Explain how a file, folder, or feature works

Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.

Process, convert, OCR, extract, redact, sign, and fill documents using the Nutrient DWS API. Works with PDFs, DOCX, XLSX, PPTX, HTML, and images.

Add or insert a new numbered pipeline step in the p2cs_project, following the standardized Step/DataFile/explore notebook patterns and safely renumbering subsequent steps (code, data, figures, tests, config, dependencies, and imports) when inserting in the middle of the pipeline. Use when creating a new step_* directory, inserting a step between existing ones, or updating step numbers across the project.

DART CI/CD troubleshooting - GitHub Actions, cache debugging, platform-specific failures

Expert guidance for building and editing n8n workflows with Synta MCP tools. Use for creating new workflows, modifying existing workflows, template discovery, node configuration, validation, and connection management in n8n.

When you need to work with a specific Flowbite component:

Capture a user's idea and write a single markdown file in `design/ideas/` using the required format: Idea summary, research, and a sketch in a code block.

Development workflow guide. Covers build, test, lint, format commands, package structure, Git hooks, TDD methodology, and coding conventions. Use when setting up dev environment, running tests, or following project conventions.

Shows project progress, phase completion status, test coverage, and deployment info. Use when checking what has been implemented, what remains, or current operational state.

Update branch memory files after completing work. Saves session history, key learnings, and collaboration observations to .trinity/ files.

Plan work using Mighty (mt) by creating/updating specs and recording decisions, then spawning/structuring implementation tasks. Use when asked to plan/outline/break down a change, draft a spec (feature/rule/invariant/bug), record an ADR-style decision, or turn a fuzzy request into a structured Mighty spec tree with linked tasks.

**The Goal:** AI-ready documentation. When documentation is clear enough, code generation becomes automatic.

FFI cross-language interop expert covering C/C++ bindings, bindgen, cbindgen, PyO3, JNI, memory layout, data conversion, and safe FFI patterns.

Rust web development expert covering HTTP frameworks (axum, actix), REST API design, handler patterns, state management, middleware, database integration, and domain-driven architecture.

Pin and self-referential types expert covering Pin, Unpin, Future, async state machines, pinning projection, and memory stability guarantees.

策略引擎、权限决策、RBAC、策略模式、责任链--- # Rust XACML - 策略引擎技能 > 本技能提供策略决策引擎的通用解决方案，包括 RBAC、责任链、策略模式等。 ## 核心概念 ### 1. 策略引擎架构 ``` 策略决策流程 ┌─────────────────────────────────────────────────────────────┐ │ 请求上下文 │ │ (主体、资源、操作、环境) │ └────────────────────────┬────────────────────────────────────┘ ▼ ┌─────────────────────────────────────────────────────────────┐ │ 策略决策点 (PDP) │ │ ├── 策略加载 │ │ ├── 策略评估 │ │ └── 决策组合 │ └────────────────────────┬────────────────────────────────────┘ ▼ ┌─────────────────────────────────────────────────────────────┐ │ 决策结果 │ │ (Permit / Deny / NotApplicable / Indeterminate) │ └─────────────────────────────────────────────────────────────┘ ``` ### 2. 决策类型 | 结果 | 含义 | 处理 | |-----|------|-----| | **Permit** | 允许访问 | 执行操作 | | **Deny** | 拒绝访问 | 返回 403 | | **NotApplicable** | 无匹配策略 | 使用默认规则 | | **Indeterminate** | 评估错误 | 返回 500 |

Macro and procedural metaprogramming expert covering macro_rules!, derive macros, proc-macros, compile-time computation, and code generation patterns.

Textum PRD→Scaffold→Story workflow for Codex with low-noise outputs and gate checks.

Create simple, performant Three.js web apps/scenes (JS/TS, ES modules): scene/camera/renderer setup, lighting, geometries, materials, animation loop, resizing, OrbitControls, GLTF/GLB loading, and practical performance guardrails.

Rust coding conventions expert covering naming, formatting, comments, clippy, rustfmt, lints, code style, best practices, and idiomatic patterns.

Unsafe code and FFI expert covering raw pointers (*mut, *const), FFI patterns, transmute, union, #[repr(C)], SAFETY comments, soundness rules, and undefined behavior prevention.

Rust learning and ecosystem tracking expert covering version updates, new features, RFC tracking, crate updates, best practice evolution, and learning resources.

Use when asked to prepare, review, or create a git commit for this repository. Follow the local commit policy, keep commits scoped to the intended changes, run the fast required checks, and write Conventional Commits that work with release-please.

ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ. Check curl, wget, rm, sudo, apt, dpkg, chmod, dd, format, powershell, bash, sh. Check pipe patterns like | sh or | bash. Check shell wrappers like bash -c, xargs, find -exec. Check cloud CLI (aws, gcloud, kubectl, terraform). Check when user says sysadmin told me, Stack Overflow says, is this safe, can I run. Block reading of .env, .ssh, .aws, and credential files. This skill blocks dangerous commands and warns on risky ones. ALWAYS apply the safety protocol from this document before responding about any command.

Primary router skill for broad .NET work. Classify the repo by app model and cross-cutting concern first, then switch to the narrowest matching .NET skill instead of staying at a generic layer.

Add or update automated tests for a change using the repository’s verification rules in `AGENTS.md`. Use when implementing a feature, bugfix, refactor, or regression test; prefer stable integration/API/UI coverage and pull deeper test strategy from the bundled references.

Use when developing Rust projects in the tempoxyz org—standardizes fmt/clippy/nextest, sccache+mold, feature-powerset checks, MSRV builds, docsrs flags, and xtask patterns so local and CI behavior match.

MoonBit language reference and coding conventions. Use when writing MoonBit code, asking about syntax, or encountering MoonBit-specific errors. Covers error handling, FFI, async, and common pitfalls.

Handle user questions, feature requests, and bug reports for connectrpc-axum. This skill should be used when users ask questions about the library, request new features, or report bugs. It first attempts to answer using project documentation, verifies bugs with integration tests, and submits GitHub issues when needed.

Use when defining or updating Go CLI i18n rules in this repo, especially around locale files, env-based language selection, and key naming.

Design specification for CLI TUI (Terminal User Interface). This skill provides comprehensive guidelines for implementing interactive terminal UI components, including page layout structure, color schemes, keyboard navigation, and multi-level navigation principles.

Implement a new Flet extension/control that wraps a third-party Flutter package end-to-end, including dependency selection, version pinning, compatibility checks, Python/Flutter integration, docs, examples, tests, and CI updates. Use when adding any flet_* package backed by an external pub.dev package.

>

Builds a complete agent with multiple Airbyte connectors using PydanticAI or Claude SDK. Scaffolds project structure, wires up connectors, composes tools, and creates a run loop. Use when building an agent with multiple connectors or scaffolding a new agent project.

Scan a live web app with Playwright, extract all features, generate PRD/epics/stories with priorities and dependencies, export to Notion. Checks required MCP servers before starting.

Apply MCAF non-functional-requirements guidance to capture or refine explicit quality attributes such as accessibility, reliability, scalability, maintainability, performance, and compliance. Use when a feature or architecture change needs explicit quality attributes and trade-offs.

Create or update a feature spec under `docs/Features/` using `docs/templates/Feature-Template.md`: business rules, user flows, system behaviour, Mermaid diagram(s), verification plan, and Definition of Done. Use before implementing a non-trivial feature or when behaviour changes; keep the spec executable (test flows + traceability to tests).

Use when something is broken and you need to find out why: test failures, runtime errors, crashes, regressions, or unexpected behavior. Trigger for 'it's not working', 'something broke', 'this used to work', 'I'm getting an error', 'CI is failing', 'the output is wrong', or 'why is X happening'. Systematic 4-phase diagnosis — never patches symptoms without finding the root cause.

Author or refine an inspequte rule spec from a rule idea, optional plan.md, and target rule-id. Use when writing src/rules/<rule-id>/spec.md from a fixed template while avoiding implementation details.

Use when the user asks about Omni platform documentation outside the narrow embed flow, including modeling, REST API, AI and MCP features, administration, permissions, connections, and platform setup; browse official `docs.omni.co` pages, prefer `$omni-embed-docs` for embed-specific questions, and answer with source links.

SIMD vectorization for Rust — detects ISA features, identifies vectorizable patterns, generates platform-specific intrinsics (ARM NEON/SVE, x86 SSE/AVX/AVX-512), validates correctness and performance. Uses tiered research with baked-in references and /deep-research fallback.

Use this skill when the task is to reproduce or analyze a concrete AutoLabOS TUI/web symptom, especially when stale state, fresh-vs-existing divergence, resume mismatch, or persisted-artifact-vs-UI disagreement may be involved.

Edit LCP protocol docs under docs/protocol/ in BOLT-style (TLVs, message formats, state flow).

Connects a mind to the Hive Mind system. For new local minds, scaffolds MIND.md and implementation.py, then registers. For remote minds, writes a MIND.md pointing at the external gateway. For re-registration, re-runs discovery against an existing folder.

Pipeline orchestrator that works Ada-labelled Planka cards through the full dev pipeline (story → plan → code → review). Use for autonomous development sessions.

Documentation creation and modification rules (docs/en/developer/ design documents, abstraction principles, structure, docs-first workflow). Use when creating documentation, updating design documents, writing architecture docs, checking which docs must change for a code change, asking about documentation structure/design principles, or working with files in docs/en/developer/ (fallback: docs/ja/).

Migrated from the legacy agent profile. Use this as an on-demand specialist workflow.

[OMX] Guide on using oh-my-codex plugin

Draft a repo-local plan using the plan skill template and optionally save it.