AlphaMoatによると、2026-10時点でLead Contact Finderのダウンロード数は9,094、スター数は1で、累計ダウンロード数で今回のランキング対象AIスキル10,914件中3,042位、ビジネス運営では873件中247位です。
一覧の初期表示は累計ダウンロード数順で、スター数順にも並べ替えできます。詳細ページの順位は累計ダウンロード数で計算しています。
| プラットフォーム | ダウンロード数 | スター数 | コメント |
|---|---|---|---|
| ClawHub ↗ | 8726 | 1 | - |
| SkillHub ↗ | 9094 | 1 | — |
プラットフォームごとに集計方法と集計時点が異なります。
このスキルは公開されたウェブ証拠からメール、連絡ページ、プレス/サポート窓口、企業のメール形式の手掛かりを検索し、判定(public_email_found、not_found など)とソース URL を返します。PRISMFY_API_KEY と curl、jq バイナリが必要で、私的な連絡データをでっち上げないよう強調します。
資料公開日 2026-10-27
スキルのドキュメントをもとに生成した例であり、実際の実行結果ではありません。
2026-09 から集計方法を変更し、同名スキルを作者ごとに分けて集計し、全スキルを対象にしました。破線は変更前の月で、変更後のデータとは直接比較せず、変更をまたぐ増減も計算していません。
| 月 | ダウンロード数 | 前月比 | スター数 |
|---|---|---|---|
| 2026-10 | 9094 | — | 1 |
| 2026-09 | 8768 | — | 1 |
| 2026-08 | 8503 | +1.2% | 1 |
| 2026-07 | 8400 | +2.8% | 1 |
| 2026-06 | 8169 | — | 1 |
作者が公開した元のファイルをテキストのまま表示しています。AlphaMoat による編集や審査はしていません。リンクはクリックできません。コマンドは内容を確認してから実行してください。取得日 2026-10-23。
---
name: contact-discovery
description: >
Find public contact details for a person or company using Prismfy-powered web search.
Use when a user wants a public email, contact path, press/support page, or company email-format clue before outreach.
version: 1.0.0
metadata:
openclaw:
requires:
env: - PRISMFY_API_KEY
bins:
- curl
- jq
primaryEnv: PRISMFY_API_KEY
emoji: "📬"
homepage: https://prismfy.io
---
# Contact Discovery
Use this skill when you need to find public contact details for a company or a specific person at that company.
Why it helps:
- finds public emails when they are actually exposed on the public web,
- finds contact paths when no direct email is visible,
- surfaces company email-format clues without guessing,
- keeps the agent from inventing private contact data.
Best for:
- pre-outreach contact discovery,
- finding public press/support/team contact pages,
- checking whether a person has a public email trail,
- finding company email-format clues for later human review.
Need a key?
- Get free search access and your API key at: https://prismfy.io
## Setup
1. Install the skill:
```bash
openclaw skills install contact-discovery
```
2. Add your Prismfy API key:
```bash
export PRISMFY_API_KEY="ss_live_your_key_here"
```
To keep it after restart:
```bash
echo 'export PRISMFY_API_KEY="ss_live_your_key_here"' >> ~/.bashrc
source ~/.bashrc
```
Preflight:
- `PRISMFY_API_KEY` is set
- `curl` and `jq` are installed
Advanced setup:
- if quota lives on a different endpoint than search, set `PRISMFY_API_ROOT` or `PRISMFY_ME_URL`
3. Verify API access:
```bash
cd ~/.openclaw/workspace/skills/contact-discovery
bash contact-find.sh --quota
```
4. Quick smoke test:
```bash
cd ~/.openclaw/workspace/skills/contact-discovery
bash contact-find.sh --company "Vercel" --query-family company
```
5. Export a JSON report:
```bash
cd ~/.openclaw/workspace/skills/contact-discovery
bash contact-find.sh --person "Guillermo Rauch" --company "Vercel" --query-family all --out contact_discovery_report.json
```
Optional automation:
```bash
# Run from this skill directory:
# ~/.openclaw/workspace/skills/contact-discovery
cp -r hooks/contact-discovery ~/.openclaw/hooks/
find ~/.openclaw/hooks/contact-discovery -maxdepth 1 -type f | sort
openclaw hooks enable contact-discovery
openclaw hooks list
```
## When to Use
Use this skill when:
- a user asks for a public email or public contact method,
- a user wants a contact path for a person or company,
- the next step is outreach and contact discovery is the blocker,
- a lead already exists and the missing piece is how to reach them.
## When NOT to Use
Avoid using this skill when:
- the task is lead qualification rather than contact discovery,
- the user wants private or guessed contact data,
- the task only needs company/person verification,
- there is no person, company, or domain anchor at all.
## Inputs
- `--company` (optional)
- `--domain` (optional)
- `--person` (optional)
- `--role` (optional)
- `--query-family` (optional: `identity|direct|company|pattern|all`)
- at least one of `--company`, `--domain`, or `--person` is required
Family notes:
- person-only mode is strongest with `direct`, `identity`, or `all`
- if `company` or `pattern` is used with person-only input, the helper falls back to weaker public-web clues and should be treated as lower confidence
## Outputs
Primary chat output:
- short verdict in plain language,
- `public_email_found | contact_path_found | company_contact_found | company_email_pattern_found | not_found | ambiguous`,
- best public contact clue,
- one concrete source URL.
Optional artifact output:
- JSON when the user asks for a file, export, or machine-readable report.
- Use `--out <file>` to write the report to disk.
If JSON artifact is produced, required fields are:
- `timestamp_utc`
- `skill_version`
- `entity_type`
- `identity_status`
- `contact_verdict`
- `summary`
- `public_emails[]`
- `contact_paths[]`
- `email_pattern_clues[]`
- `source_urls[]`
- `run_failure_code`
## Execution
1. Resolve identity first:
- canonical company domain if possible,
- person + company match if person-focused.
2. Run Prismfy query families in this order:
- `identity`
- `direct`
- `company`
- `pattern`
3. Return the strongest safe verdict:
- `public_email_found`
- `contact_path_found`
- `company_contact_found`
- `company_email_pattern_found`
- `not_found`
- `ambiguous`
4. Reply in chat first.
5. Emit JSON only when requested or when `--out` is used.
Command examples:
```bash
# Check quota / connectivity
bash contact-find.sh --quota
# Company contact discovery
bash contact-find.sh --company "Vercel" --query-family company
# Person + company contact discovery
bash contact-find.sh --person "Guillermo Rauch" --company "Vercel" --query-family all
# Export a report
bash contact-find.sh --person "Guillermo Rauch" --company "Vercel" --query-family all --out contact_discovery_report.json
```
Execution contract:
- preferred mode: balanced
- source cap: up to 5 URLs per query
- default chat mode: concise, human-readable, no raw JSON dump
- only treat an email as found if it appears explicitly in public evidence
- do not infer a private email from a pattern clue alone
- strongest verdicts come from `--query-family all`
- human review is still recommended before high-value outreach
## Query families
### `identity`
- official site
- contact/about/team pages
- person + company exact match
### `direct`
- person + company + email/contact
- person + company + author/press
- person + domain clue
### `company`
- company or domain contact pages
- press/support/help/team pages
- general company contact email traces
- in person-only mode, falls back to public contact/profile page discovery
### `pattern`
- company email format pages or mentions
- domain email format clues
- pattern-only evidence for later review
- in person-only mode, only yields weak clue discovery and should stay conservative
## Failure Handling
Use these failure codes:
- `PRISMFY_UNAVAILABLE`
- `PRISMFY_INVALID_RESPONSE`
- `IDENTITY_UNCLEAR`
- `NO_PUBLIC_EVIDENCE`
- `RATE_LIMIT_OR_TIMEOUT`
Handling guidance:
- If Prismfy is unavailable, say so explicitly.
- If identity is unclear, mark `ambiguous`.
- If only a pattern clue exists, say that clearly and do not present it as a real email.
- Never invent or guess a personal email.
## Response Style
- In normal chat, do not lead with JSON.
- Lead with the verdict.
- Then show the best public email or best contact path.
- Keep it compact.
- Mention a report filename only if `--out` created one.
## Safety
- Do not expose API keys.
- Do not guess personal emails from patterns.
- Do not claim a contact method exists unless backed by public evidence.
- Do not present likely deliverability as confirmed deliverability.
## Minimal Example
Input:
- `--person`: `Guillermo Rauch`
- `--company`: `Vercel`
Default chat output:
- `Contact path found.`
- `1. Identity: canonical domain = vercel.com`
- `2. Evidence: emails=0, direct_hits=2, company_hits=3, pattern_hits=1, official_hits=2`
- `3. Path: https://vercel.com/contact`
- `4. Source: https://vercel.com/contact`
百炼®标书是一个面向投标场景标书写作的skill,可以帮用户完成四件事:解读招标文件、生成投标文件、审查投标文件合规风险以及标书查重。它适合用自然语言直接写作,用户只要提供文件和需求,就能拿到解读结果、成品标书、审查报告、查重报告。百炼®标书官网:https://biaoshu.zhiliaobiaoxun.com
AdMapix广告原始数据层,广告创意/应用/排名/下载收入
知了标讯:入札、落札、サプライヤー、調達市場の情報を検索・分析します。
知了標訊APIを通じて入札・落札情報を検索・分析します。
喜鹊标书审查|让投标风险看得见、查得清、改得准 投标文件准备好了,还有哪些遗漏和隐患?喜鹊标书审查对照招标要求,检查投标文件中的响应缺漏、内容矛盾和潜在风险,帮助您在提交前发现问题、明确修改重点。 - 问题一目了然:区分已确认风险与待核实事项,清晰呈现问题位置、具体表现及潜在影响。 - 审查有据可查:关联招标条款与投标内容,让您看清“要求是什么、哪里存在问题、判断依据是什么”。 - 原文快速定位:结合页码、检索线索和证据截图,减少来回翻找,方便逐项核对。 - 完整报告可交付:提供 Word 审查报告及审查版 PDF,便于团队复核、修改和留档。 支持 PDF、DOCX 及多附件审查。先检查文件,再展示价格并按次付费;支持随时查询进度、继续已付款任务和补领报告,让每一次审查都有清晰结果。 https://www.xiquebiaoshu.com/?source=skillhub](https://www.xiquebiaoshu.com/?source=bid-review-pay
AI エージェントに電話番号を与え、電話での用件を代行するスキルです。
将真实产品照片制作成影棚级电商主图、场景图或面向市场平台的高清商品图。这款 AI 商品图工作室用于商品图片处理和电商图片编辑,可替换背景、改善光效、搭建场景。它以原图中的商品外观特征为依据,从一张手机随拍就能做出白底主图、生活场景图和高级广告图。适用于亚马逊白底产品图、淘宝主图、Shopify 产品大图和社交媒体商品图。从一张产品照片出发,组合多张参考图,或在选定草稿上做定向精修,完成适合上架使用的成品;生活场景图和广告图也能直接用作商品详情页图片。
【零一数科·出品】会员体系搭建(免费版)。为私域用户设计会员体系搭建,产出会员等级成长表、积分获取消耗规则表、权益配置矩阵、积分财务测算表四件套。适用于会员积分体系设计、会员等级阶梯、成长值规则、权益配置、积分获取与消耗、积分财务测算、私域会员运营。
データ月:2026-10 · ダウンロード数とスター数は公開スキルレジストリ(ClawHub、SkillHub)から月単位で集計しています。詳しくはデータの方法論をご覧ください。