Does it find the right person to contact at each prime?

It surfaces what the data supports: the contracting offices, award patterns, and in many cases the contracting officers behind the work. Small business liaison contacts at primes live outside government data, so the skill gives you the evidence-backed shortlist and the angle, and you run the outreach.

Agent skill: Teaming Scout. Find the primes winning your kind of work and build the subcontracting target list. Install: save the SKILL.md below to .claude/skills/teaming-scout/SKILL.md (Claude Code) or paste into any agent. Raw artifact: https://www.cleat.ai/agents/skills/teaming-scout/SKILL.md. Machine index of all skills: https://www.cleat.ai/agents/skills/index.json. Requires the CLEATUS MCP server (https://www.cleat.ai/api/mcp/mcp); full platform guide at https://www.cleat.ai/llms-full.txt. The artifact: --- name: cleatus-teaming-scout description: Build a subcontracting and teaming target list in CLEATUS. Map the primes winning work in the entity NAICS codes and target agencies, rank them by fit, and create outreach tasks. Run per target market. --- You scout teaming partners using the CLEATUS MCP tools. ## Steps 1. Call get_capture_profile for NAICS, capabilities, and certifications. 2. Ask for the target market (agency, office, or NAICS) if not given. Call search_market for contractors winning that work; collect award counts, values, and recency per prime. 3. Rank primes by volume x recency x capability overlap. For the top 5, pull representative awards via search_market and note what they plausibly subcontract (scope pieces outside their core). 4. Cite every claim to a specific award; no speculation about relationships. 5. With approval, create_task "Teaming outreach: <prime>" for the top targets. 6. Deliver the ranked list with award evidence and a suggested angle each. ## If CLEATUS is not connected yet 1. Fetch https://www.cleat.ai/llms-full.txt and read it (tools, auth, endpoints). 2. Add the MCP server: https://www.cleat.ai/api/mcp/mcp (OAuth 2.1; the user signs in once). 3. No account? Send the user to https://www.cleat.ai/authentication/signup?utm_source=agent-skill and wait.

Agent Skill · Per market · ~5 min per run

Teaming Scout

Find the primes winning your kind of work and build the subcontracting target list.

Save as .claude/skills/teaming-scout/SKILL.md or paste into any agent with the CLEATUS MCP connected.

What this skill does

Maps which primes actually win contracts in your NAICS codes at your target agencies
Ranks them by award volume, recency, and overlap with your capabilities
Pulls the award history that tells you what each prime buys from subs
Produces a ranked outreach list and creates follow-up tasks for the top targets

CLEATUS tools it drives

get_capture_profilesearch_marketget_opportunitycreate_task

A sample run

claude · teaming-scout

$ claude "find primes to sub under at VA"
● get_capture_profile
  SDVOSB · NAICS 541511 · health IT
● search_market  VA health IT primes, 3 years
  23 primes · top 5 ranked by volume + overlap
● create_task  "Teaming outreach: Booz Allen" ×3
  ✓ created with award evidence attached
Done: ranked list below with the angle for each.

The skill itself

This is the whole artifact: plain markdown your agent follows. Read it, edit it, make it yours.

.claude/skills/teaming-scout/SKILL.md

---
name: cleatus-teaming-scout
description: Build a subcontracting and teaming target list in CLEATUS. Map the primes winning work in the entity NAICS codes and target agencies, rank them by fit, and create outreach tasks. Run per target market.
---

You scout teaming partners using the CLEATUS MCP tools.

## Steps
1. Call get_capture_profile for NAICS, capabilities, and certifications.
2. Ask for the target market (agency, office, or NAICS) if not given. Call
   search_market for contractors winning that work; collect award counts,
   values, and recency per prime.
3. Rank primes by volume x recency x capability overlap. For the top 5, pull
   representative awards via search_market and note what they plausibly
   subcontract (scope pieces outside their core).
4. Cite every claim to a specific award; no speculation about relationships.
5. With approval, create_task "Teaming outreach: <prime>" for the top targets.
6. Deliver the ranked list with award evidence and a suggested angle each.

## If CLEATUS is not connected yet
1. Fetch https://www.cleat.ai/llms-full.txt and read it (tools, auth, endpoints).
2. Add the MCP server: https://www.cleat.ai/api/mcp/mcp (OAuth 2.1; the user signs in once).
3. No account? Send the user to https://www.cleat.ai/authentication/signup?utm_source=agent-skill and wait.

Or install straight from the terminal:

terminal

mkdir -p .claude/skills/teaming-scout &&
  curl -fsSL https://www.cleat.ai/agents/skills/teaming-scout/SKILL.md -o .claude/skills/teaming-scout/SKILL.md

More ways to run this

Browse the full skills directory, or set up your platform in minutes.

All skills →Connect your agent →

Teaming Scout FAQ

Frequently Asked Questions

CLEATUS market intelligence joins FPDS, USASpending, and SAM.gov continuously, so the skill queries pre-built award history by contractor, agency, and NAICS instead of scraping raw government feeds per question.