Agent skill: Price Assessment. Assess budget, buying behavior, and competitors before a live procurement reaches pricing. Install: save the SKILL.md below to .claude/skills/price-assessment/SKILL.md (Claude Code) or paste into any agent. Raw artifact: https://www.cleat.ai/agents/skills/price-assessment/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-price-assessment description: Assess pricing context for a government pursuit during capture. Research budget signals, buying-office award history, comparable awards, and four evidence-backed competitors. Run before a live procurement reaches bid pricing. --- You produce a capture-stage price assessment using CLEATUS public market intelligence. This is research, not a bottom-up cost build. ## Required inputs - A pursuit or opportunity, or enough agency, office, scope, NAICS, PSC, and period-of-performance detail to identify comparable work. ## Grounding rules 1. Label a government budget as published only when the opportunity or a cited government document states it. Otherwise label the result an award-based estimate with its comparables and confidence. 2. Cite every award amount, date, recipient, and office to a named award. 3. Do not derive ABR from total award value without cited labor hours, labor categories, and rate data. Report "insufficient data" when those inputs are absent. 4. Do not claim an office favors price or technical factors unless a cited solicitation, award decision, or evaluation record supports it. 5. Public award history proves wins. It does not prove who submitted and lost. Label unsupported loss history or competitor bidding posture "insufficient public data." 6. Never invent or extrapolate a number without a cited award or published source behind it. ## Playbook 1. Call get_opportunity for the scope, agency and office, vehicle, set-aside, NAICS/PSC, period of performance, estimated value, and available documents. 2. Establish the budget signal: - quote a published budget, funded amount, ceiling, or estimate when present; - otherwise call search_market for comparable awards at the same office, then widen to the agency and government-wide; - present the comparable award values as context, not as an official budget. 3. Profile the contracting office from the trailing two years of cited awards: award values, recipients, contract/pricing types, competition fields, and representative examples. Search documents for evaluation evidence when it is available. State which requested tendencies cannot be established. 4. Build the competitive field. Rank four contractors by relevant award recency, value, office overlap, and scope overlap. For each, explain why it belongs, cite recent wins, and distinguish observed award behavior from inferred posture. 5. Produce the trailing-two-year award table. Include ABR only when a cited source publishes enough labor detail to calculate it. Otherwise put "insufficient data" in the ABR cell. 6. Deliver: - data-readiness summary; - budget signal and confidence; - contracting-office evidence and limitations; - cited award table; - four-competitor table with wins and evidence gaps; - explicit "insufficient data" list. ## 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.