe manifests, model comparisons, semantic oracles, and interpreting fluency failures without ad-hoc transcript parsing.

prime-radiant-inc Skill

Use when a surface parses untrusted or model-generated input — a wire protocol, tool-call JSON, upstream SSE, an HTTP body — or after a parser/dispatch bug, to fuzz that surface and turn any deterministic failure into a permanent, flake-guarded regression test. Covers picking a seam, choosing oracles beyond "no panic", the portable promoter/schema-generator core, and the safety bounds that keep a fuzzer from executing dangerous handlers.

prism-shadow Bundle

Answer engineering-portfolio review tasks that run against the shared read-only work-item API (endpoints + query token in environment_access.md). Covers three task families that share one data model: (A) quarterly portfolio-mix vs target, (B) reliability/security SLA aging & breach, and (C) release-readiness rollups. Use when a task asks for closed-work category mix, SLA overdue/aging/escalation, or a ship decision, and provides an answer_template.json to fill.

pyvista Bundle

Sweep recently merged upstream VTK merge requests, triage the bug fixes and features that matter to cvista's shipped modules, and land each as its own PR linked back to the original MR. Use when asked to check upstream VTK for backports, catch cvista up on upstream fixes, or port a specific VTK MR. Drives the vtk-backport-engineer agent for the per-MR landing work.

rysweet Skill

Model Evaluation Benchmark Skill

sap-samples Skill

Query @cap-js/mcp-server before writing CDS entities, types, aspects, services, or CAP service handlers. Triggers on schema and service files in db/ and srv/.

sap-samples Skill

Query @ui5/mcp-server before writing SAPUI5 controllers, XML views, control APIs, or model bindings. Triggers on views and controller extensions in app/.

sap-samples Skill

Query @sap-ux/fiori-mcp-server before writing CDS annotations, Fiori Elements config, or manifest.json. Triggers on annotation files in app/ and manifests.

secondorderai Bundle

Use this skill when the user needs structured planning, complex analysis, difficult tradeoff decisions, or troubleshooting under uncertainty and the agent should apply a compact meta-thinking loop with task classification, a meta-mode gate, plan extraction, critique, and concise trust signals. Prefer it when surfacing confidence, limitations, and context gaps will materially improve the answer. Do not use it for simple factual or one-step requests where extra framing would add friction without improving the result.

secondorderai Bundle

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.

siglernir-ai Bundle

Turn Codex and Claude Code into an accountable engineering pair on one Git task: one agent leads or implements, a different agent challenges and reviews, rejected work can return for bounded correction, and neither ships alone. Durable project-local state preserves scope, decisions, evidence, and the next actor across windows and CLI turns; exact-scope and fail-closed checks stop unsafe or inconsistent progress. Stable capability profiles can resolve to replaceable local model mappings without freezing provider model names, while the user retains approval over sensitive actions. Roles can be swapped with explicit user approval. Use when the user explicitly selects or names codex-claude-handoff, requests cross-agent implementation and independent review, setup, diagnosis, role reassignment, or the full supervised workflow. Do not trigger for ordinary project tasks. On first use, request approval before installing the bundled protocol.

siglernir-ai Bundle

Turn Codex and Claude Code into an accountable engineering pair for one supervised Git task, with durable local state, configurable roles, independent review by a different agent, bounded correction after rejection, exact-scope verification, fail-closed stops, and user approval gates. Use only when the user selects codex-claude-handoff through /skills, mentions $codex-claude-handoff, names codex-claude-handoff, or explicitly requests the full cross-agent workflow; do not trigger for ordinary project tasks.

siglernir-ai Skill

Turn Codex and Claude Code into an accountable engineering pair on one Git task: one agent leads or implements, a different agent challenges and reviews, rejected work can return for bounded correction, and neither ships alone. Durable project-local state preserves scope, decisions, evidence, and the next actor across windows and CLI turns; exact-scope and fail-closed checks stop unsafe or inconsistent progress, while the user retains approval over sensitive actions. Roles can be swapped with explicit user approval. Use when the user explicitly selects or names codex-claude-handoff, requests cross-agent implementation and independent review, setup, diagnosis, role reassignment, or the full supervised workflow. Do not trigger for ordinary project tasks. On first use, request approval before installing the bundled protocol.

signalpilot-labs Skill

Load when task involves dbt model versioning, creating v2 of a model, or backward-compatible model changes. Covers versions YAML config, defined_in, latest_version, and ref() with version pins.

skogai Skill

Use when performing JSON transformations, manipulating nested JSON structures, filtering arrays, extracting values, validating JSON schemas, or composing multi-step JSON operations. This skill provides 60+ schema-driven jq transformations optimized for AI agent discoverability.

sones3 Bundle

Triage GitHub issues through a label-based state machine. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

srid Bundle

Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. Use this skill whenever reviewing a PR, diff, or code snippet for accidental complexity — particularly when the code was generated by an AI coding assistant and line-by-line review isn't feasible. Also use when the user asks about complecting, simplicity vs. easiness, structural coupling, or concept deduplication. Trigger on phrases like "is this simple", "does this complect", "review for complexity", "structural analysis", or any reference to Hickey, Simple Made Easy, or grey-box review.