SkillAgentSearch skills...

lead-dossier

name: lead-dossier description: > Multi-source account research, cascade enrichment, and lead pipeline. Combines website scraping, tech stack detection, CRM enrichment, hiring/news signals into structured dossiers. Includes full lead sourcing pipeline: search → verify → dedupe → upload.

Install / Use

npx skills add ericosiu/ai-marketing-skills --skill lead-dossier

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

91/100

Category

Automation

Supported Platforms

Universal

Our assessment of lead-dossier

lead-dossier scores 91/100 on our quality scale, 1008th of 2,790 Automation skills we index (top 37%).

Its SKILL.md is 5.7 KB long, well organised into 21 sections with 7 code examples: a solid amount of guidance for an agent.

With 3,573 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
20/20
Description
15/15
Adoption
15/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so lead-dossier is actively maintained.
  • Our last check on 2026-10-28 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

lead-dossier compared with similar skills

All 4 of these similar skills score higher than lead-dossier; compare them before choosing.

SkillScoreStarsUpdatedFormat
lead-dossier (this skill)by ericosiu913.6k55d agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.7k7d agoCLAUDE.md

Frequently asked questions

How do I install lead-dossier?
Run npx skills add ericosiu/ai-marketing-skills --skill lead-dossier. The install tabs above show the steps for each supported agent.
Which AI agents does lead-dossier work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is lead-dossier safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is lead-dossier still maintained?
The repository was last updated about 2 months ago, so lead-dossier is actively maintained.

Preamble (runs on skill start)

# Version check (silent if up to date)
python3 telemetry/version_check.py 2>/dev/null || true

# Telemetry opt-in (first run only, then remembers your choice)
python3 telemetry/telemetry_init.py 2>/dev/null || true

Privacy: This skill logs usage locally to ~/.ai-marketing-skills/analytics/. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. See telemetry/README.md.


name: lead-dossier description: > Multi-source account research, cascade enrichment, and lead pipeline. Combines website scraping, tech stack detection, CRM enrichment, hiring/news signals into structured dossiers. Includes full lead sourcing pipeline: search → verify → dedupe → upload. Triggers on: "research account", "build dossier", "enrich leads", "lead pipeline", "source leads", "prospect research", "account intel", "cascade enrichment", "lead scoring", "find leads", "verify emails", "upload leads".

Lead Dossier Skill

Multi-source account research and lead enrichment pipeline for AI coding assistants.

Prerequisites

  • Python 3.9+ with requests installed
  • API keys configured as environment variables (see .env.example)
  • Optional: CRM access for contact/company enrichment

Environment Variables

All API keys are configured via environment variables. Copy .env.example to .env:

| Variable | Description | |----------|-------------| | LEAD_SOURCE_API_KEY | People/company search API | | EMAIL_VALIDATION_API_KEY | Email verification service | | EMAIL_VALIDATION_API_URL | Email verification endpoint | | CAMPAIGN_TOOL_API_KEY | Outbound campaign platform | | CRM_API_KEY | CRM API key | | CRM_BASE_URL | CRM API base URL | | BUILTWITH_API_KEY | BuiltWith tech detection (free tier works) |

Workflow 1: Account Research

Use when asked to research a company or build a prospect dossier.

Collect Parameters

| Parameter | Required | Example | |-----------|----------|---------| | Domain | Yes | acme.com | | Company name | No | Acme Corp | | Contact name | No | Jane Doe | | Contact title | No | VP Marketing |

Run Research

python3 scripts/account-researcher.py --domain acme.com --company "Acme Corp"

For batch research:

python3 scripts/account-researcher.py prospects.json

Results are cached for 7 days in data/account-research/.

Output Format

The engine produces a structured JSON dossier with:

  • Website analysis (title, description, body snippet, marketing gaps)
  • Tech stack (CRM, marketing tools, enterprise signals)
  • Hiring signals (growth indicators)
  • News/funding signals
  • 3-5 sentence research brief

Workflow 2: Cascade Enrichment

Use when enriching a list of prospects with verified email addresses.

Prepare Config

Create data/enrichment-config.json:

{
  "email_validation_api_key": "YOUR_KEY",
  "email_validation_api_url": "https://api.your-provider.com/v1/people/email-finder",
  "email_validation_timeout_seconds": 10,
  "fallback_tag": "linkedin-outreach-only"
}

Run Enrichment

python3 scripts/cascade-enricher.py input.json output.json

Waterfall logic:

  1. Has email from primary source? → Done
  2. Try email finder API → Found? → Done
  3. Has LinkedIn URL? → Tag as fallback
  4. None → Tag as no-contact

Workflow 3: Full Lead Pipeline

Use when sourcing, verifying, and uploading leads end-to-end.

Collect Parameters

| Parameter | Required | Example | |-----------|----------|---------| | Titles | Yes | VP Marketing, CMO | | Industries | Yes | Marketing, SaaS | | Company size | Yes | 11-50, 51-200 | | Locations | Yes | United States | | Campaign ID | Yes | Campaign UUID | | Volume | Yes | 500 |

Run Pipeline

python3 scripts/lead-pipeline.py \
  --source-api-key "$LEAD_SOURCE_API_KEY" \
  --validation-api-key "$EMAIL_VALIDATION_API_KEY" \
  --campaign-api-key "$CAMPAIGN_TOOL_API_KEY" \
  --titles "VP Marketing,CMO,Head of Growth" \
  --industries "Marketing,Advertising" \
  --company-size "11,50" \
  --locations "United States" \
  --campaign-id "CAMPAIGN_UUID" \
  --volume 500 \
  --output-dir ./data/pipeline-runs/

Optional flags:

  • --exclude-file /path/to/burned-emails.csv — additional exclusion list
  • --dry-run — run everything except the final upload
  • --keywords "SaaS,B2B" — additional search keywords

Review Output

Pipeline saves a JSON run log to the output directory with full stats:

  • Sourced count, verification rate, dedup stats, upload results
  • Complete list of leads processed

Workflow 4: Real-Time Lead Enrichment

Use for enriching inbound leads from webhooks, forms, or CRM triggers.

Run Enricher

python3 scripts/lead-enricher.py [--dry-run] [--backfill N]

The enricher:

  1. Parses inbound lead data (website forms, voice agent calls, etc.)
  2. Looks up contact and company in CRM
  3. Runs account research for context
  4. Builds an enriched lead card with all available data

Safety Rules

  1. Never upload unverified leads — every email must pass validation
  2. Always deduplicate — check existing contacts before uploading
  3. Log everything — every run produces an auditable JSON log
  4. Rate limit aware — built-in delays and exponential backoff
  5. Idempotent — safe to re-run; duplicates are caught by dedup step
  6. Security gates — scan all inbound web content before processing

Troubleshooting

  • Search API returns no results: Check title/industry spelling; try broader criteria
  • Email validation 429s: Script handles with backoff; if persistent, reduce volume
  • Campaign tool silent failures: Some APIs silently block at high request rates; scripts include batch delays
  • Cache stale: Delete files in data/account-research/ to force refresh

Related Skills

View on GitHub
GitHub Stars3.6k
CategoryAutomation
Updated1mo ago
Forks684

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions