New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Update Crawl Benchmark

by JunieXD in JunieXD/AutoEmailSender

Safely merge one or more computers' local Auto Email Sender crawl databases into the public website benchmark JSON, normalize confirmed school aliases, verify privacy and data invariants, and run…

GPL-3.0Auto-check passedDocuments & Office

Install Update Crawl Benchmark

skills CLI
$ npx skills add JunieXD/AutoEmailSender --skill update-crawl-benchmark -a claude-code

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

GitHub CLI
$ gh skill install JunieXD/AutoEmailSender update-crawl-benchmark --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/JunieXD/AutoEmailSender.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/update-crawl-benchmark .claude/skills/update-crawl-benchmark && 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
update-crawl-benchmark
GitHub stars
149
Token cost
~719 tokens
SKILL.md length
331 words
Files
2
Skills in repo
5
Repo updated
First seen
Licence
GPL-3.0

At a glance

Safely merge one or more computers' local Auto Email Sender crawl databases into the public website benchmark JSON, normalize confirmed school aliases, verify privacy and data invariants, and run…

  • Works in 6 steps: Identify the requested database;… → Check… → From backend/, run → …
  • The user asks to update
  • Calls uv and npm
  • Validate the official 智能抓取效果展示 data from a local autoemailsender.db

What it does

Update Crawl Benchmark is an agent skill from JunieXD/AutoEmailSender. Safely merge one or more computers' local Auto Email Sender crawl databases into the public website benchmark JSON, normalize confirmed school aliases, verify privacy and data invariants, and run backend and website checks. Use when the user asks to update, upload, refresh, merge, or validate the official 智能抓取效果展示 data from a local autoemailsender.db or the historical XLSX.

Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Documents & Office, covering Excel spreadsheets. It works with Microsoft Excel. The repository describes itself as: AutoEmailSender 是一个专为套磁场景设计的智能邮件助手. The licence is GPL-3.0.

When your agent uses it

  • The user asks to update
  • Validate the official 智能抓取效果展示 data from a local autoemailsender.db
  • The historical XLSX

Example prompts

  • “/update-crawl-benchmark”

Requirements

  • Python 3

Workflow steps

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

  1. Identify the requested database; omitting it uses the desktop app's standard data directory. Bring the public JSON up to date with the…
  2. Check config/crawl-benchmark-aliases.json. Add university/school aliases only when supported by the source or confirmed by the user.
  3. From backend/, run
  4. Read changes.added/updated/retained/removed, changed, and next_action. If the requested update has changes, rerun the same arguments…
  5. Review the diff: existing records from other machines remain, same-job enrichment updates retain recordId, aliases are correct, and only…
  6. Run uv run python -m unittest test.test_crawl_benchmark_publication in backend, then npm run test and npm run build in website. Report…

What it can do on your machine

Read from SKILL.md and the folder at commit 5b04197. 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

    Shell commands in SKILL.md call:

    • uv
    • npm

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

  • Network

    No URLs in SKILL.md. Its commands use uv and npm, which can reach the network depending on how they are called.

    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

Update Crawl Benchmark loads about 719 tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 331 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~719

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 JunieXD/AutoEmailSender at commit 5b04197, republished under its GPL-3.0 licence (© JunieXD). 331 words, ~719 tokens.

Download SKILL.mdSave it as .claude/skills/update-crawl-benchmark/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
update-crawl-benchmark
description
Safely merge one or more computers' local Auto Email Sender crawl databases into the public website benchmark JSON, normalize confirmed school aliases, verify privacy and data invariants, and run backend and website checks. Use when the user asks to update, upload, refresh, merge, or validate the official 智能抓取效果展示 data from a local auto_email_sender.db or the historical XLSX.

Update Crawl Benchmark Data

Merge local crawl aggregates into website/data/crawl-benchmark.json. Read docs/operations/crawl-benchmark-publication.md when changing publication behavior or resolving a schema, merge or privacy issue.

  1. Identify the requested database; omitting it uses the desktop app's standard data directory. Bring the public JSON up to date with the remote version while preserving unrelated edits.

  2. Check config/crawl-benchmark-aliases.json. Add university/school aliases only when supported by the source or confirmed by the user.

  3. From backend/, run:

    bash
    uv run python ../scripts/data/update_crawl_benchmark.py --json --dry-run

    Use --database <absolute-path> for another computer and --legacy-xlsx <absolute-path> only for requested historical data or its initial migration. Preview reads the same existing public JSON as execution. Do not use a new --output path as a preview: it would select a different merge baseline.

  4. Read changes.added/updated/retained/removed, changed, and next_action. If the requested update has changes, rerun the same arguments without --dry-run. An unchanged run preserves the file and its generation time. Errors return ok: false, code and next_action with exit code 2; fix the named input instead of rebuilding or discarding existing history.

  5. Review the diff: existing records from other machines remain, same-job enrichment updates retain recordId, aliases are correct, and only aggregate fields are published. Enrichment progress uses all candidates as its denominator.

  6. Run uv run python -m unittest test.test_crawl_benchmark_publication in backend, then npm run test and npm run build in website. Report changed counts, aliases still needing evidence (if encountered) and verification results. The script does not infer unconfirmed aliases. Commit or publish according to the user's request.

The script opens the database read-only. Do not migrate, edit or publish it. Names, emails, logs, prompts and database paths do not belong in public output.

The output is Schema 3; existing Schema 2/3 JSON is an input: retain other machines' records. After a conflicting remote update, integrate it and rerun the script, rather than selecting one side. Local numeric job IDs alone are not global identities. A schema 1 upgrade needs the primary history database; see the operations guide before rebuilding that baseline.

© JunieXD, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .codex/skills/update-crawl-benchmark of JunieXD/AutoEmailSender.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 5b04197

Compare with similar skills

Update Crawl Benchmark 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.

Update Crawl Benchmark compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Update Crawl Benchmark this skillJunieXD/AutoEmailSender149—~719Automated safety check: PassGPL-3.0
Excel Unmerge Before WriteHKUDS/OpenSpace7.7k—~820Automated safety check: PassMIT
MarkitdownImCa0/just-laws78114 repos~3.2kAutomated safety check: NotesMIT
Data Table Managern8n-io/n8n207k—~2.3kAutomated safety check: PassCustom licence
Docx4jplutext/docx4j2.4k—~2.5kAutomated safety check: PassNone
Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences2742 repos~2.7kAutomated safety check: PassApache-2.0

Similar skills

  • Excel Unmerge Before Write

    HKUDS/OpenSpace

    Unmerge merged cells in openpyxl worksheets before writing values to avoid AttributeError

    7.7k GitHub stars~820 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed

  • Markitdown

    ImCa0/just-laws

    Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.

    781 GitHub starsUsed in 14 repos~3.2k tokens
    Documents & OfficeAuto-check: notes

  • Data Table Manager

    n8n-io/n8n

    Official

    Load before calling data-tables or parse-file. An agent skill from n8n-io/n8n.

    207k GitHub stars~2.3k tokensUpdated today
    Documents & OfficeAuto-check passed

  • Docx4j

    plutext/docx4j

    A skill your agent uses when writing Java code that creates, reads or edits Word (.docx), PowerPoint (.pptx) or Excel (.xlsx) files with docx4j — including generating documents, editing existing…

    2.4k GitHub stars~2.5k tokensUpdated yesterday
    Documents & OfficeAuto-check passed

  • Instrument Data To Allotrope

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.

    274 GitHub starsUsed in 2 repos~2.7k tokens
    Documents & OfficeAuto-check passed

  • Cyber Ppt

    crazyykhllc-bit/CyberPPT

    当用户需要把 DOCX、PDF、TXT、XLSX、研究报告、业务材料或原始数据转成高密度、可编辑、咨询风格 PPTX 时使用；也适用于需要 SCR 论证、视觉风格探索、详细图表和渲染质检的 PPT。

    1.8k GitHub stars~10k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed

More from JunieXD/AutoEmailSender

  • Submit Mentors To Community

    JunieXD/AutoEmailSender

    校验、准备并通过外部 Git/gh 创建社区导师投稿 draft PR，支持查重与恢复。Use when a maintainer asks to submit, contribute, or batch-submit verified mentor/professor XLSX data to the community mentor library.

    149 GitHub stars~471 tokensUpdated 1 mo ago
    Auto-check passed

  • Crawl Mentors To XLSX

    JunieXD/AutoEmailSender

    从学校、学院、系所或实验室官网抓取公开导师/教师信息，核对个人主页与证据来源，并生成经过自动校验、可直接导入 Auto Email Sender 的 XLSX。Use when a user provides faculty, professor, mentor, supervisor, university, department, or lab directory URLs and…

    149 GitHub stars~429 tokensUpdated 1 mo ago
    Auto-check passed

  • Auto Email Sender Release

    JunieXD/AutoEmailSender

    A skill your agent uses when preparing, certifying, publishing, recovering, monitoring, or verifying an AutoEmailSender release; releasing repository-delivered Skills such as crawl-mentors-to-xlsx…

    149 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Auto Email Sender

    JunieXD/AutoEmailSender

    Operate Auto Email Sender through its local CLI for mentor and correspondence queries, drafts, campaigns, crawling, diagnosis, and confirmed email delivery.

    149 GitHub stars~938 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Update Crawl Benchmark

What does Update Crawl Benchmark do?

Safely merge one or more computers' local Auto Email Sender crawl databases into the public website benchmark JSON, normalize confirmed school aliases, verify privacy and data invariants, and run…. Update Crawl Benchmark is an agent skill from JunieXD/AutoEmailSender. Safely merge one or more computers' local Auto Email Sender crawl databases into the public website benchmark JSON, normalize confirmed school aliases, verify privacy and data invariants, and run backend and website checks.

When should I use Update Crawl Benchmark?

Update Crawl Benchmark fits situations like: the user asks to update; validate the official 智能抓取效果展示 data from a local autoemailsender.db; the historical XLSX.

How do I install Update Crawl Benchmark in Claude Code?

Run `npx skills add JunieXD/AutoEmailSender --skill update-crawl-benchmark -a claude-code`. Or copy the skill folder (.codex/skills/update-crawl-benchmark in JunieXD/AutoEmailSender) into .claude/skills/update-crawl-benchmark in your project. Claude Code loads it when a task matches its description.

How do I install Update Crawl Benchmark in Codex?

Run `npx skills add JunieXD/AutoEmailSender --skill update-crawl-benchmark -a codex`. Or copy the skill folder (.codex/skills/update-crawl-benchmark in JunieXD/AutoEmailSender) into .agents/skills/update-crawl-benchmark in your project. Codex loads it when a task matches its description.

Can I use Update Crawl Benchmark 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 JunieXD/AutoEmailSender --skill update-crawl-benchmark -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/update-crawl-benchmark, .gemini/skills/update-crawl-benchmark, .github/skills/update-crawl-benchmark and .opencode/skills/update-crawl-benchmark in your project.

What does Update Crawl Benchmark need to run?

Going by SKILL.md and its folder, Update Crawl Benchmark needs the command-line tools its instructions call (uv and npm). Our summary lists: Python 3.

Does Update Crawl Benchmark access the network?

SKILL.md contains no URLs. Its commands use uv and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Update Crawl Benchmark 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 Update Crawl Benchmark use?

Update Crawl Benchmark is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Update Crawl Benchmark use?

About 719 tokens (SKILL.md is roughly 2.9k 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 Update Crawl Benchmark?

Skills that share tags, products or a category with Update Crawl Benchmark: Excel Unmerge Before Write (HKUDS/OpenSpace, 7.7k stars), Markitdown (ImCa0/just-laws, 781 stars), Data Table Manager (n8n-io/n8n, 207k stars) and Docx4j (plutext/docx4j, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Update Crawl Benchmark?

JunieXD (a GitHub user) maintains it in JunieXD/AutoEmailSender, which has 149 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 6, 2026.

Source: JunieXD/AutoEmailSender on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.