Name: Contact Sourcer
Author: Skills Guide Bot

Automated summary

This skill sources people at target companies through the people_search capability and writes them to storage at the 'sourced' stage after deduplication and cross-referencing against the master DB.

Strengths

Runs the configured people_search provider waterfall, falling back from one provider to the next
Backfills missing domains and deduplicates before writing
Cross-references each contact against the master database (crossref_master) to avoid duplicates
Can create a list when needed and reports both the waterfall table and the resulting list_id

Limitations

Fully dependent on agents/contact-sourcer/agent.md, provider manifests and keys configured in the repo
Covers only the sourcing stage: no email enrichment, verification or outreach
Assumes storage/cli.py and the master database already exist and are reachable

When to use it

Use it when you only need to feed the pipeline with new qualified contacts by company, title and geography.

When not to use it

Avoid it if the goal is writing outreach messages or enriching/verifying contact details, which the skill does not cover.

Security analysis

Caution

Quality score72/100

No destructive, obfuscated, or exfiltrating commands appear in the skill itself; it orchestrates a legitimate sourcing pipeline. Risk is elevated to caution because it grants Bash plus network tools, consumes provider API keys, and writes personal data to storage, so correctness of the referenced agent.md and config hygiene matter.

Findings

•Uses Bash to execute an external agent file and storage CLI, which gives broad execution latitude if that file is tampered with
•Resolves 'keyed providers' for people_search, implying handling of API credentials/secrets
•Sources and persists personal data (names, titles, companies, possibly contact info) into a master DB — PII/compliance exposure

How this analysis is made

Examples

Source at named companies

Source contacts at Stripe, Adyen and Mollie — persona: Head of Payments or VP Engineering, geography: EU. Write them at stage 'sourced' and report the waterfall table.

Add to an existing list

Find people at these 12 fintech companies with the title 'Head of Risk' and add them to list_id lst_204, deduping and cross-referencing the master DB.

Run sourcing only

Run only the sourcing stage for companies in my input file: titles = CTO, VP Data; geography = France. Create a new list if none is given.

name: contact-sourcer description: > Source people at target companies (capability people_search) and write them to storage at stage 'sourced'. Runs the configured people_search waterfall, backfills domains, dedups, and cross-references the master DB. Use when the user wants to "source contacts", "find people at these companies", or run only the sourcing stage. allowed-tools: Read, Bash, WebSearch, WebFetch

Input (companies + persona/titles + geography, and optionally an existing list_id): $ARGUMENTS

Execute the contact sourcer: read agents/contact-sourcer/agent.md and follow it exactly — bootstrap (config + context + resolve the people_search waterfall from keyed providers), source per provider via their manifests, backfill domains, dedup + crossref_master, then write via storage/cli.py (create_list if needed, upsert_contacts). Report the waterfall table and the resulting list_id.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/contact-sourcer-mrx3xwe8/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/contact-sourcer-mrx3xwe8' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/contact-sourcer-mrx3xwe8/download' --output '.skill-downloads/contact-sourcer-mrx3xwe8/SKILL.md.part' && mv '.skill-downloads/contact-sourcer-mrx3xwe8/SKILL.md.part' '.skill-downloads/contact-sourcer-mrx3xwe8/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Bash, WebSearch, WebFetch

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/contact-sourcer-mrx3xwe8/SKILL.md' && test -s '.skill-downloads/contact-sourcer-mrx3xwe8/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/contact-sourcer' && cp -R '.skill-downloads/contact-sourcer-mrx3xwe8' '.claude/skills/contact-sourcer'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/contact-sourcer-mrx3xwe8'

openskills read 'contact-sourcer-mrx3xwe8'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/contact-sourcer-mrx3xwe8/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Create Interactive Maps with kepler.gl

Data & AI

Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.

Claude CodeCursorCodexintermediateSafe 11,995

Skills Guide Bot