Agent skill

Openprd Benchmark Router

by DavidLam-oss in DavidLam-oss/obsidian-wechat-converter

为 OpenPrd 产品、CLI、Agent harness、AI code review / PR review harness、上下文工程、提示词优化和图标资源选择对标来源与调研路径。

MITAuto-check passedDevelopment

Install Openprd Benchmark Router

skills CLI
$ npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-benchmark-router -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install DavidLam-oss/obsidian-wechat-converter openprd-benchmark-router --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/DavidLam-oss/obsidian-wechat-converter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/openprd-benchmark-router .claude/skills/openprd-benchmark-router && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
openprd-benchmark-router
GitHub stars
334
Token cost
~1.9k tokens
SKILL.md length
498 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

为 OpenPrd 产品、CLI、Agent harness、AI code review / PR review harness、上下文工程、提示词优化和图标资源选择对标来源与调研路径。

  • Works in 6 steps: 先识别优化对象:OpenPrd 产品/PRD 流程、CLI、skill… → 读取当前工作区证据:.openprd/、.openprd/benchmarks/i… → 选择最小足够的外部证据源:公开 GitHub 仓库走… → …
  • Tasks that involve Pull requests
  • SKILL.md covers 核心原则, 触发信号, 路由流程 and Project Registry, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Openprd Benchmark Router is an agent skill from DavidLam-oss/obsidian-wechat-converter. 为 OpenPrd 产品、CLI、Agent harness、AI code review / PR review harness、上下文工程、提示词优化和图标资源选择对标来源与调研路径。

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests and Code review. It works with GitHub. The repository describes itself as: Obsidian 公众号排版(支持自定义 CSS和公众号贴图)、飞书云同步与多平台(小红书、知乎等)发布插件。Markdown 转微信文章 / Feishu docs / 知乎、小红书、今日头条等草稿,支持数学公式、本地图片、GIF 和 Mermaid。 The licence is MIT.

When your agent uses it

  • Tasks that involve Pull requests
  • Tasks that involve Code review

Example prompts

  • “/openprd-benchmark-router”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 先识别优化对象:OpenPrd 产品/PRD 流程、CLI、skill 体系、长程任务、通用 harness、AI code review / PR review harness、context engineering、prompt engineering、图标资源或图标实现库。
  2. 读取当前工作区证据:.openprd/、.openprd/benchmarks/index.md、.openprd/benchmarks/sources.yaml、AGENTS.md、repo-local skills、生成的 .codex/.claude/.cursor…
  3. 选择最小足够的外部证据源:公开 GitHub 仓库走 DeepWiki;第三方工具、SDK、CLI 或官方 API 用 Context7;产品官方文档、工程博客和一手资料用官方来源。
  4. 形成 OpenPrd 设计判断时,明确区分已证实事实、从来源归纳出的设计原则,以及对本项目的推断。
  5. 用分析维度提炼可迁移原则,避免照搬表面功能。
  6. 如果任务变成大量参考项目行为挖掘、长时间覆盖或需求补全,再路由到 $openprd-discovery-loop 承接持续调研。

What it can do on your machine

Read from SKILL.md and the folder at commit 3fef612. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • phosphoricons.com
    • lobehub.com
    • techicons.dev
    • thiings.co
    • iconfont.cn
    • github.com
    • milvus.io
    • nolanlawson.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Openprd Benchmark Router loads about 1.9k tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 498 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from DavidLam-oss/obsidian-wechat-converter at commit 3fef612, republished under its MIT licence (© DavidLam-oss). 498 words, ~1,850 tokens.

Download SKILL.mdSave it as .claude/skills/openprd-benchmark-router/SKILL.md (or your agent's skills folder).
name
openprd-benchmark-router
description
为 OpenPrd 产品、CLI、Agent harness、AI code review / PR review harness、上下文工程、提示词优化和图标资源选择对标来源与调研路径。
<!-- OPENPRD:GENERATED
adapter=codex
source=openprd-benchmark-router
version=0.1.19
checksum=1cbd70dcfc3a1acc
-->

OpenPrd Benchmark Router

当用户要求最佳实践、benchmark、对标、参考设计、产品优化、CLI 优化、Agent harness 优化、AI code review / PR review harness、上下文工程、提示词工程或图标资源时,先使用这份 skill。

核心原则

  • 不把对标当成固定关键词匹配。结合用户目标判断参考源是否真的能提升设计、实现、排查、评审、规划或文档质量。
  • 不强行对标。环境、权限、账号、普通脚本报错、一次性短问答或与产品/领域设计无关的问题,继续当前任务即可。
  • 不默认下载全文、仓库或整站。先保留轻量链接、来源 ID 和适用边界;真正需要事实时再读取。
  • 通常只选 1-3 个最相关来源;不要为了显得全面而扩大上下文。
  • 不把索引、来源目录或记忆当事实来源;未经核验的外部内容不能作为已确认事实输出。

触发信号

  • 用户提到 OpenPrd、OpenSpec、Superpowers、Anthropic Skills、Lark CLI、Agent harness、AI code review、PR review、review lane、long-running agents、context engineering、prompt engineering、最佳实践、对标、参考、复刻或优化设计。
  • 用户提到图标、icon、图标站、图标库、图标资源、UI 图标、AI 图标、技术图标、3D 图标、功能图标、iconfont 或视觉资产参考。
  • 用户提到界面审美、设计框架、主题库、模板库、组件骨架、视觉资产库、前端体验风格或页面参考方法。
  • 用户要求解释某个 Codex / Claude / Cursor agent 为什么没有发现 skill,或希望提升 skill 自动识别、路由、生成、安装和持续执行能力。
  • 用户没有显式说 skill 名也要触发;不要要求用户记住 $openprd-benchmark-router。

路由流程

  1. 先识别优化对象:OpenPrd 产品/PRD 流程、CLI、skill 体系、长程任务、通用 harness、AI code review / PR review harness、context engineering、prompt engineering、图标资源或图标实现库。
  2. 读取当前工作区证据:.openprd/、.openprd/benchmarks/index.md、.openprd/benchmarks/sources.yaml、AGENTS.md、repo-local skills、生成的 .codex/.claude/.cursor 引导和相关源码。
  3. 选择最小足够的外部证据源:公开 GitHub 仓库走 DeepWiki;第三方工具、SDK、CLI 或官方 API 用 Context7;产品官方文档、工程博客和一手资料用官方来源。
  4. 形成 OpenPrd 设计判断时,明确区分已证实事实、从来源归纳出的设计原则,以及对本项目的推断。
  5. 用分析维度提炼可迁移原则,避免照搬表面功能。
  6. 如果任务变成大量参考项目行为挖掘、长时间覆盖或需求补全,再路由到 $openprd-discovery-loop 承接持续调研。

Project Registry

  • 项目自己的 .openprd/benchmarks/ 优先于 OpenPrd 内置 Source Map。
  • sources.yaml 里的 approved source 是长期可复用参考;inbox/ 里的 candidate 只表示待确认线索。
  • 用 openprd benchmark add <url|repo|file> 写入 candidate,用 openprd benchmark approve <id> 纳入 approved registry。
  • 执行或复盘中发现被用户采纳的优质信源时,用 openprd benchmark observe <url|repo|file> --notes <text> 累计 evidence;达到阈值后只推荐 approve,不自动晋级。
  • 用 openprd benchmark verify 检查重复来源、失效链接、缺失本地文件和过宽触发规则。

Source Policy

  • GitHub 仓库:需要理解架构、核心模块、关键流程或对标结论时,先用 DeepWiki。默认顺序是 read_wiki_structure 1 次,再 ask_question 1-2 次;只有在本地源码和已有结论仍不足时才追加。DeepWiki 不可用或覆盖不足时,再回退到 GitHub README、源码和官方文档。
  • 官方技术文档:涉及第三方库、框架、API、SDK、MCP、CLI 工具的用法、配置、限制、版本差异或迁移路径时,先检查本地代码、锁文件、README、类型定义;本地不足时再用 Context7,默认顺序是 resolve_library_id 1 次,再 query_docs 1-2 次。Context7 不足时说明缺口,再补官方文档、源码或其他一手资料。
  • 工程文章和产品文档:优先读取当前线上一手页面,只抽取和当前任务相关的观点与设计原则,不复制长文;如果内容可能过时,要说明时效风险。
  • 视觉与设计参考:优先吸收结构、节奏、信息组织、资产策略和质量门,不照搬品牌表层风格。需要官方品牌或产品事实时,优先官方站点、官方媒体包、官方设计系统和项目自身 approved benchmark。
  • 本地源码优先:当前工作区已经有相关源码时,常规修 bug、查实现、改功能优先读本地代码;DeepWiki 主要用于外部仓库架构理解和对标分析。
  • 停止调研:找到足以支持当前决策的 1-3 个高相关来源后停止扩展;候选来源重复时保留更权威、更新或更贴近当前任务的来源。
  • 追加调用前先写清“已确认什么、还缺什么”;不要为了同一问题只换个说法反复查询。

Source Map

  • Fission-AI/OpenSpec:适合对标 spec 驱动变更流程、change lifecycle、spec 与 execution artifact 分层、动态 agent 指令组装和验证门禁。
  • obra/superpowers:适合对标 mandatory skill routing、多平台适配、轻量 bootstrap、worktree/subagent 协作和 skill 深浅分层。
  • slavingia/skills:适合对标 0 到 1 验证、community-first、10 specific people、current workaround、manual-first delivery、Magic Piece of Paper、spreadsheet / no-code first、automate-one-step-at-a-time、forms and lists / CRUD first、build for today's customers not hypothetical future ones、avoid irreversible decisions、one-thing MVP、weekend test、3-of-10 payment proof、10+ paying before productize、first-customer circles、100 paying before launch、charge-from-day-one、customer-1 profitability、spend time before money、minimalist review 和 default alive 思路,并把这些原则回写到 requirement-intake、brainstorm 和 PRD 结构。
  • CLI 与 skill 体系对标:larksuite/cli、anthropics/skills、Claude Skills 官方文档、Claude Code Skills 官方文档。
  • 长程 Agent 任务:Anthropic long-running agents harness 工程文章。
  • 通用 harness:OpenAI harness engineering、LangChain agent harness anatomy。
  • AI code review / PR review harness:Nolan Lawson 的 “Using AI to write better code more slowly”、Milvus 关于多模型代码审查辩论/交叉验证的实验文章。
  • Context engineering:Manus context engineering、Anthropic context engineering。
  • Prompt engineering:OpenAI prompt engineering / prompt guidance、Claude prompt engineering、Gemini prompting strategies。
  • 图标资源站一级最佳实践:UI 图标优先看 Phosphor Icons(https://phosphoricons.com/);AI 公司与产品图标看 LobeHub Icons(https://lobehub.com/icons);技术栈图标看 Tech Icons(https://techicons.dev/);透明底 3D 图标看 Thiings(https://www.thiings.co/things);功能图标、矢量插画、3D 插画和字体资源看 iconfont(https://www.iconfont.cn/)。
  • 图标实现库二级最佳实践:Lucide、Tabler、React Icons。需要落到前端代码时,再结合当前项目框架、包管理器、bundle 体积和导入方式选择具体库。
Show full SKILL.md (180 more words)Show less

Evaluation Lenses

  • 产品与工作流:用户从哪里开始、如何知道下一步、模糊输入如何变成结构化产物、哪些步骤要保存/展示/恢复、哪些步骤必须保留用户确认。
  • Agent 与 Harness:目标、边界、停止条件、工具选择、进度记录、证据、验证结果、失败恢复和人工接管点是否清楚。
  • PR 审查 lane:reviewer 是否独立审查、主代理是否先汇总再验证、是否有误报过滤、agreement matrix、严重级别和 merge recommendation。
  • 上下文工程:哪些信息常驻、哪些按需检索,是否使用稳定路径、链接和来源 ID 支持 just-in-time 检索,如何处理过期、冲突和可信度。
  • 提示词与 Skill 设计:触发描述是否具体但不过度强制,主说明是否短,细节是否按需放到 reference,是否明确不要硬套参考源。
  • 图标与视觉资产:先判断用途是 UI、AI 品牌、技术栈、3D 物件还是功能图标;优先选最贴近用途的资源站,再在实现阶段选择合适的代码图标库。
  • 前端设计框架:先判断要借的是主题锁定、布局骨架、组件清单、事实前置、素材前置、图片前置还是质量门;把可迁移原则落回 .openprd/design/、repo-local skill、hooks 或测试,不要停留在“参考了几个好看页面”。
  • CLI 与开发者体验:命令是否可发现、可组合、可预测;错误信息是否说明发生了什么、影响是什么、下一步怎么做;危险操作是否有确认。

设计输出

  • 给出 OpenPrd 应该内置什么、生成什么、路由什么、保留什么门禁。
  • 如果来源本质上在讲 0 到 1 验证或创业判断,优先把“社区契合 -> 当前替代与痛点证据 -> 手工/表单/no-code 桥接 -> 付费验证 -> 产品化门槛 -> 增长纪律”落到 requirement-intake、brainstorm、PRD 模板和 hook 提示里,而不是只加一条灵感备注。
  • 优先把结论落到 CANONICAL_SKILLS、repo-local skills、AGENTS/CLAUDE/Cursor 生成规则、hooks 或测试,而不是停留在口头建议。
  • 不把外部项目整包复制进 OpenPrd;只吸收可验证的路由、生成、门禁、状态承接和用户体验原则。
  • 需要显式说明时,简短写出参考了哪个来源、借鉴点、适用原因、不照搬边界,以及落到当前任务的具体决策。

Stop Rule

  • 同一来源默认只做一次结构理解和一到两次聚焦问题;证据足够支撑当前决策后立即停止调研。
  • 如果 DeepWiki、Context7 或官方资料覆盖不足,明确说明缺口,再把后续结论标为推断。

Project Benchmark Registry

  • 先读取 .openprd/benchmarks/index.md 和 .openprd/benchmarks/sources.yaml。
  • 项目级 approved benchmark 优先于 OpenPrd 内置 Source Map;inbox/ candidate 只能作为待确认线索。
  • benchmark observe 只累计被采纳信源的证据;达到阈值后仍需用户确认 approve。
  • 每次最多优先挑 1-3 个与当前任务最相关的 approved source。
Approved Sources
  • github-com-slavingia-skills slavingia/skills
    • 场景: skill-design
    • 触发: 设计 skill 触发、metadata、安装方式、自动识别或项目级覆盖规则
    • 不适用: 普通 PRD / 产品流程设计;与 CLI 无关的一次性 UI 视觉问题;单次脚本报错或纯环境权限问题
    • 研究方式: deepwiki_then_github
    • 来源: slavingia/skills (https://github.com/slavingia/skills)
  • milvus-io-ai-code-review-gets-better-when-models-debate-claude-vs-gemini-vs-code milvus.io/ai-code-review-gets-better-when-models-debate-claude-vs-gemini-vs-codex-vs-qwen-vs-minimax.md
  • nolanlawson-com-using-ai-to-write-better-code-more-slowly nolanlawson.com/using-ai-to-write-better-code-more-slowly
    • 场景: agent-harness, pr-review-harness
    • 触发: 设计 Agent harness、长程任务、状态持久化、验证门禁或人工接管;设计 merge 前高风险复核、独立 reviewer 交叉验证、误报过滤、reviewer agreement 或 merge recommendation
    • 不适用: 普通 PRD / 产品流程设计;与 CLI 无关的一次性 UI 视觉问题;默认给每个低风险 PR 拉起多 reviewer 并行审查
    • 研究方式: official_page_first
    • 来源: https://nolanlawson.com/2026/05/25/using-ai-to-write-better-code-more-slowly/

© DavidLam-oss, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .codex/skills/openprd-benchmark-router of DavidLam-oss/obsidian-wechat-converter.

Open the folder on GitHubat commit 3fef612

Compare with similar skills

Openprd Benchmark Router next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Openprd Benchmark Router compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openprd Benchmark Router this skillDavidLam-oss/obsidian-wechat-converter334—~1.9kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
GitHub Review Iterationprisma/orm48k—~2.2kAutomated safety check: PassApache-2.0
PR Review State Fetchprisma/orm48k—~767Automated safety check: PassApache-2.0
PR Finalize Reviewmicrosoft/garnet12k—~3.1kAutomated safety check: PassMIT
Fastlane Pull Request Reviewfastlane/fastlane42k—~550Automated safety check: PassMIT

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Official

    Fetches a pull request's canonical review state as JSON, validates it, and renders markdown, a text summary and triage target files from it using bundled scripts.

    48k GitHub stars~767 tokensUpdated today
    DevelopmentAuto-check passed
  • PR Finalize Review

    microsoft/garnet

    Official

    Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.

    12k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Reviews a fastlane pull request against its linked issue and the project guides, separating blocking from non-blocking findings and handling vulnerabilities privately.

    42k GitHub stars~550 tokensUpdated today
    DevelopmentAuto-check passed
  • Pull Request Babysitter

    thedotmack/claude-mem

    Keeps watching a pull request, fixing real review and CI problems and resolving stale threads, until it is clean and ready to merge.

    99k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed

More from DavidLam-oss/obsidian-wechat-converter

All 14 skills in this repo
  • Openprd UI Context

    DavidLam-oss/obsidian-wechat-converter

    OpenPrd UI Context skill:区分 greenfield、brownfield 与局部修正,基于已确认 PRD、可选 CodeGraph 和本地证据提出专业 UI/UX 方向,并在用户确认后编译 PRODUCT.md、DESIGN.md 和 Impeccable handoff。

    334 GitHub stars~899 tokensUpdated today
    Auto-check passed
  • Wechat AI Layout

    DavidLam-oss/obsidian-wechat-converter

    为 Obsidian 微信公众号转换器生成受约束的 AI 编排结果。只在需要把文章内容映射为公众号安全 block JSON、诊断编排结果、优化 layout schema、分析 fallback 介入原因时使用。遇到教程、案例、产品介绍、截图型内容时应优先考虑这个 skill。

    334 GitHub stars~498 tokensUpdated today
    Auto-check passed
  • Openprd Test Strategy

    DavidLam-oss/obsidian-wechat-converter

    OpenPrd 测试策略分流 skill:按风险把任务分到单元、集成、端到端、人工、视觉、小程序、性能和安全验证,并要求 evidence-plan。

    334 GitHub stars~578 tokensUpdated today
    Auto-check passed
  • Project Release

    DavidLam-oss/obsidian-wechat-converter

    Release workflow for obsidian-wechat-converter (version bump, release notes, tag and publish).

    334 GitHub stars~597 tokensUpdated today
    Auto-check passed
  • Openprd Diagram Review

    DavidLam-oss/obsidian-wechat-converter

    生成并迭代 OpenPrd 图示产物,供用户确认或理解。适用于解释型 SVG、架构图、产品流程图、用户旅程、流程图、系统边界图、依赖图,以及 freeze 前的可视化评审场景。

    334 GitHub stars~724 tokensUpdated today
    Auto-check passed
  • Openprd Frontend Design

    DavidLam-oss/obsidian-wechat-converter

    OpenPrd 前端设计框架 skill:为界面、页面、视觉、样式和前端体验任务提供设计资产框架、审美立意、反 AI 味门禁和实现前方向评审规则。

    334 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Openprd Benchmark Router

What does Openprd Benchmark Router do?

为 OpenPrd 产品、CLI、Agent harness、AI code review / PR review harness、上下文工程、提示词优化和图标资源选择对标来源与调研路径。. Openprd Benchmark Router is an agent skill from DavidLam-oss/obsidian-wechat-converter.

When should I use Openprd Benchmark Router?

Openprd Benchmark Router fits situations like: tasks that involve Pull requests; tasks that involve Code review.

How do I install Openprd Benchmark Router in Claude Code?

Run `npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-benchmark-router -a claude-code`. Or copy the skill folder (.codex/skills/openprd-benchmark-router in DavidLam-oss/obsidian-wechat-converter) into .claude/skills/openprd-benchmark-router in your project. Claude Code loads it when a task matches its description.

How do I install Openprd Benchmark Router in Codex?

Run `npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-benchmark-router -a codex`. Or copy the skill folder (.codex/skills/openprd-benchmark-router in DavidLam-oss/obsidian-wechat-converter) into .agents/skills/openprd-benchmark-router in your project. Codex loads it when a task matches its description.

Can I use Openprd Benchmark Router in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DavidLam-oss/obsidian-wechat-converter --skill openprd-benchmark-router -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openprd-benchmark-router, .gemini/skills/openprd-benchmark-router, .github/skills/openprd-benchmark-router and .opencode/skills/openprd-benchmark-router in your project.

What does Openprd Benchmark Router need to run?

SKILL.md names no scripts, command-line tools or credentials: Openprd Benchmark Router is instructions for the agent only.

Does Openprd Benchmark Router access the network?

SKILL.md names 8 domains. As links in the text: phosphoricons.com, lobehub.com, techicons.dev, thiings.co, iconfont.cn, github.com, milvus.io and nolanlawson.com. This is read from the text; nothing was executed.

Is Openprd Benchmark Router safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Openprd Benchmark Router use?

Openprd Benchmark Router is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Openprd Benchmark Router use?

About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Openprd Benchmark Router?

Skills that share tags, products or a category with Openprd Benchmark Router: PR Babysitter (openinterpreter/openinterpreter, 69k stars), GitHub Review Iteration (prisma/orm, 48k stars), PR Review State Fetch (prisma/orm, 48k stars) and PR Finalize Review (microsoft/garnet, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openprd Benchmark Router?

DavidLam-oss (a GitHub user) maintains it in DavidLam-oss/obsidian-wechat-converter, which has 334 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 9, 2026.

Source: DavidLam-oss/obsidian-wechat-converter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.