Can it research an office before I have a pursuit?

Yes, give it an agency, office, or NAICS code directly and skip the pursuit-update step. The write-back is optional and always confirmed first.

Agent skill: Incumbent Recon. Know who holds the work, what they charge, and which contracting officers sign. Install: save the SKILL.md below to .claude/skills/incumbent-recon/SKILL.md (Claude Code) or paste into any agent. Raw artifact: https://www.cleat.ai/agents/skills/incumbent-recon/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-incumbent-recon description: Research the incumbent and buying office for a government pursuit in CLEATUS, covering award history, comparable contract sizes, and the contracting officers behind the office. Run before Go/No-Go. --- You research the competitive landscape for one pursuit using the CLEATUS MCP tools. ## Steps 1. From the pursuit's opportunity, note the agency, office, NAICS, and PSC. 2. search_market for prior awards at that office in that NAICS: capture incumbent names, award amounts, and period-of-performance ends. 3. search_market for the contracting officers attached to those awards; note names and recent signing activity. 4. Synthesize: likely incumbent, typical award size, recompete timing, and the two most relevant COs. 5. With approval, update_pursuit to append the recon summary to the pursuit notes. Cite every claim to a specific award; no speculation. ## 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 pursuit · ~3 min per run

Incumbent Recon

Know who holds the work, what they charge, and which contracting officers sign.

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

What this skill does

Identifies the likely incumbent and their award history at the buying office
Sizes comparable awards so you price against reality instead of guessing
Profiles the contracting officers behind the office: who signs, how often, for what
Writes the recon summary onto the pursuit so the whole team sees it

CLEATUS tools it drives

search_marketget_opportunityupdate_pursuit

A sample run

claude · incumbent-recon

$ claude "recon the VA 36C10B pursuit"
● search_market  awards · VA TAC · NAICS 541512
  14 awards · incumbent: 3-time repeat winner
● search_market  contracting officers · VA TAC
  3 COs identified · 2 active this FY
● update_pursuit  recon summary appended
  ✓ saved to pursuit notes
Incumbent, sizing, and CO profile delivered.

The skill itself

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

.claude/skills/incumbent-recon/SKILL.md

---
name: cleatus-incumbent-recon
description: Research the incumbent and buying office for a government pursuit in CLEATUS, covering award history, comparable contract sizes, and the contracting officers behind the office. Run before Go/No-Go.
---

You research the competitive landscape for one pursuit using the CLEATUS MCP tools.

## Steps
1. From the pursuit's opportunity, note the agency, office, NAICS, and PSC.
2. search_market for prior awards at that office in that NAICS: capture
   incumbent names, award amounts, and period-of-performance ends.
3. search_market for the contracting officers attached to those awards; note
   names and recent signing activity.
4. Synthesize: likely incumbent, typical award size, recompete timing, and the
   two most relevant COs.
5. With approval, update_pursuit to append the recon summary to the pursuit
   notes. Cite every claim to a specific award; no speculation.

## 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/incumbent-recon &&
  curl -fsSL https://www.cleat.ai/agents/skills/incumbent-recon/SKILL.md -o .claude/skills/incumbent-recon/SKILL.md

More ways to run this

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

All skills →Connect your agent →

Incumbent Recon FAQ

Frequently Asked Questions

CLEATUS continuously ingests and joins FPDS, USASpending, and SAM.gov, plus 40,000+ state and local sources, so the skill queries pre-joined award history, entities, and contracting-officer data instead of scraping raw government feeds per question.