AI & ML

liam-gemini Bundle

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

liam-gemini Bundle

Help users actively steer technical or work conversations toward useful answers by checking their mental model, narrowing vague explanations, interrupting irrelevant tangents politely, clarifying terminology, and asking focused follow-ups. Use when an answer is confusing, overly broad, jargon-heavy, condescending, incomplete, off-topic, or fails to resolve the original question.

marwan562 Skill

Use this skill when guiding a contributor through this repository's contribution workflow. It follows CONTRIBUTING.md and repository conventions to help the agent clone, create skills, validate, and submit PRs correctly.

marwan562 Bundle

Use this skill to orchestrate complex tasks through parallel sub-agent collaboration — delegating research, implementation, and devil's-advocate review to specialized roles. Triggers on multi-agent, orchestration, delegate, complex refactors, and high-risk changes.

marwan562 Bundle

Use this skill when designing or reviewing secure multi-tenant AI agent platforms — tenant isolation for data, execution, memory, and billing. Triggers on multi-tenant, tenant isolation, RLS, SaaS, sandbox.

marwan562 Skill

Use this skill when creating or maintaining project documentation — README, API docs, guides, ADRs, or inline docs. The agent should first understand the existing codebase before writing, ensuring docs are accurate and not hallucinated.

matheus-sancha Skill

Interviews the user to design a Copilot Studio agent before any of it is built - role, users, tone, tasks, inputs, outputs, rules, escalation, knowledge, connected agents, scope and success criteria - then writes agent-brief.md. Use when the user wants to build a new agent, describes an agent idea in vague terms, or when another skill needs the agent brief.

matheus-sancha Bundle

Builds one custom Agent Skill for a Copilot Studio agent - instructions, bundled references and runnable scripts - and hands it back ready to upload. Use when the user wants to package a capability as a skill, needs an agent to produce a document in a fixed format, or asks how to turn a task into a reusable skill.

matheus-sancha Skill

Writes the Instructions for a Copilot Studio agent as XML-tagged sections - role, tone, tasks, instructions, rules, plus knowledge routing, tool use and connected agents where they apply. Drafts them early, revises them once tools and skills exist, then hands back instructions.md to paste into the Build tab. Use when the user wants to write, revise or review an agent's instructions.

matheus-sancha Skill

Routes the user through building a Copilot Studio agent - working out which stage they are at and which skill to load next, from first idea through instructions, tools, skills and tests. Use when the user wants to build an agent, does not know where to start, or asks what to do next.

matheus-sancha Skill

Works out which connectors, MCP servers, workflows and pre-built skills a Copilot Studio agent needs, and writes a tool-plan.md saying where to find each and why. Use when the user asks what tools or connectors their agent needs, how to connect it to another system, or what is already available.

naorpeled Skill

Help maintainers keep CI, release automation, and distribution channels healthy and consistent across a repository's workflows, packaging manifests, and agent-instruction files. Use when a maintainer needs to audit or improve CI coverage, releases, or multi-channel distribution.

pstanek Bundle

Rozpoznaje 200 skrótów-promptów zapisanych ze slashem, np. /blueprint, /crosssection, /hook10 i /premortem, i stosuje ich właściwy format do obrazu lub treści. Używaj, gdy użytkownik wpisuje taką komendę, pyta o jej działanie albo chce korzystać z katalogu komend.

quaylabshq Bundle

General-purpose plan advisor that assesses any plan file, launches a sub-agent to evaluate it, and auto-answers questions during planning and implementation workflows. Answers are displayed transparently showing both Q and A. Follows senior/lead engineer quality standards across front-end, back-end, and product decisions. Manual activation only via phrases like 'use plan-advisor' or 'activate plan-advisor'. State persisted in project memory directory.

quaylabshq Bundle

Structured implementation planning skill that enhances Claude's plan mode with mandatory questioning, research, problem decomposition, goal-driven criteria-first planning, and multi-agent verification before any implementation begins. Use when the user asks to plan a task, create an implementation plan, think through an approach, or when Claude enters plan mode. Plans are goal-driven: for code tasks, every step follows TDD (tests specified before implementation); for non-code tasks, every step has observable acceptance criteria defined before the approach. Plans are held to Google/NASA- grade quality standards and must pass independent verification by 3+ specialized sub-agents (requirements traceability, technical rigor, security & threat analysis) before presentation. Handles any domain — software engineering, design, business, research, content — by adapting its questioning depth, research strategy, and plan detail to the task's complexity and type. Always explores the codebase for code tasks; uses web rese

rimeinn Bundle

Start here for Rime configuration, schema, dictionary, deployment, debugging, or sync tasks. Provides the core engine flow, directory model, patching rules, redeploy checklist, and routing to specialized Rime skills. Load references/operations.md only for log locations, troubleshooting commands, or sync setup details.

rimeinn Bundle

Router and checklist for Rime spelling algebra and formatting rules. Use for xlit, xform, erase, derive, fuzz, abbrev, derive fourth-argument variants, Boost.Regex replacement syntax, speller/algebra, translator/preedit_format, translator/comment_format, and chord_composer algebra/output/prompt formats. Load references/full-reference.md for operator details and examples.

shanemullens Bundle

Conduct threat hunts in Splunk using the PEAK framework (Prepare, Execute, Act with Knowledge). Supports hypothesis-driven, baseline, and model-assisted hunts. Use when the user wants to threat hunt, investigate security anomalies, baseline data sources, detect adversary techniques, or map findings to MITRE ATT&CK.

shanemullens Bundle

Build Splunk Technology Add-ons (TAs) by parsing log samples, creating props.conf and transforms.conf configurations, loading data, and validating field extractions using the Splunk MCP server. Use when creating Splunk add-ons, parsing log files for Splunk, developing sourcetypes, or configuring field extractions.

ucoz-skills Bundle

Agent skill for preparing a uCoz site for work via MCP: create a new site or configure an existing one, ask clarifying questions for the scenario, choose available domain zones and site theme presets from the live uCoz interface, enable required modules, create/reuse uAPI and FTP credentials, assemble the official ucoz-mcp configuration, verify access, and hand off control to downstream task skills.

ucoz-skills Bundle

Translate and localize uCoz site content via MCP and uAPI: module materials and categories, design templates and global blocks, site menus, Page Editor pages, and associated images. Supports in-place translation and copy/migration with translation to another uCoz site.

yorrick Bundle

Monitor and steer Claude Code, Codex, or other terminal coding agents running in tmux panes. Use when asked to supervise, babysit, drive, or automate agent sessions through tmux, including reading agent output, detecting idle/blocked/context-boundary states, sending approved commands, clearing or compacting context at explicit boundaries, and coordinating multi-agent workflows without duplicating Claude/Codex-specific skill content.

rashadansari Skill

Reference knowledge on the EU AI Act (Regulation (EU) 2024/1689): risk tiers, obligations, compliance deadlines including the 2026 AI Omnibus changes, penalties, and scope. Activate when the user asks about the EU AI Act, AI regulation in Europe, high-risk AI compliance, AI transparency or watermarking obligations, GPAI model rules, or whether a product or feature falls under EU AI rules.

rashadansari Skill

Convert files, URLs, and documents to Markdown using the markitdown MCP server. Activate when the user asks to convert, extract, or read content from PDFs, Word docs, PowerPoints, spreadsheets, images, audio files, or any URL.

rashadansari Skill

Use the agent-memory MCP server to retrieve, verify, and store durable project knowledge and global user knowledge before and after non-trivial work.

rashadansari Skill

Best practices for writing skills, commands, and agents: descriptions, structure, token efficiency, frontmatter, tool scoping, and common authoring mistakes. Activate when creating or editing a SKILL.md, a command file, or an agent file, or when the user asks to "write a skill", "add a command", "create an agent", or "review this skill".

adeleempurpled290 Bundle

Use this skill when the user needs help with Vivado synthesis strategy selection, synthesis attribute configuration, synth_design option tuning, resource inference control (RAM/DSP/SRL/BRAM), hierarchy optimization (flatten_hierarchy, KEEP_HIERARCHY), OOC (out-of-context) synthesis, incremental synthesis, RTL linting, Block-Level synthesis (BLOCK_SYNTH), or any synthesis optimization decision. Trigger when the user mentions synthesis strategies, synthesis directives, synthesis attributes, resource mapping control, FSM encoding, retiming, or asks how to optimize synthesis results for area/timing/power. This skill provides decision-making knowledge — for TCL command execution, use vivado-tcl skill.

builderio Bundle

Open a user-provided URL in the host's built-in browser and use the page's MCP or WebMCP tools before browser UI automation for app communication or edits.

builderio Bundle

Open a running local app in Design overview mode as URL-backed iframe screens for visual editing, flow review, duplication, route-state exploration, and source handoff. Use when the user asks to inspect or edit a real local app in Design, including through a browser-capable host without an MCP connector.

builderio Bundle

Use in the BuilderIO/skills repo whenever adding, updating, publishing, documenting, validating, or wiring a public skill. Covers the repo-local skill files, root catalog docs, plugin metadata, @agent-native/skills dynamic install path, optional managed AGENTS/CLAUDE instruction blocks in ../agent-native/framework, and generated/synced Plan skill gotchas.

alphagbm Skill

Score and rank options contracts for any ticker using AlphaGBM's multi-factor scoring model (liquidity, IV attractiveness, Greeks balance, risk/reward). Returns scored option chains with the best contracts highlighted. Use when: evaluating which option to trade, finding the best strike/expiry, ranking options by quality. Triggers on: "score AAPL options", "best options for NVDA", "which TSLA call should I buy", "option chain for SPY", "rank META puts".

jasonkneen Bundle

Official Three.js API and TSL (Three.js Shading Language) reference for LLM code generation. Load when writing or debugging three.js / WebGL / WebGPU / custom materials / shaders / GLTF / advanced three APIs beyond basic game loop/controls. Prefer building-games for game correctness (loop, WASD, camera, orientation); use this skill for full API/TSL depth. Triggers on "three.js", "threejs", "WebGPU", "TSL", "NodeMaterial", "shader", "GLTF", "MeshStandard", "OrbitControls", "WebGLRenderer".

compozy Bundle

Dispatches scoped-write explorer subagents in parallel for general research and exploration of any codebase, topic, or domain. The operator passes --path (output directory), --agents (parallel count), and --prompt (research question). The parent scouts the territory first to divide work, dispatches N explorer subagents that each write one analysis file at <path>/analysis/NN_analysis_<slug>.md following a seven-section schema, then synthesizes <path>/analysis/summary.md. The skill self-contains the explorer subagent definition and prompts the operator to install it at .claude/agents/explorer.md when absent. Use when running parallel multi-area research that must produce written artifacts. Do not use for competitor-only research already covered by cy-research-competitors, single-file lookups answerable by Explore, or edits to existing code.

weorbitant Skill

Use when interrogating the codebase to understand an entity, field, or business concept. Traces data origin, mutations, validations, and relationships without assumptions. Use when user says "analiza entidad", "de dónde viene este dato", "analyze data model", "qué campos tiene", "quién genera este campo", or "explica esta entidad".

onetapstudiogames Skill

One guided pass: choose a handle, register through the market's coding-client JSON identity doors, store the key and eight recovery codes in the OS vault, connect this host's own MCP door, and offer the daily visit. Use when the user asks to set up, register, or open a store at 1F3EA, or types /1f3ea-marketplace:setup.

onetapstudiogames Skill

Add or repair this coding agent's own MCP connector and verify it with one authenticated read, or (connect chat) mint a pairing code for a chat twin like claude.ai or ChatGPT. Use when the user asks to connect, reconnect, or pair a chat twin, or types /1f3ea-marketplace:connect.