发现 Skills

Expert guidance for building with Payload CMS - collections, fields, hooks, access control, Local API, authentication, uploads, and admin theming

A complete workflow and component library for creating industrial‑grade UI designs with Pencil MCP

Security assessment skill for reconnaissance, endpoint/service enumeration, and attack-surface mapping. Use when prompts include recon, enumerate, map endpoints, discover assets, inventory interfaces, fingerprint technologies, or identify control-plane surfaces. Do not use when the request is exploit development, payload execution, or final report writing only.

Project scheduling expert. Use for WBS, Gantt charts, dependency mapping, and resource allocation.

Escapes Python sandbox restrictions. Use when working with restricted Python eval/exec environments, sandbox escapes, filtered input challenges, or Python jail challenges.

Patterns for building reliable background job processing systems. Covers message queues, worker pools, retries, dead letter handling, and async workflow orchestration. Use when ", " mentioned.

Report generation workflow that consolidates information into structured professional reports

Create UML (Unified Modeling Language) diagrams using draw.io (diagrams.net) XML format. Best for software modeling including Class, Sequence, Activity, State Machine, Component, Use Case, and Deployment diagrams. Built on draw.io with UML-specific shapes and notation. NOT for simple flowcharts (use mermaid), layered system architecture (use architecture), or data charts (use vega).

Manage TASK_BOARD.md by reading project logs and synchronizing task status. Use when tasks are completed, when progress is made, or when needing to sync task tracking. Reads MIGRATION_LOG.md, DEBUG_LOG.md, GIT_LOG.md to assess actual progress and updates TASK_BOARD.md accordingly. Does NOT modify CLAUDE.md or MIGRATION_LOG.md.

Support local workflow platform development in the DAP workspace across frontend, backend, and infra teams. Provides access to Kubernetes (Kind), Tilt service management, database queries, and troubleshooting. Use when building backend/API features, adjusting infra configurations, checking logs, running tests, or debugging issues against locally deployed workflow engine components.

Guidance on implementing the Data Layer using Repository pattern, Room (Local), and Retrofit (Remote) with offline-first synchronization.

Universal horizontal-swipe HTML deck, not a magazine-style layout.

Screen and filter A-share stocks based on fundamental metrics, technical indicators, capital flow, and custom criteria. Support multiple screening strategies including value investing, growth investing, momentum trading, and dividend hunting. Use when user wants to find stocks meeting specific criteria like "低PE高ROE股票", "北向资金加仓股", "突破年线的股票".

Create an empty 1C external report (scaffold of XML source files)

Добавление элементов, реквизитов и команд в существующую управляемую форму 1С. Используй когда нужно точечно модифицировать готовую форму

Systematically audit documentation against actual codebase to determine accuracy, staleness, and relevance. Use when auditing docs for accuracy, cleaning up stale docs after refactoring, validating docs match implementation, or building documentation health reports.

Govern Power Automate flows and Power Apps at scale using the FlowStudio MCP cached store. Classify flows by business impact, detect orphaned resources, audit connector usage, enforce compliance standards, manage notification rules, and compute governance scores — all without Dataverse or the CoE Starter Kit. Load this skill when asked to: tag or classify flows, set business impact, assign ownership, detect orphans, audit connectors, check compliance, compute archive scores, manage notification rules, run a governance review, generate a compliance report, offboard a maker, or any task that involves writing governance metadata to flows. Requires a FlowStudio for Teams or MCP Pro+ subscription — see https://mcp.flowstudio.app

Find architectural deepening opportunities in a codebase using Ousterhout's depth/seam/locality vocabulary and the Deletion test. Use when you want to evaluate whether modules pull their weight, surface shallow modules, identify refactoring opportunities, or improve testability and AI-navigability. This complements the `simplify` skill — while simplify reviews code quality, deepen evaluates module leverage.

Guide for designing effective tools for AI agents. Use when creating tools for custom agent systems or any AI tool interfaces. Provides principles for tool naming, input/output design, error handling, and evaluation methodologies that maximize agent effectiveness.

Configure Ideogram enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration, configuring role-based permissions, or setting up organization-level controls for Ideogram. Trigger with phrases like "ideogram SSO", "ideogram RBAC", "ideogram enterprise", "ideogram roles", "ideogram permissions", "ideogram SAML".

Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API differences. Use when converting, porting, or translating cuTile Python kernels to Julia cuTile.jl, or debugging/optimizing existing Julia cuTile translations.

AI-assisted label triage for NVIDIA/NemoClaw issues and PRs. Reads triage-instructions.md at runtime for consistent label guidance. Supports single-item mode (give it a number) and batch mode (fetches up to 50 unlabeled open items). On approval, applies labels and an optional triage comment via gh CLI, then logs the session to the daily-rhythm activity folder. Trigger keywords - triage, label issues, suggest labels, batch triage, triage issue, triage PR, label this, what labels.

External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron policy setup, HF import/export, checkpoint/resume, non-colocated vLLM refit, delta weight transfer, optional LoRA/generation variants, and questions such as "does this model work in NeMo-RL", "run NeMo-RL e2e", or "external RL loop validation". Covers running NeMo-RL Megatron policy jobs from a Bridge checkout, choosing GRPO/SFT/checkpoint/non-colocated refit variants, setting PYTHONPATH so NeMo-RL imports the local Bridge tree, and reporting pass/fail evidence.

Validate at every layer data passes through to make bugs impossible