跳到正文
cccskills
免费在 GitHub 公开中文介绍

OpenSourceManagement

检查配置中登记的 GitHub 仓库,整理议题、拉取请求和讨论的处理优先级,并提供后续行动与回复建议。还可比较 Ollama 新模型与本地模型,并审查私有仓库的公开准备情况。

原文查看原文说明

Triages open issues, pull requests and GitHub Discussions across the principal's own open-source repos (the list in Config.md) via the gh CLI, ranks what needs attention with suggested replies, posts edit-in-place marker comments, diffs new Ollama library models against a local model box, and takes a private repo public (readiness audit, fresh-history export, README and social image), stopping at the principal's go-ahead. USE WHEN open source issues, pull requests, check PRs, review PRs, check issues, community discussions, community activity, what needs attention, open source state, marker comment, triage comment, new open source models, latest open-weight models, what should I pull into Ollama, do we have this model, new Ollama models, local models, is this repo public-ready, take this repo public, open source this, public release on GitHub. NOT FOR triaging repos outside the configured list, LifeOS releases, internal work trackers, or running/prompting local models.

danielmiessler/LifeOS星标 19,635(GitHub 19,635 + cccskills 0)
集成工具GitHub

实测评分 未实测

查看安装方法

适用场景

  • 整理议题的处理顺序
  • 找出需要审查的拉取请求
  • 查看多个仓库的活动情况
  • 比较 Ollama 新模型与本地模型
  • 审查仓库是否准备好公开

中文介绍

功能

此技能会检查配置文件中登记的开源仓库里的 GitHub 议题、拉取请求和讨论,并根据紧急程度与影响排列处理顺序。它会给出下一步行动和回复建议,也能汇总多个仓库的活动情况。对于需要反复更新的说明,它会编辑带有标记的现有评论,而不是不断添加新评论。它还可以将 Ollama 模型库中的新模型与本地模型环境进行比较,确认哪些模型尚未安装。准备公开私有仓库时,它会审查准备情况,并协助准备全新提交历史的导出内容、README 和社交媒体预览图片。

适用场景

需要了解哪些社区问题应优先处理、找出需要审查的拉取请求,或查看多个公开仓库的活动时,可以使用此技能。它也适用于比较适合本地环境的 Ollama 新模型,以及检查私有仓库的公开准备情况。

使用示例

  • “请检查我登记的仓库中的议题和拉取请求。”
  • “widget 仓库中有没有需要处理的拉取请求?”
  • “请审查这个仓库是否已经准备好公开。”

注意事项

检查范围仅限配置文件中登记的仓库。GitHub 操作通过 gh CLI 执行,首次使用前需要完成登录设置。模型比较可以选择使用本地模型环境的配置。只有准备情况审查结果为 READY,并且你指定了要公开的仓库后,才会继续公开操作。

本介绍由 AI(OpenAI Codex)根据公开的 SKILL.md 撰写。准确的规格请查看下方原文。

文档检查

AI 根据 SKILL.md 的内容检查了需要注意的操作和使用前提。评分只依据实际运行的结果(实测对比)。

安全性发送数据、删除文件、执行命令等是否有说明
A良好公开操作须先得到 READY 审查结果,并由用户指定仓库。
安装难易度所需工具和 API 密钥是否少且有说明
B部分不足需要配置 Config.md 并登录 gh;首次设置步骤见 Setup.md。

不计入评分。 由 AI(OpenAI Codex)于 2026年10月28日 评估。仅供参考,安装前请同时查看原文。

如果您认为评估有误,请申请复核

请写明哪一项有误以及原因。无需登录。我们会对照 SKILL.md 重新评估,并在此处更新结果。

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

包含的文件(17)

  • SKILL.md10.2 KB
  • Intents/CheckDiscussions.md4.7 KB
  • Intents/CheckIssues.md4.1 KB
  • Intents/CheckPullRequests.md4.9 KB
  • Intents/CheckState.md6.1 KB
  • Intents/GoPublic.md9.8 KB
  • Intents/LocalModels.md2.2 KB
  • Intents/PostMarkerComment.md5.6 KB
  • Setup.md4.5 KB
  • Tools/Fetch.help.md2.3 KB
  • Tools/Fetch.ts10.5 KB
  • Tools/LocalModels.help.md3.1 KB
  • Tools/LocalModels.ts9.7 KB
  • Tools/LocalModelsLib.ts4.8 KB
  • Tools/MarkerComment.ts10.6 KB
  • Tools/PublicReady.help.md4.0 KB
  • Tools/PublicReady.ts27.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

OpenSourceManagement

Contents: Ideal State · Intent Routing · Repos · Quick Reference · Data & Config · Gotchas · Examples

Triages and manages GitHub activity across the principal's open source repos, the OSS_REPOS list in Config.md. Repos outside that list are out of scope; when Config.md routes one elsewhere (for example a repo another skill triages), point there. Through the gh CLI it checks and prioritizes issues, recommends which PRs to merge or review, reads discussions, gives a cross-repo state snapshot, and posts a single bot comment that edits in place via hidden HTML markers instead of stacking new comments each time.

Ideal State

  • Every report comes from this session's live gh fetch, structured per repo, with items ranked by urgency and impact, each repo's community mood rated (positive, neutral, negative), and specific next actions with suggested responses, written direct and actionable.
  • A fetch that failed or hit its limit is named as a hole or a truncation, never rendered as a quiet repo.
  • No public "fixed", "merged" or "done" claim goes out before the change lands in the source of truth (Gotchas: FIX-IN-SOURCE-FIRST), and a recurring bot note is one marker comment edited in place, never a stack.
  • A private repo goes public only as an audited, fresh-history export that reads READY, with a problem-first README, a license and a social preview image, and only on the principal's word naming that repo.
  • Local-model checks name what is new in the Ollama library, whether each fits and is already on the local model box, and leave every pull to the principal.

Intent Routing

IntentTriggerFile
CheckIssues"check issues", "open source issues", "<repo> issues"Intents/CheckIssues.md
CheckPullRequests"check PRs", "pull requests", "review PRs", "open PRs"Intents/CheckPullRequests.md
CheckDiscussions"check discussions", "community discussions", "what are people asking"Intents/CheckDiscussions.md
CheckState"open source state", "project state", "check our open source", "what needs attention"Intents/CheckState.md
PostMarkerComment"post triage comment", "leave a marker comment", "edit-in-place comment", "update bot comment", "upsert comment"Intents/PostMarkerComment.md
LocalModels"new open source models", "latest open-weight models", "what should I pull", "do we have <model>", "new Ollama models"Intents/LocalModels.md
GoPublic"is X public-ready", "take this repo public", "open source this", "prep X for public release"Intents/GoPublic.md
FileRead when
Tools/Tools/Fetch.help.md holds the triage fetch's kinds, flags, config keys and hole semantics; Tools/LocalModels.help.md holds LocalModels flags and column semantics; Tools/PublicReady.help.md holds every public-readiness check and the export contract
Setup.mdfirst-time setup: Config.md keys, the gh login, the optional model host, a proof command

Repos

The repos come from Config.md, never from this skill:

OSS_OWNER: <github login or org>
OSS_REPOS: <repo>, <repo>, <repo>
OSS_PRIORITY: <repo>        # optional: triaged first in batch work

Tools/Fetch.ts reads OSS_OWNER and OSS_REPOS at run time and loops over the list in the order written; --repo <name> narrows to one listed repo and refuses any other. Every intent's per-repo section repeats once per listed repo. Config.md § Source of truth and § Out of scope carry the per-repo routing the gotchas below rely on.

Quick Reference

# The one live fetch every triage intent pre-injects (JSON; a failed call is a hole, never an empty list)
bun ~/.claude/skills/OpenSourceManagement/Tools/Fetch.ts <issues|prs|discussions|stats>... [--repo <name>] [--limit N] [--brief]

# Marker-backed comment upsert (edit-in-place, never stack)
bun run ~/.claude/skills/OpenSourceManagement/Tools/MarkerComment.ts \
  upsert <owner>/<repo> <number> <marker-id> <body-file> [--dry-run]
bun run ~/.claude/skills/OpenSourceManagement/Tools/MarkerComment.ts \
  find <owner>/<repo> <number> <marker-id>

# Is a repo safe to publish, and its clean fresh-history export (never pushes)
bun ~/.claude/skills/OpenSourceManagement/Tools/PublicReady.ts audit <repo> [--json] [--no-build]
bun ~/.claude/skills/OpenSourceManagement/Tools/PublicReady.ts export <repo> --out <empty-dir>

# Newest Ollama library models vs the local model box (host from Config.md)
bun ~/.claude/skills/OpenSourceManagement/Tools/LocalModels.ts [--json] [--limit N] [--host <ssh>] [--local]

Data & Config

Everything install-specific lives in LIFEOS/USER/CUSTOMIZATIONS/SKILLS/OpenSourceManagement/Config.md; first-time setup and a proof command are in Setup.md.

  • OSS_OWNER, OSS_REPOS, OSS_PRIORITY — KEY: value lines; Tools/Fetch.ts reads the first two.
  • ## Source of truth — prose naming any listed repo that is generated or synced from another tree, and where that tree is. Read it before any fix.
  • ## Out of scope — prose naming repos this skill must not triage and where they go instead.
  • ## Local Model Host — the local model box's ssh alias and ollama binary; Tools/LocalModels.ts reads that table at run time; no hostnames live in this skill.

When OSS_OWNER or OSS_REPOS is missing, Fetch.ts prints an ERROR: line and fetches nothing; point the principal at Setup.md.

Gotchas

  • FIX-IN-SOURCE-FIRST. Every accepted change — a PR merge, an issue fix, a discussion-driven change — lands in the code's actual source of truth BEFORE any public "fixed/merged/done" response. The two halves are one action: fix in source + respond publicly. Source-of-truth routing comes from Config.md § Source of truth:
    • A repo not named there is its own source of truth: direct merges on the public repo stand. If the change also touches a local copy Config.md says mirrors that repo (vendored code, docs or tools that reference it), update the local copy in the same pass.
    • A repo named there as generated or synced from another tree (a release script that rebuilds the public repo from a private source, for example) never takes a merge on the public repo: port the change into the named source first, credit the contributor, and close the PR; the next sync carries it. A change made only on the public repo is wiped by the next sync.
    • "Already fixed" closes require verifying the fix is present in the source of truth this session (Read/diff evidence), not just absent from public main.
  • Covers the OSS_REPOS list only. Not every repo the owner has; a repo in Config.md § Out of scope goes where that section says.
  • Community sentiment can be negative during breaking changes. Frame triage responses constructively.
  • Batch work starts with OSS_PRIORITY when it is set, usually the repo with the most community activity.
  • Use marker comments for any rolling bot-authored note. The default gh issue comment posts a new comment every time — wrong for triage status, weekly digests, per-PR summaries. Reach for PostMarkerComment instead. Marker IDs must be <intent>-<purpose> and unique per (issue, kind); two intents MUST NOT share a marker on the same issue or they will overwrite each other.
  • LocalModels scrapes ollama.com HTML; there is no public JSON API for the library. Class names drift, and the served HTML splits tag attributes across lines, so the parser collapses ALL whitespace before matching; normalizing newlines alone leaves every size and capability blank. Every field is best-effort: a blank column is a parser miss, not a missing model. Fix the regex, never hard-fail.
  • A library model's VRAM fit is on total params, not active. MoE models load every expert. A 118B-A8B model is a 118B load.
  • Always --dry-run first against a public community repo. Comment bodies are public and permanent in the timeline even after edit. Inspect the body, confirm the marker ID, then drop --dry-run.

Examples

Example 1: Check all open source state

User: "Let's look at our open source issues"
→ Invokes CheckState intent
→ Fetches issues, PRs, discussions across every repo in OSS_REPOS
→ Analyzes sentiment and priority
→ Returns comprehensive state report with recommendations

Example 2: Check one repo's issues

User: "Check widget issues"   (widget is in OSS_REPOS)
→ Invokes CheckIssues intent
→ Fetches open issues from $OSS_OWNER/widget (--repo widget)
→ Categorizes by type (bug, feature, question)
→ Returns prioritized list with recommended responses

Example 3: Review pull requests

User: "Any PRs need attention on widget?"
→ Invokes CheckPullRequests intent
→ Fetches open PRs from $OSS_OWNER/widget
→ Summarizes each PR's purpose and status
→ Recommends which to merge, review, or discuss

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

AnnualReports

免费有简介

按类别或厂商查找并获取网络安全报告,比较威胁、勒索软件、数据泄露、云安全和AI趋势。分析会注明每项数据的厂商、年份及报告,并分别呈现来源间的分歧。

  • 按类别查找威胁报告
  • 获取指定厂商的报告
  • 比较多家厂商的勒索软件趋势
danielmiessler/LifeOS2万2026年10月28日 更新

ApertureOscillation

免费有简介

通过三轮分析,对比单个功能或组件的设计需求与整个系统的目标,梳理两者的冲突、合适的实现范围,以及方案是否符合整体方向。

  • 判断服务或库是否应拆分
  • 比较功能需求与产品方向
  • 检查新组件是否符合现有系统
danielmiessler/LifeOS2万2026年10月28日 更新

Aphorisms

免费有简介

按文章主题寻找格言或引文,按相关程度排序,并附上作者和推荐理由。可添加带出处的引文、按主题研究思想家的言论、整理使用记录,帮助避免重复引用。

  • 为新闻简报寻找引文
  • 保存有出处且不重复的引文
  • 按主题研究思想家的言论
danielmiessler/LifeOS2万2026年10月28日 更新

Art

免费有简介

按用途选择制作流程,生成博客插图、技术图解、比较图、漫画和图标等视觉内容,并输出供预览的图像。

  • 制作博客标题图
  • 解释系统结构
  • 展示比较或时间线
danielmiessler/LifeOS2万2026年10月28日 更新

ArtDirection

免费有简介

依据简报和制作标准评估图片、影片、幻灯片及网站页面截图,由视觉评审给出评分和缺陷优先级,支持有限轮次的修改;通过评审后才能交付,并可记录人工评分供后续校准。

  • 按优先级整理图片修改项
  • 依标准评估影片或幻灯片
  • 发布前检查视觉效果
danielmiessler/LifeOS2万2026年10月28日 更新

ArXiv

免费有简介

按主题、研究领域或论文编号查找 arXiv 论文,并整理标题、作者、摘要和链接;查看新投稿,也可在有内容时获取 AlphaXiv 的人工智能生成概述。

  • 查看人工智能和机器学习新论文
  • 查找特定主题的论文
  • 按论文编号或 arXiv 网址查询
danielmiessler/LifeOS2万2026年10月28日 更新

查看 danielmiessler 的全部技能

报告此技能的问题