awesome-repo-maintainer-zh

awesome-repo-maintainer-zh is a skill for Claude Code, Codex from gy910210/hermes-research-skills. It costs 80 tokens per session (876 once invoked), scanned A, original, MIT.

A maintenance skill for long resource lists in Awesome-style files and repository README pages. It compares supporting documents with the catalogue and prepares structured update instructions.

In plain words
What is it for?
Use it to compare documents with an existing resource page, identify additions and corrections, and produce a catalogue update packet or normalized page.
Why use it?
It helps find missing or duplicated entries and keeps titles, sources, dates, notes, and sections consistent across a curated list.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to compare documents with an existing resource page, identify additions and corrections, and produce a catalogue update packet or normalized page.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gy910210/hermes-research-skills/awesome-repo-maintainer-zh
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add gy910210/hermes-research-skills --skill awesome-repo-maintainer-zh
Clone the repo
git clone --depth 1 https://github.com/gy910210/hermes-research-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for awesome-repo-maintainer-zh

README.md
[![agentmods](https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/awesome-repo-maintainer-zh/github.svg)](https://agentmods.dev/skills/gy910210/hermes-research-skills/awesome-repo-maintainer-zh)
Your own site
<a href="https://agentmods.dev/skills/gy910210/hermes-research-skills/awesome-repo-maintainer-zh"><img src="https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/awesome-repo-maintainer-zh/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for awesome-repo-maintainer-zh

Your own site · 80×15
<a href="https://agentmods.dev/skills/gy910210/hermes-research-skills/awesome-repo-maintainer-zh"><img src="https://agentmods.dev/badge/skills/gy910210/hermes-research-skills/awesome-repo-maintainer-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 876 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.00876
Opus 5 $0.00040 $0.00438
Sonnet 5 $0.00016 $0.00175
Haiku 4.5 $0.00008 $0.00088

Measured 12d ago against content hash 1fd3363574ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

awesome-repo-maintainer-zh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/awesome-repo-maintainer-zh/SKILL.md · 73 lines

What it actually says

Hermes 适配说明

  • 本 skill 现面向 Hermes 使用,优先依赖 Hermes 原生工具:search_filesread_filewrite_filepatchsession_searchdelegate_taskcronjobbrowserweb/searchvision
  • 若正文提到 references/...scripts/...,优先读取当前 skill 目录下对应文件,不再依赖 Claude 专属目录结构。
  • 原始 Claude agents/openai.yaml 不作为执行前提;需要并行研究、分工精读或角色评审时,改用 Hermes 的 delegate_task
  • 保留原有研究方法论与产物契约,但执行层统一按 Hermes 工具体系落地。

Awesome Repo Maintainer(中文)

这个 skill 负责维护 awesome-*.md、repo README 和长列表资源页。
它不是知识库主稿维护器,而是 curated catalog / repo page 维护器。

何时使用

  • 已有一个 awesome-*.md 或 README 形式的论文资源页。
  • 中文增强版资源页、专题稿、周度增量稿里出现了新论文,想同步回 repo 页面。
  • 想统一补齐标题、来源、发布日期、一句话说明、章节归类。
  • 想检查“支持文档里有、repo 页面里没有”的遗漏条目。

输入

  • catalog_file
  • support_docs[]
  • normalization_policy
    • title_style
    • source_and_date_required
    • one_line_note_required
  • sync_goal
    • diff_only
    • append_missing
    • normalize_all
    • restructure_sections

输出

  • catalog_update_packet
    • missing_entries[]
    • duplicate_entries[]
    • normalization_fixes[]
    • section_moves[]
    • ready_to_apply_entries[]
    • unverifiable_candidates[]
  • normalized_repo_page

工作流

  1. 先读取现有 repo 页面,识别现有章节树、条目格式和元数据规范。
  2. 读取支持文档,提取其中已经稳定出现的论文、benchmark、dataset、challenge 条目。
  3. 做差分检查:
    • 支持文档里有、repo 页面里没有
    • repo 页面里有,但 source/date/一句话说明不完整
    • 同一论文在多个章节重复出现
  4. 对每个候选条目执行规范化:
    • 标题
    • 链接
    • Source
    • Published
    • 一句话说明
    • 推荐章节
  5. 对无法稳定核实的条目,放入 unverifiable_candidates,不要硬写入正式 repo 页面。
  6. 如果主题已经有资源页、增强版目录页或配套深度分析稿,优先做 paired sync,而不是只对单一文件更新。

守护

  • repo 页面优先短、准、可维护,不把长分析直接灌进去。
  • 不把中文分析稿的综合判断直接写成 repo 页面里的论文结论。
  • 如果 publication/source 还不能核实,宁可不加,也不要伪精确。
  • 标题风格统一,但不擅自改论文原始标题含义。

推荐产出形式

  • 一个 missing_entries + normalization_fixes 差分表
  • 一份更新后的 repo 页面草稿
  • 一个“哪些条目仍待验证”的小结
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 73 lines · 80 tokens per session scan A 1fd3363574ab

Subscribe to this mod's changes

awesome-repo-maintainer-zh is a skill published in the GitHub repository gy910210/hermes-research-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 80 tokens to every session and 876 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.