Agent skill

Source Connector Authoring

by Bubble252 in Bubble252/offer-harvester

Design and validate safe source connector manifests for public graduate-admission, policy, advisor, lab, and community sources.

MITAuto-check passedData & Analytics

Install Source Connector Authoring

skills CLI
$ npx skills add Bubble252/offer-harvester --skill source-connector-authoring -a claude-code

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

GitHub CLI
$ gh skill install Bubble252/offer-harvester source-connector-authoring --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/Bubble252/offer-harvester.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/source-connector-authoring .claude/skills/source-connector-authoring && 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
source-connector-authoring
GitHub stars
123
Token cost
~379 tokens
SKILL.md length
151 words
Files
5 (incl. scripts, references)
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Design and validate safe source connector manifests for public graduate-admission, policy, advisor, lab, and community sources.

  • Works in 5 steps: Read references/manifest-schema.md… → Define a source-specific allowlist,… → Record robots/ToS review date and… → …
  • Adding a crawler
  • SKILL.md covers Hard Boundaries and 中文说明
  • Runs Python scripts from its folder

What it does

Source Connector Authoring is an agent skill from Bubble252/offer-harvester. Design and validate safe source connector manifests for public graduate-admission, policy, advisor, lab, and community sources. Use when adding a crawler, refresh job, source connector, source access policy, field mapping, live test, or safe fallback.

Its SKILL.md is about 380 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/manifest-schema.md` and `scripts/manifest_fixture.json`).

It sits in Data & Analytics, covering Web scraping. The licence is MIT.

When your agent uses it

  • Adding a crawler
  • Source connector
  • Source access policy

Example prompts

  • “/source-connector-authoring”

Requirements

  • Python 3

Workflow steps

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

  1. Read references/manifest-schema.md before creating or editing a connector.
  2. Define a source-specific allowlist, field mapping, refresh interval, rate limit, and fallback.
  3. Record robots/ToS review date and allowed access method.
  4. Use public pages, official APIs, or explicitly authorized exports only.
  5. Validate the manifest with scripts/validate_manifest.py --input .

What it can do on your machine

Read from SKILL.md and the folder at commit c640922. 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

    Ships 2 files in scripts/ (Python), which the agent can run.

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

  • Network

    No URLs in SKILL.md.

    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

Source Connector Authoring loads about 379 tokens when it runs, and up to ~514 if it reads all its reference files. Until then it costs about 70 tokens; SKILL.md has 151 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~379
With references · SKILL.md plus every file in references/, read only if the agent opens them
~514

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); the scripts in this folder are not scanned.

SKILL.md

The full file from Bubble252/offer-harvester at commit c640922, republished under its MIT licence (© Bubble252). 151 words, ~379 tokens.

Download SKILL.mdSave it as .claude/skills/source-connector-authoring/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
source-connector-authoring
description
Design and validate safe source connector manifests for public graduate-admission, policy, advisor, lab, and community sources. Use when adding a crawler, refresh job, source connector, source access policy, field mapping, live test, or safe fallback.

Source Connector Authoring

  1. Read references/manifest-schema.md before creating or editing a connector.
  2. Define a source-specific allowlist, field mapping, refresh interval, rate limit, and fallback.
  3. Record robots/ToS review date and allowed access method.
  4. Use public pages, official APIs, or explicitly authorized exports only.
  5. Validate the manifest with scripts/validate_manifest.py --input <manifest.json>.

Hard Boundaries

  • Do not bypass login walls, CAPTCHA, private-group access, robots controls, or rate limits.
  • Do not treat a community post as confirmed fact; emit it only as a reviewable risk signal.
  • Do not store full community content unless its source policy allows it and a deletion path exists.
  • Do not register a connector until its live test and human policy review pass.

中文说明

  1. 创建或编辑 connector 前先阅读 references/manifest-schema.md。
  2. 定义来源专属 allowlist、字段映射、刷新间隔、限速与失败 fallback。
  3. 记录 robots/ToS 审查日期和允许的访问方式。
  4. 只使用公开页面、官方 API 或明确授权的导出。
  5. 使用 scripts/validate_manifest.py --input <manifest.json> 校验 manifest。
强制边界
  • 不绕过登录墙、CAPTCHA、私密群组权限、robots 控制或限速。
  • 社区帖子不是确认事实,只能输出为待复核风险信号。
  • 除非来源策略允许且有删除路径,否则不保存完整社区正文。
  • connector 通过 live test 和人工策略审查前不得注册。

© Bubble252, MIT. 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 4 other files (scripts, references) in skills/source-connector-authoring of Bubble252/offer-harvester.

  • SKILL.md
  • agents/openai.yaml
  • references/manifest-schema.md
  • scripts/manifest_fixture.json
  • scripts/validate_manifest.py

Open the folder on GitHubat commit c640922

Compare with similar skills

Source Connector Authoring 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.

Source Connector Authoring compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Source Connector Authoring this skillBubble252/offer-harvester123—~379Automated safety check: PassMIT
Tmuxtrpc-group/trpc-agent-go1.8k24 repos~868Automated safety check: PassApache-2.0
Ketch1broseidon/ketch6971 repos~3.9kAutomated safety check: PassMIT
Crawl4AI Web Scrapingsmallnest/goclaw5981 repos~2.5kAutomated safety check: PassMIT
Boss Zhipin Scrapereatmoreduck/boss-zhipin-scraper1.5k—~2.6kAutomated safety check: PassMIT
Axyusukebe/ax7191 repos~918Automated safety check: PassMIT

Similar skills

  • Tmux

    trpc-group/trpc-agent-go

    Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

    1.8k GitHub starsUsed in 24 repos~868 tokens
    Data & AnalyticsAuto-check passed
  • Ketch

    1broseidon/ketch

    Research skill for ketch — a fast stateless CLI for web search, OSS code search, curated library docs, page scraping, and site crawling; an optional MCP server exists for operators who want it, but…

    697 GitHub starsUsed in 1 repo~3.9k tokens
    Data & AnalyticsAuto-check passed
  • Crawl4AI Web Scraping

    smallnest/goclaw

    Scrapes sites, handles JavaScript-heavy pages and extracts structured data with Crawl4AI, through its crwl CLI or Python SDK, including schema-based extraction without an LLM.

    598 GitHub starsUsed in 1 repo~2.5k tokens
    Data & AnalyticsAuto-check passed
  • Boss Zhipin Scraper

    eatmoreduck/boss-zhipin-scraper

    Scrape BOSS直聘 (job listing site) via Chrome CDP. An agent skill from eatmoreduck/boss-zhipin-scraper.

    1.5k GitHub stars~2.6k tokensUpdated 9 days ago
    Data & AnalyticsAuto-check passed
  • Ax

    yusukebe/ax

    Use the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or extract structured data from HTML.

    719 GitHub starsUsed in 1 repo~918 tokens
    Data & AnalyticsAuto-check passed
  • Anakinscraper

    Anakin-Inc/anakin

    Scrape any website into clean markdown or structured JSON. An agent skill from Anakin-Inc/anakin.

    4.5k GitHub stars~859 tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed

More from Bubble252/offer-harvester

  • Grad Apply Workflow

    Bubble252/offer-harvester

    Evidence-grounded graduate application workflow protocols for this repository.

    123 GitHub stars~920 tokensUpdated 1 mo ago
    Auto-check: notes
  • Evidence Claim Audit

    Bubble252/offer-harvester

    Audit graduate-application claims against supplied evidence and return supported, unsupported, stale, or confirmation-required findings.

    123 GitHub stars~427 tokensUpdated 1 mo ago
    Auto-check passed
  • Profile Field Normalization

    Bubble252/offer-harvester

    Normalize graduate-application profile fields while preserving field evidence, source provenance, confidence, and confirmation status.

    123 GitHub stars~377 tokensUpdated 1 mo ago
    Auto-check passed
  • Advisor Due Diligence

    Bubble252/offer-harvester

    Build an evidence-grounded advisor review covering identity, research direction, recruitment signals, lab context, source gaps, and community risk signals.

    123 GitHub stars~281 tokensUpdated 1 mo ago
    Auto-check passed
  • Contact Email Coach

    Bubble252/offer-harvester

    Prepare evidence-grounded graduate-advisor contact email candidates with review and audit findings.

    123 GitHub stars~301 tokensUpdated 1 mo ago
    Auto-check passed
  • Recommendation Letter Helper

    Bubble252/offer-harvester

    Prepare evidence-grounded recommendation requests, recommender material packets, and clearly labeled reference drafts for graduate applications.

    123 GitHub stars~283 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Source Connector Authoring

What does Source Connector Authoring do?

Design and validate safe source connector manifests for public graduate-admission, policy, advisor, lab, and community sources. Source Connector Authoring is an agent skill from Bubble252/offer-harvester. Design and validate safe source connector manifests for public graduate-admission, policy, advisor, lab, and community sources.

When should I use Source Connector Authoring?

Source Connector Authoring fits situations like: adding a crawler; source connector; source access policy.

How do I install Source Connector Authoring in Claude Code?

Run `npx skills add Bubble252/offer-harvester --skill source-connector-authoring -a claude-code`. Or copy the skill folder (skills/source-connector-authoring in Bubble252/offer-harvester) into .claude/skills/source-connector-authoring in your project. Claude Code loads it when a task matches its description.

How do I install Source Connector Authoring in Codex?

Run `npx skills add Bubble252/offer-harvester --skill source-connector-authoring -a codex`. Or copy the skill folder (skills/source-connector-authoring in Bubble252/offer-harvester) into .agents/skills/source-connector-authoring in your project. Codex loads it when a task matches its description.

Can I use Source Connector Authoring 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 Bubble252/offer-harvester --skill source-connector-authoring -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/source-connector-authoring, .gemini/skills/source-connector-authoring, .github/skills/source-connector-authoring and .opencode/skills/source-connector-authoring in your project.

What does Source Connector Authoring need to run?

Going by SKILL.md and its folder, Source Connector Authoring needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Source Connector Authoring access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Source Connector Authoring 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Source Connector Authoring use?

Source Connector Authoring 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 Source Connector Authoring use?

About 379 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 135 tokens, read only when the agent opens those files.

What are the alternatives to Source Connector Authoring?

Skills that share tags, products or a category with Source Connector Authoring: Tmux (trpc-group/trpc-agent-go, 1.8k stars), Ketch (1broseidon/ketch, 697 stars), Crawl4AI Web Scraping (smallnest/goclaw, 598 stars) and Boss Zhipin Scraper (eatmoreduck/boss-zhipin-scraper, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Source Connector Authoring?

Bubble252 (a GitHub user) maintains it in Bubble252/offer-harvester, which has 123 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on August 27, 2026.

Source: Bubble252/offer-harvester on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.