Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Setup

ASecurity

Interactive config wizard for research-cards: create, inspect, or adjust ~/.config/research-cards/config.json by interviewing the user against config.example.json's inline docs. Use when the user asks to set up / configure / initialize research-cards, 建立 config、設定 research-cards、調整設定、初始化、幫我設定、check my config, enable a backend (backends list: local/heptabase/hackmd), change the output language, or turn features on/off.

3 stars
0 votes
0 copies
0 views
Added 9/22/2026
researchpythonbashapibackend

Works with

claude codecliapimcp

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add SungFeng-Huang/research-cards --skill setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Setup?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Setup
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sungfeng-huang-setup/badge)](https://www.skillsdirectory.com/skills/sungfeng-huang-setup)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: setup
description: "Interactive config wizard for research-cards: create, inspect, or adjust ~/.config/research-cards/config.json by interviewing the user against config.example.json's inline docs. Use when the user asks to set up / configure / initialize research-cards, 建立 config、設定 research-cards、調整設定、初始化、幫我設定、check my config, enable a backend (backends list: local/heptabase/hackmd), change the output language, or turn features on/off."
---

# setup — config 精靈

把 `config.example.json` 的行內文件(`$comment` 們)變成一場**短訪談**:
建立、體檢、或調整 `~/.config/research-cards/config.json`。原則:

- **最小 config 優先**——純 .md 資料夾模式只需要 `obsidian.vault` 一個
  必填(`backends` 缺省即 `["local"]`)。不要把 example 整份抄給使用者。
- **絕不臆造 id**——heptabase 模式的 workspace_id/tag_id/property UUID
  一律由指令查出或使用者提供(`heptabase tag list`/`tag properties`)。
- **改前先讀**——調整模式永遠先讀現有 config,只動使用者要動的鍵;
  寫回後跑驗證器。

## Step 0 — 體檢(每次都先跑)

```bash
python3 <此 skill 目錄>/check_config.py          # 人讀報告
python3 <此 skill 目錄>/check_config.py --json    # 給 agent 解析
# heptabase 模式想順便測 app 連線:加 --probe
```

輸出告訴你:config 在哪(含 `RESEARCH_CARDS_CONFIG` env 覆蓋與 legacy
`heptabase-cards` 路徑)、載不載得起來(載入失敗會指名缺哪個 key)、
backend 的可及性(vault 目錄/heptabase CLI)、以及 **upgrade_hints**——
example 有記載、此 config 尚未設定的鍵(新功能的加購清單,如
`profile.language`、`obsidian.journal`)。

## 模式 A — 建立(config 不存在)

訪談順序(一次問一組,別轟炸):

1. **用途**:讀論文管線(study)?研究專案卡(project)?都要?
   → `features.{study, project}`(預設皆開,都要就不用寫)。
2. **backends**:預設推薦**純 .md 資料夾**(不需要任何筆記 app;就是
   `backends: ["local"]`,可省略不寫;list 首位=正本,舊單值
   `backend` 鍵仍相容)。使用者有 Heptabase 才問
   `heptabase`/`both`——並提醒 macOS+desktop app+CLI ≥ 0.4.0 的需求。
3. **資料夾**:`obsidian.vault` 路徑(iCloud 要提醒 Full Disk Access)+
   `folders`(預設 `{"papers": "Papers", "overviews": "Overviews"}`)。
4. **profile**:`reader`(讀者身分,流進每張卡的「為什麼該讀」)、
   `field`(主領域)、`language`(產出語言;不設=跟 Claude Code 的
   language 設定,再預設繁體中文)。
5. **agent**:跑無人值守腳本的 CLI(`claude`|`codex`);互動用途照預設。
6. 只寫使用者實際回答的鍵——寫入前把 draft 亮給使用者核可,寫入後跑
   Step 0 驗證。

Heptabase/both 額外流程(照 example 的 `heptabase` 段 `$comment`):

```bash
heptabase tag list                       # 找 workspace 的 tag id
heptabase tag properties <tagId>        # 各 tag 的 property UUID
```

按使用者的 tag 命名收集 `workspace_id`、`collections`(papers/overviews/
projects 的 tag_id)、`props`(Tasks/Source Type/arxiv/Level)。查不到
的值**留空並明講**——heptabase 路徑的指令會在缺 key 時指名報錯,這是
設計(絕不猜 UUID)。

## 模式 B — 調整(config 已存在)

1. Step 0 體檢;把 `upgrade_hints` 攤給使用者(「example 新增了這些設定,
   要開嗎?」)。
2. 使用者點名要改的東西 → 讀 example 對應段的 `$comment` 給出選項與
   語義(例:`profile.language` 的 fallback 鏈、`overflow_spill` 預設
   已開、`email.hf_min_upvotes` 的選文語義)。
3. 只改點名的鍵;改完重跑驗證器並回報 diff。

常見調整的對照:

| 使用者說 | 動哪裡 |
|---|---|
| 「換輸出語言」 | `profile.language`(空=跟 Claude Code 設定) |
| 「接上 Heptabase」 | `backends` → `["heptabase"]`/`["heptabase", "local"]`+`heptabase` 段(模式 A 的 id 收集) |
| 「開信件剪報」 | `email.{account, mailbox}`(Mail.app 帳號+專用資料夾;排程另見 README) |
| 「關掉 project 方向」 | `features.project: false` |
| 「裝了 hung-yi-lee」 | `integrations.hung_yi_lee.skill_path` |
| 「journal 換資料夾」 | `obsidian.journal.folder`(vault 相對;逃逸會被拒) |
| 「接上 HackMD/發佈到 HackMD」 | `hackmd.collections`(key → folder_id,`hackmd-cli folders` 查)+permissions;token 走 `hackmd-cli login`/`HMD_API_ACCESS_TOKEN`,**絕不進 config**——詳見 hackmd-sync skill |

## 邊界

- **cluster(hb bridge)上不要建 heptabase config**:bridge 沒有
  `tag properties`,id 收集做不到;純 .md 模式可以(只要 vault 路徑),
  或提醒使用者回 Mac 設定。
- 這個 skill 只動 `config.json`——topics 目錄(`~/.config/research-cards/
  topics/`)的建立屬 overview 的 quickstart 流程,不在此處代辦。
- Agent(claude/codex)皆可執行;無 MCP 依賴。

Attribution

SungFeng-HuangSungFeng-Huang
View sourceMore from SungFeng-Huang →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full research, quick brief, paper review, lit-review, fact-check, three-way literature scan, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report co...

494352 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

813271 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory, coverage-bounded integrity checks, two-stage peer review, and auditable quality-assurance artifacts. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end p...

494351 votes

Exa Search

Semantic search, similar content discovery, and structured research using Exa API

304951 votes
View all in research →