Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Analyze the completeness of a plan, report, or change proposal and its impact assessment on the project. Use when: the user provides a document (plan, technical debt assessment, change proposal, RFC, ADR, security report, etc.) and asks to analyze its quality, completeness, or potential risks. Trigger: /custom-skills-plan-analyze @file path — applies whether the request is made in Chinese or English.
Generates Dart models from a JSON structure using json_annotation and equatable. Use this skill when the user provides a JSON object and wants the corresponding Dart model classes generated, or asks things like "generate a Dart model for this JSON", "create a model from this response", "dart model from json". Always use this skill when the user provides JSON and needs Dart model output.
Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing, hanging, slow, producing weird metrics, has crashed, or asks to debug, diagnose, troubleshoot, or investigate a training issue.
Systematic debugging methodology with root cause analysis. Phases: investigate, hypothesize, validate, verify. Capabilities: backward call stack tracing, multi-layer validation, verification protocols, symptom analysis, regression prevention. Actions: debug, investigate, trace, analyze, validate, verify bugs. Keywords: debugging, root cause, bug fix, stack trace, error investigation, test failure, exception handling, breakpoint, logging, reproduce, isolate, regression, call stack, symptom vs cause, hypothesis testing, validation, verification protocol. Use when: encountering bugs, analyzing test failures, tracing unexpected behavior, investigating performance issues, preventing regressions, validating fixes before completion claims.
Lightweight ADR decision log that auto-captures plans. Use when planning a new feature, proposing architecture changes, tracking implementation decisions, exiting plan mode, or asking 'should I write a decision log'. Includes a Claude Code hook for automatic capture on ExitPlanMode.
Build, inspect, edit, verify, and export dependency-free DesainPakeAI prototype workspaces with the dpai CLI. Use for prototype pages, layouts, components, design tokens, DESIGN.md guidance, visual-review retrieval, canvas working state, or single-HTML export. Do not use for the TanStack host UI or legacy prototype templates.
Design patterns with Java examples - classic (Factory, Builder, Strategy, Observer, Decorator, Adapter) and enterprise/microservices (Saga, Outbox, CQRS). Use when user asks about patterns, designing extensible components, or distributed transaction strategies.
Designs modular high-level architectures from functional requirements and produces design documents for each module. Use when designing a new system, creating architecture documentation, or producing module-level design specs with integration contracts and test specifications.
Build, plan, review, and document pyRevit extensions. Use when Codex needs the pyRevit development workflow, templates, prompts, checklists, or scripts for creating or updating pyRevit commands in this repo. Pair with a version-specific Revit skill (e.g., 2023/2024/2025) for API constraints.
Use this skill whenever the user is writing, debugging, or building Python algo trading code using the Dhan-Tradehull library (pip install Dhan-Tradehull). Triggers on: any mention of Tradehull, Dhan_Tradehull, tsl., get_ltp_data, order_placement, ATM_Strike_Selection, get_option_chain, get_historical_data, super order, forever order, conditional trigger, OI scalping, options strategy using Dhan, place order Dhan Python, Tradehull authentication, get_positions, get_holdings, enable_pnl_based_exit, get_option_greek, margin_calculator, or any TradeHull course code task. Always use this skill before writing any Tradehull code — even for simple snippets — to ensure correct method signatures and patterns.
Design safe Django and PostgreSQL indexes from measured query plans, including B-tree, composite, covering, partial, expression, GIN/JSONB, BRIN, and concurrent migration patterns. Use when a Django query plan suggests missing or mismatched indexes, a production table needs an index without write downtime, or existing indexes need review.
Create EARS (Easy Approach to Requirements Syntax) formal requirements - Layer 3 of the SDD flow, translating PRD features into atomic, testable WHEN-THE-SHALL-WITHIN statements. Use after BRD and PRD exist. Single-document authoring primitive; for end-to-end or batch generation the autopilot (`doc-ears-autopilot`) drives this skill.
Generate a standalone bug report that another developer can use to reproduce, investigate, and fix an issue. Use when the user says 'file a bug', 'write a bug report', 'report this issue', or asks to document a defect for handoff.
How to land a formal cherry-pick of a merged PR for the flutter/flutter repo stable or beta channel. Only use for flutter/flutter landed pull requests. Only use when the cherry pick request is into "stable", "beta" or a branch that has the format with flutter-<major>.<minor>-candidate.0
Repair persisted fix-now findings in compatible atomic batches: root-cause fixes, green gate, commit/push, and per-row `folded: yes` updates. Never reclassify or substitute backlog notes. Triggers: "fold-findings", "fix the review findings", "repair audit blockers".
Analyze and address unresolved feedback on a GitHub pull request. Use when the user has received PR review comments and wants to systematically address each piece of feedback, or when the user mentions PR feedback, review comments, or addressing reviewer concerns.
Design and implement service layer classes for Frappe Framework v15 with proper business logic separation. Triggers: "create service", "add service layer", "frappe service", "business logic", "/frappe-service". Generates service classes with validation, orchestration, and integration patterns.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
The drum sounds. Eight animals gather — each a fresh subagent with its own context, model, and focus. The conductor orchestrates, verifies gates, and ensures every animal actually does its job. Use when building a full feature from exploration to documentation.
Generate a self-contained JavaScript server runtime and registration metadata for an MCP codeful tool. Use when the user asks to create a codeful MCP tool, generate server logic for an MCP tool, write a runTool function, build a Dataverse-backed MCP tool, or pair MCP server logic with an MCP App widget
Open a GitHub pull request (draft or ready for review) from the current branch using the gh CLI. Use this whenever the user wants to open, create, raise, submit, or "ship" a PR / pull request, or says things like "open a PR", "PR this branch", "put this up for review", or invokes /gh-pr — even when they don't specify the base branch, title, or description. Handles pushing the branch, writing the title and body from the actual diff, respecting the repo's PR template, linking issues, and dropping to --draft for unfinished work.
[Required reading · Mandatory] Mandatory usage guidelines for the Giime component library. You must read this skill before writing or modifying any frontend code that involves UI components. Covers enhanced features of gm-* components, usage of plugins such as GmConfirmBox/GmMessage/GmCopy, common code patterns, and how to obtain MCP documentation.
[Hyper] Create, enter, list, remove, clean up, or repair Git worktrees for isolated branches and parallel agent sessions, including direct `git-worktree ARGUMENT` creation without follow-up questions. Use when the user asks for git worktree setup/removal, branch-per-folder workflows, parallel Codex/Claude/Cursor workspaces, or the repository-local `.hyper/git-worktree/` convention; when creating and no argument/task is clear, ask what work will happen there in the user's language, derive the folder name, then move subsequent work into the new worktree.
Managing multiple branches simultaneously with Git worktree. When to use: (1) when developing multiple features in parallel (2) when you want to do other work during a PR review (3) when doing a production hotfix and development at the same time (4) when you want to learn how to use worktree. Trigger examples: "with worktree," "different branches at the same time," "want to develop in parallel," "develop while doing PR review," "worktree for hotfixes"
Use when writing or reviewing Gleam code on the Erlang target - especially Wisp + Mist HTTP services, OTP-based processes (gen_server / supervisor analogues), justfile workflows, gleeunit testing, `gleam format`, GitHub Actions CI, and performance measurement. Trigger on `gleam.toml`, `.gleam` files, or Erlang/BEAM-related symptoms even if the user does not say "Gleam" by name.
Clarify fuzzy intent and pressure-test design choices through focused dialogue before implementation. Use when the user wants to shape an idea, resolve consequential tradeoffs, or says to grill or crystallize it. Not written-artifact critique, bug diagnosis, or implementation.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.