company-discovery
Automates company discovery and target account list building for lead sourcing.
Install
mkdir -p .claude/skills/company-discovery && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19087" && unzip -o skill.zip -d .claude/skills/company-discovery && rm skill.zipInstalls to .claude/skills/company-discovery
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Find target companies that fit the ICP (capability company_search), create the pipeline list, and hand the company set to people_search. Supports look-alike / segment / expansion modes and synthesizes company_search from people_search when a provider lacks native org search. Use when the user wants to "find companies", "build a target account list", or run only the discovery stage.Key capabilities
- →Find target companies based on an Ideal Customer Profile (ICP)
- →Create a pipeline list of discovered companies
- →Deduplicate company lists and apply exclusions
- →Synthesize company search from people search if native org search is unavailable
- →Support look-alike, segment, and expansion modes for discovery
- →Return a company list and list ID for further sourcing
How it works
This skill discovers target companies by reading an agent's instructions, bootstrapping configuration, performing company searches, and then deduplicating and applying exclusions to create a pipeline list.
Inputs & outputs
When to use company-discovery
- →Building target account lists
- →Company segment expansion
- →Finding new sales prospects
About this skill
Input (a brief / segment / seed companies, optional geography): $ARGUMENTS
Execute company discovery: read agents/company-discovery/agent.md and follow it exactly
— bootstrap (config + icp.md + resolve the company_search waterfall, where builtin
providers like web_research are always available), discover companies (builtin
WebSearch/WebFetch, script, or manifest-driven requests; synthesize from people_search if
needed), dedupe + apply exclusions, create_list, and return the company list + list_id
for the sourcing stage.
When not to use it
- →When the user wants to perform people search directly without prior company discovery
- →When the user has a predefined list of companies and does not need discovery
- →When the user wants to bypass the deduplication and exclusion process
Limitations
- →The skill relies on the `company_search` capability
- →Built-in providers like WebSearch/WebFetch are always available
- →Company search can be synthesized from people_search if needed
How it compares
This workflow systematically identifies and refines a list of target companies based on an ICP, providing a structured approach to market segmentation and lead generation compared to ad-hoc searching.
Compared to similar skills
company-discovery side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| company-discovery (this skill) | 0 | 1mo | No flags | Beginner |
| session-logs | 8 | 2mo | Review | Intermediate |
| context-management-context-restore | 10 | 3mo | Review | Advanced |
| conversation-memory | 8 | 6mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by kkrlstrm
View all by kkrlstrm →You might also like
session-logs
openclaw
Search and analyze your own session logs (older/parent conversations) using jq.
context-management-context-restore
sickn33
Use when working with context management context restore
conversation-memory
davila7
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
zlibrary-to-notebooklm
zstmfhy
自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式，自动转换，一键创建知识库。
workiq-copilot
github
Guides the Copilot CLI on how to use the WorkIQ CLI/MCP server to query Microsoft 365 Copilot data (emails, meetings, docs, Teams, people) for live context, summaries, and recommendations.
compound-learnings
parcadei
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".