Token导航 LogoToken导航TokenDH.com
研究检索需要联网clawhub未标认证来源可访问clear审计通过

vulkan-encyclopedia沃尔坎百科全书

Agent Skill

vulkan-encyclopedia 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

3,535

周安装

143

GitHub Stars

公开资料未说明

下载量

1,110
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:vulkan-encyclopedia(沃尔坎百科全书)
来源仓库:https://github.com/kklouzal/vulkan-encyclopedia
安装命令:
openclaw skills install vulkan-encyclopedia
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install vulkan-encyclopedia

简介

提供 Vulkan API 规范与参考工作流程,精准定位命令语义与同步机制问题。

  • 适合图形编程开发场景,可查找 VUID 规则和有效使用模式。
  • 使用时需明确具体 API 调用或结构体用法疑问,以提高检索准确性。
  • 通过 clawhub 安装,专为 OpenClaw 宿主设计,需确保网络访问规范文档源。
  • 注意不同硬件驱动可能对规范解释存在差异,建议结合实际运行环境测试验证。

SKILL.md

name
vulkan-encyclopedia
description
>-
metadata
{"openclaw":{"emoji":"🌋","homepage":"https://docs.vulkan.org/spec/latest/index.html"}}

Vulkan Encyclopedia

Overview

Use a docs-first workflow for Vulkan work. Prefer the official Vulkan specification/reference docs at https://docs.vulkan.org/spec/latest/index.html, consult cached local copies under .Vulkan-Encyclopedia/ before re-fetching, and record useful authoritative excerpts plus environment-specific operational learnings so future work gets faster, safer, and more grounded.

This skill is for the Vulkan API/spec layer, not for generic rendering theory and not for standalone shader-language questions unless they are being asked in direct service of Vulkan API behavior.

Workflow

  1. Classify the task

- Decide whether the task is a Vulkan API question, specification lookup, code-review task, validation/debugging task, architecture/design task, or live implementation task. - Use this skill when the task materially depends on Vulkan API semantics, Vulkan object/command structure, extension/feature behavior, synchronization rules, limits/capabilities/formats, or validation/spec interpretation. - Do not use this skill for generic graphics concepts, standalone shader-language work, or engine-level rendering discussion unless the Vulkan API/spec layer is actually in play.

  1. Check local cache first

- Use .Vulkan-Encyclopedia/ as the local knowledge/cache root. - Check these locations first when relevant: - .Vulkan-Encyclopedia/docs/docs.vulkan.org/spec/latest/... - .Vulkan-Encyclopedia/notes/components/... - .Vulkan-Encyclopedia/notes/patterns/... - .Vulkan-Encyclopedia/inventory/... - If a cached page or note already answers the question well enough, use it.

  1. Consult authoritative Vulkan docs before answering or acting

- Before answering direct or indirect Vulkan questions that depend on API semantics, exact command/structure rules, feature or extension behavior, synchronization guarantees, limits, valid usage, or version-sensitive details, consult the official Vulkan docs unless the answer is already well-supported by the local cache. - Before performing non-trivial Vulkan code review or implementation guidance, consult the relevant docs first when: - exact member names, allowed states, or command rules matter - synchronization or resource-lifetime behavior is easy to misremember - the task involves VUID interpretation, extension/feature enabling, or pipeline/resource correctness - If the problem is really about GLSL syntax/qualifiers/stage interfaces rather than Vulkan API semantics, prefer the GLSL skill instead of stretching this one. - Do not improvise fragile Vulkan answers from memory when the spec is easy to check.

  1. Cache consulted docs locally

- When you consult a Vulkan docs page, save a normalized cache copy under .Vulkan-Encyclopedia/docs/docs.vulkan.org/spec/latest/.... - Mirror the official docs path structure as much as practical. - Cache only pages actually consulted; do not try to mirror the whole spec eagerly. - Use scripts/cache_doc.py when appropriate.

  1. Separate authoritative documentation from local observations

- Store official-doc-derived material under .Vulkan-Encyclopedia/docs/.... - Store environment-specific operational knowledge under: - .Vulkan-Encyclopedia/notes/components/ - .Vulkan-Encyclopedia/notes/patterns/ - .Vulkan-Encyclopedia/inventory/ - Distinguish clearly between: - authoritative documented behavior - observed project/environment state - inferred best-practice guidance

  1. Record useful local learnings

- After useful live work, save durable notes such as: - project-specific Vulkan architecture notes - recurring validation/debugging patterns - extension/feature adoption decisions - synchronization/resource-management gotchas - safe/unsafe operational boundaries for the codebase or environment - Prefer concise durable notes over re-learning the same Vulkan details later.

Live Work Rules

  • Treat spec lookup as the default preflight for non-trivial Vulkan work.
  • Prefer read/inspect first when entering unfamiliar Vulkan code.
  • Treat synchronization, memory/resource lifetime, queue ownership, layout transitions, extension/feature gating, and validation/VUID interpretation as higher-sensitivity areas.
  • When uncertainty remains after checking cache + docs, say so and avoid bluffing.
  • When answering a question, mention when useful whether the answer comes from cached official docs, a fresh official docs lookup, or live observed project state.

Data Root

Use this workspace-local root for cache and notes:

  • .Vulkan-Encyclopedia/

Expected structure:

  • .Vulkan-Encyclopedia/docs/docs.vulkan.org/spec/latest/...
  • .Vulkan-Encyclopedia/notes/components/...
  • .Vulkan-Encyclopedia/notes/patterns/...
  • .Vulkan-Encyclopedia/inventory/...

Use scripts/init_workspace.py to create or repair the expected directory structure.

Note Destinations

  • Component-specific observations → .Vulkan-Encyclopedia/notes/components/<component-name>.md
  • Reusable Vulkan patterns/gotchas → .Vulkan-Encyclopedia/notes/patterns/<topic>.md
  • Environment-wide architecture/access info → .Vulkan-Encyclopedia/inventory/*.md
  • Cached official docs → .Vulkan-Encyclopedia/docs/docs.vulkan.org/spec/latest/...

Secrets / Sensitive Data

  • Do not store plaintext credentials, API keys, session tokens, private URLs, recovery codes, or other secrets in the encyclopedia notes/inventory tree.
  • If a note needs to mention access details, keep it high-level and redact or omit secret material.
  • Treat these workspace notes as operational memory, not as a secrets vault.

Resources

  • scripts/init_workspace.py — create or repair the .Vulkan-Encyclopedia/ directory tree.
  • scripts/cache_doc.py — fetch and cache a consulted official Vulkan docs page under .Vulkan-Encyclopedia/docs/....
  • references/workflow.md — detailed operating workflow and evidence-handling rules.
  • references/cache-layout.md — canonical .Vulkan-Encyclopedia/ directory structure.
  • references/topic-map.md — useful Vulkan topic groupings for faster authoritative lookup.

Good Outcomes

  • Answer a Vulkan question using cached or freshly checked official docs instead of guesswork.
  • Inspect Vulkan code after checking the relevant spec pages and record any new project-specific operational knowledge.
  • Build a growing local Vulkan knowledge cache that makes later work faster, safer, and more grounded.
  • Turn one-off Vulkan discoveries into durable notes so future work does not rediscover them from scratch.

Avoid

  • Answering Vulkan-specific questions purely from memory when the spec is easy to consult.
  • Treating local observed engine/project behavior as if it were guaranteed authoritative Vulkan behavior.
  • Dumping large amounts of low-value docs into the workspace without a reason.
  • Writing project-specific observations into the official-doc cache tree.
  • Making high-confidence claims about synchronization/valid-usage details without checking the spec when exact behavior matters.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

70.87%
按下载量换算787

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills