其他技能

Universal Pipeline JSON 编写指南。基于 MaaFramework Pipeline 协议，提供节点命名、识别算法、动作类型、流程控制、可复用节点等编码规范与模式参考。在编写、修改或审查 Pipeline JSON、设计节点流程、使用 TemplateMatch/OCR/Custom 识别或 Click/Swipe 动作时使用。

中文简介正在准备中。当前显示原文说明。

Interrogate the user before implementing a non-trivial or ambiguous ask, converging on shared intent. Use when the user says "grill me", when an ask admits multiple interpretations, or before any sizable piece of work whose intent isn't fully clear.

中文简介正在准备中。当前显示原文说明。

Guides pull request creation and review, including posting findings, controlling scope, readying work for review, and splitting work into a stacked-PR chain.

中文简介正在准备中。当前显示原文说明。

This skill should be used when validate-chunk reports errors or failures, when the user asks to "fix these errors", "resolve validation issues", "refine this chunk", or when specific build, lint, or type errors need surgical fixes. Makes precise, targeted edits to resolve specific validation issues without over-engineering.

中文简介正在准备中。当前显示原文说明。

Use when claiming the AI bounty on the tDVV mainnet sidechain. This public claim skill now supports Portkey AA/CA only, requires CA sync and holder preflight before any write, and routes to AA/CA onboarding, AA/CA claim, or diagnostics-only stop handling.

中文简介正在准备中。当前显示原文说明。

Claim the AI bounty on tDVV by delegating to the canonical repo SKILL and its branch docs; this public skill is AA/CA only and requires explicit write confirmation.

中文简介正在准备中。当前显示原文说明。

Execute or resume an implementation plan from `.agents/local/plans/`, keeping its companion backlog and validation evidence current. Use when the user asks to implement a saved plan or continue planned multi-phase work.

中文简介正在准备中。当前显示原文说明。

Create a Product Requirements Document from the current conversation and save it under `.agents/local/plans/`. Use when the user asks for a PRD, product specification, or requirements document for an Uniffy feature.

中文简介正在准备中。当前显示原文说明。

Check the current branch for an existing PR and either update or create one with an auto-generated description based on all commits since diverging from main.

中文简介正在准备中。当前显示原文说明。

Create a conventional commit for all uncommitted changes

中文简介正在准备中。当前显示原文说明。

Create a structured session handoff when context is running low or work is pausing. Deep context mining, self-validation, multi-file splitting. Captures everything the next session needs.

中文简介正在准备中。当前显示原文说明。

Organizes an author’s response to peer review. Extracts every referee and editor point, tags severity and type, orders the revision by dependency, flags defensible pushbacks as questions, and builds a numbered comment → response → location letter whose substantive answers the author writes. Use when the user has referee reports, a revise-and-resubmit decision, or an editor’s letter and wants to plan the revision, draft the response letter, or check that every point was addressed. The reviewer-side twin is journal-review.

中文简介正在准备中。当前显示原文说明。

Follow up on open PRs in skillsaw — fix failing CI, address reviewer feedback, push updates, and validate backward compatibility. Use when an open PR needs maintenance.

中文简介正在准备中。当前显示原文说明。

Onboard a repository to skillsaw — run the linter, triage the findings by rule, apply autofixes, manually fix what remains, set up CI, and create a baseline. Use when adopting skillsaw on a new or existing project.

中文简介正在准备中。当前显示原文说明。

Fix skillsaw lint violations — apply deterministic autofixes, then resolve the remaining violations with targeted edits guided by `skillsaw explain`. Use when skillsaw reports violations, when asked to clean up lint findings, or after `skillsaw fix` leaves violations behind.

中文简介正在准备中。当前显示原文说明。

Bump the version, generate release notes, and publish a new skillsaw release to PyPI. Use when cutting a new release.

中文简介正在准备中。当前显示原文说明。

Create, review, or maintain Node3D runnable examples, consumer-style package imports, feature demos, vendor adaptations, assets, and example validation.

中文简介正在准备中。当前显示原文说明。

Work on Node3D C++ addons, addon-tools bindings, binding.gyp/common.gypi, install.js, ts/native.ts, native handles, lifetime safety, and native verification.

中文简介正在准备中。当前显示原文说明。

Work on @node-3d/core browser-like runtime, Document/Window/canvas behavior, WebGL/Three.js compatibility, globals, context and resource behavior.

中文简介正在准备中。当前显示原文说明。

Use when selecting a Mermaid diagram type, looking up Mermaid syntax, adapting a Mermaid example, or locating a Mermaid reference for a flowchart, sequence, UML, architecture, chart, or other diagram.

中文简介正在准备中。当前显示原文说明。

This skill should be used when the user asks to "fix mypy errors", "add type annotations", "fix type checking", "resolve no-untyped-def", "fix mypy type errors", or when working with type hints while respecting StreamFlow's forbidden type constraints (no Any, dict[str, Any], etc.).

中文简介正在准备中。当前显示原文说明。

Relay agent results without corrupting exact counts, failure reasons, source scope or status. Use when receiving agent output or handing results to another actor; distinguish observations from attributed conclusions and reference complete artifacts.

中文简介正在准备中。当前显示原文说明。

Integrate multiple source findings into an attributed synthesis or comparison. Use for combine these summaries, synthesize results, merge findings or multi-source analysis. Preserve claim-level provenance, coverage, qualifiers, conflicts and uncertainty rather than repeatedly compressing narrative summaries.

中文简介正在准备中。当前显示原文说明。

Enforce mandatory pre-action verification checkpoints to prevent pattern-matching from overriding explicit reasoning. Use this skill when about to execute implementation actions (Bash, Write, Edit) to verify hypothesis-action alignment. Blocks execution when hypothesis unverified or action targets different system than hypothesis identified. Critical for preventing cognitive dissonance where correct diagnosis leads to wrong implementation.

中文简介正在准备中。当前显示原文说明。