Communitygithub.com

promo-scout:验证优先的推广情报

针对任何仓库或组织,提供基于验证的推广情报。拉取实时GitHub状态,通过sshx多方共识进行分析,返回一份有证据支持的看板,展示哪些内容真正值得推广、它们如何相互关联以及哪些内容无法验证。适用于当代理或操作者询问“什么值得推广/什么有关联/什么是真实的”针对目标仓库或组织时。

promo-scout:验证优先的推广情报 是什么?

promo-scout 是一个通用的、验证优先的推广情报工具。与那些仅靠炒作的信息抓取器不同,它要求所有看板条目都必须有实时的 GitHub 状态作为证据支持,并且判断结果由 `sshx` 共识机制产生(基于隔离的视角和真值表),而不是单靠某个模型的断言。该工具要求调用者已配置好 `gh` 命令行工具(通过 `gh auth login` 或 `GH_TOKEN` 认证),并且具备 `sshx` 技能。它能有效回答关于目标仓库或组织的三个关键问题:当前真正值得推广的内容、跨仓库的关联关系,以及哪些看似诱人的声明实际上无法验证。其关键流程包括:首先通过内置脚本获取实时 GitHub 状态包(仅依赖此唯一证据源),然后调用 `sshx` 机制(使用推广性、跨仓库关联和怀疑论/过度声明检测三种独立视角)运行共识,最后生成包含“目前可推广”、“关联关系”和“已丢弃(无法验证)”三个部分的看板。该工具内置安全机制,默认仅扫描公开仓库,私库访问需要用户明确确认。

兼容平台~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/ChronoAIProject/nyx-skills/tree/HEAD/promo-scout

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

promo-scout

通用的、验证优先的推广情报工具。它与炒作抓取器截然相反:没有实时 GitHub 状态作为证据,任何内容都不会进入看板;判断由 sshx 共识(隔离视角 + 真值表)做出,而非仅凭单一模型的断言。

要求:gh 已通过现有 GitHub 认证进行认证(通过 gh auth login 或 GH_TOKEN),并且调用者可以使用 sshx 技能。

何时使用

当代理或操作者希望针对目标仓库/组织了解以下信息时:当前真正值得推广的内容、跨仓库的关联关系,以及哪些看似诱人的声明实际上无法验证。

步骤 0 — 向用户确认明确的范围

没有宽泛的账号级默认值。要求用户指定:

  • 整个组织(默认仅公开仓库),
  • 一个或多个特定仓库(所有者/仓库),或
  • 混合列表。 同时确认组织目标时的 REPO_LIMIT(默认为最近活跃的 12 个公开仓库)。私库收集需要用户明确选择加入,必须使用 --include-private 标志;除非用户已确认,否则不得使用该标志。

步骤 1 — 获取实时状态(确定性的;可在任何地方运行)

使用明确的目标运行内置抓取器:

python3 scripts/promo_scout_fetch.py <org | owner/repo> [更多...]   # 公开/默认范围
python3 scripts/promo_scout_fetch.py --include-private <org | owner/repo> [更多...]   # 仅在明确确认后

它会写入 /tmp/promo_scout_bundle.json:每个仓库的 README 头部、最近的提交、发布版本、打开的 PR、最近的问题。这是共识步骤唯一可以使用的证据。

步骤 2 — 对数据包运行真正的 sshx 共识

调用 sshx 技能(工人委托、隔离视角、codex-cli 工人),并将数据包作为固定输入,做出以下决策:

仅依据此实时 GitHub 状态包,生成三个列表。(1)可推广:当前真正值得推广的项目——每个项目必须引用数据包中的具体证据(发布标签、带日期的提交、README 功能)。(2)关联关系:跨仓库链接,其中一个仓库的工作与另一个仓库的工作相关联,每个链接都应有数据包中的真实信号支持(共享的 PR、依赖关系提及、互补功能)。(3)已丢弃:数据包不支持的那些诱人声明,需注明缺失的证据。不得过度声明;如果证据缺失,则归入“已丢弃”,而非“可推广”。

使用不同的 sshx 思考视角,例如:推广性视角、跨仓库关联视角以及怀疑论/过度声明检测视角。要求根据 sshx 真值表达成收敛;当工人无法确立某个声明时,应遵循 abstain(弃权)。

步骤 3 — 输出看板

将达成一致的结果以看板形式写出(Markdown + 可选 JSON):## 可推广、## 关联关系、## 已丢弃(无法验证)。每个可推广/关联项目都内嵌其数据包证据。“已丢弃”列表是必须的——它代表了看板的可信度。

护栏

  • 没有证据就不得发布。实时数据包是唯一的来源;不得使用外部记忆,不得夸大数字。
  • 关联关系/综合结论必须从对实时状态的共识中涌现出来——不得注入预先编写的叙事。
  • 本质上的诚实:无法验证 → 已丢弃;当无法达成共识时,报告 abstain(弃权),而非猜测。

Individual skills in this repo

This repo contains 9 individual skills — each has its own dedicated page.

ChronoAIProject/aevatar-attachment-probe

Boundary test for inbound Lark attachments — the user sends an image or file alongside this command and the bot reports exactly what it can observe on the chat path (text only, attachment refs, or nothing), without guessing. Detects when the platform wires chat-path attachment visibility so dependent skills can be upgraded.

ChronoAIProject/aevatar-vision-probe

Verify the read-image (vision) path end to end — the user sends an image plus the trigger, a workflow vision step describes it, and the run output proves the model actually saw the image (a real description, not "no image received"). Run it before any image-dependent workflow (petty-cash receipt, invoice OCR).

ChronoAIProject/codex-formal-answer

Use when answering mathematical, conceptual, philosophical, or metaphysical questions through repository-first scientific reasoning, a clause-complete formal bridge, retained exact Lean specializations, reusable library growth, and an ordinary conversational answer; the formal work stays internal and is shown only when the user asks for it.

ChronoAIProject/lark-im-ops

Send, reply to, react to, read, and find Lark messages and chats through the bot's NyxID-brokered im/v1 APIs — proactively post to a chat or DM, thread-reply, add or remove emoji reactions, read a single message or pull a chat's history over a time window, search or list the chats the bot is in, and download an image/file from a message. Handles the "content must be a JSON string" footgun and receive_id_type selection, and doubles as the im-scope probe — on a scope 403 it reports the exact missing permission instead of failing silently.

ChronoAIProject/nyx-skills

Method for producing short vertical videos from ChatGPT image generation through a fixed browser tab, local TTS narration, timed subtitle burn-in, cover exports, and a manifest. Use when an operator needs a reproducible image-to-short workflow with pinned session consistency, per-beat visual prompts, 1080x1920 safe-area rules, local ffmpeg/PIL assembly, and private access kept outside the skill.

ChronoAIProject/ornn-agent-manual-cli

The manual an AI agent loads to operate Ornn — the model-agnostic skill-lifecycle API (an npm-style registry + CLI for agent skills) — via the NyxID CLI (`nyxid proxy request ornn-api …`). Load and follow this skill WHENEVER the user asks to do anything with Ornn skills or skillsets. Skills: search Ornn or find a skill, pull or install a skill (or a specific version), run a skill, build and upload a skill, publish a new version, make a skill public / private / shared, run or read a security audit, deprecate or delete a version, diff two versions, check usage analytics, bind a skill to a NyxID service, link a skill to GitHub or sync from source, manage npm-style dist-tags, or transfer skill ownership. Skillsets — curated multi-skill bundles with a required master prompt: bundle skills into a set, create or publish a skillset, resolve its closure in one call, export a skillset as a Claude Code marketplace plugin, transfer skillset ownership, or diagnose why a shared skillset isn't visible (visibility derives fr

ChronoAIProject/petty-cash-approval-payload-builder

Runs the petty-cash approval flow end to end yourself — collect Lark DM/sheet/image context, extract receipt details, build the exact approval body, then SUBMIT the Lark approval instance.

ChronoAIProject/public-copy-release-guard

Portable checklist for gating public-facing copy before release. Use when captions, posts, manifests, topics, titles, or launch copy must be checked for generic AI wording, leaked internal labels, forbidden experiment or tool names, platform topic allowlists, CTA spam, and unsupported overclaims.

ChronoAIProject/research-claim-fidelity-reviewer

Severity-weighted BLOCK, WARN, OK reviewer method for technical and research posts. Use when reviewing X threads, announcements, captions, or launch copy for hook strength, thread arc, generic AI vocabulary, source fidelity, claim support, numeric-claim verification, and thread format before recommending publish.

相关技能