Veteran GovCon AI Kit: capability statement, SAM.gov profile checklist and past performance with your agent
by PaperChaseWebb
For veteran-owned and other small firms starting in federal contracting: a fact sheet your agent drafts from, eight prompts for a one-page capability statement, a SAM.gov profile checklist, a past performance skill, agency research prompts and capstat_check.py, thirteen read-only checks for UEI, CAGE and NAICS shape, hype words, placeholders, length and a dated source line for any status you list.
- Price
- $29
- Difficulty
- Beginner
- Setup
- 45 min
- Format
- .md file
veteran-govcon-ai-kit-capability-statement-and-sam-checks.md · 13 KB · instant download after checkout
Want this built for you instead? We can build it for you.
What you end up with
A one-page capability statement drafted from your own facts, with every code shaped right and every status claim tied to the record you checked it in.
What you get
- 11 sections in one .md file
- Ground rules and a facts.md template
- Eight capability statement prompts and a one-page layout
- SAM.gov profile checklist
- Past performance skill and agency research prompts
- capstat_check.py: 13 read-only checks (C01 to C13)
- A quality checklist
Who it is for
Owners who want their agent to draft a capability statement and keep it honest: only facts from your fact sheet, status wording copied from your own record with the date you checked it.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.
Tools needed
Cost to run: The pack is the only purchase. The checker uses no model tokens.
Time to result: A checked first draft of a capability statement in an afternoon
Sample prompts, free to use
Read facts.md and the ground rules. Draft the capability statement in the one-page layout. Use only facts in facts.md; write [PLACEHOLDER] where one is missing. Run python3 capstat_check.py capstat.md and fix every finding.
From the pack.
Free preview of the file
# Veteran GovCon AI Kit: capability statement prompts, a SAM.gov profile checklist and a past performance skill Version 1.0, 2026-10-30. By PaperChaseWebb, a veteran-owned firm. For owners of small federal contracting firms, including veteran-owned ones, who use Grok Bot, Claude Code, Codex, Hermes or a chat assistant to draft their capability statement and past performance write-ups. One Markdown file and one Python 3 script, standard library only. See section 10 for exactly what was and was not tested. This kit does not give legal, size or eligibility advice, and it does not say what any certification means or how to get one. Your status and the exact words you may use for it come from your own records with the agency that granted it. The kit makes your agent ask for that record instead of guessing. ## 1. What is in this kit 1. What is in this kit 2. Ground rules for the agent (paste once) 3. Your fact sheet: the only source the agent may use 4. Capability statement: eight prompts 5. The one-page layout 6. SAM.gov profile checklist 7. Past performance skill: a SKILL.md for Claude Code, Codex and Hermes, and a Grok Bot block 8. Agency research prompts 9. capstat_check.py: thirteen read-only checks on your statement 10. How this was tested 11. Quality checklist ## 2. Ground rules for the agent Paste this before any prompt below. ``` You are helping me write federal contracting material for my company. Rules: 1. Use only facts in facts.md. If a fact is missing, write [A
Test record
- Date
- Oct 30, 2026
- What was run
- capstat_check.py pulled from the pack text on a made-up company statement, one planted fault per code C01 to C13, and a missing file. Linux, Python 3.13.5.
- Result
- PASS and exit 0 on the clean statement; 13 of 13 planted faults caught alone with exit 1; exit 2 on a missing file; fixtures unchanged.
- Not run
- The prompts inside an agent on a real company. Any check against SAM.gov, SBA records or agency rules. Windows.
Copied from this item's dated test notes. What was not run stays in.
Worth knowing
- The checker tests format and wording only. Whether a code, status or certification applies to you is yours to confirm in your own SAM.gov and SBA records; the kit tells the agent to copy status wording from your record, not to describe it.
- Not legal or contracting advice, and no promise of awards or contracts.
- Tested 2026-10-30: capstat_check.py pulled from the pack text on a made-up company statement, one planted fault per code C01 to C13, and a missing file. Linux, Python 3.13.5. Result: PASS and exit 0 on the clean statement; 13 of 13 planted faults caught alone with exit 1; exit 2 on a missing file; fixtures unchanged. Not run: The prompts inside an agent on a real company. Any check against SAM.gov, SBA records or agency rules. Windows.
Questions
Does it say what SDVOSB, 8(a) or HUBZone mean or whether I qualify?
No. It asks you to copy the wording from your own record and add the date you checked it; capstat_check.py flags a status with no such line.
Details
Version 1.0 · Updated Oct 30, 2026 · Markdown version of this page
License: Use for your own work and for clients. Do not resell or republish the pack itself. Download terms
Related
Capability statement ground rules and a five-line fact check (free sample)
From the Veteran GovCon AI Kit: the ground rules that keep an agent to your own facts when drafting a capability statement, and a five-line manual check for code shapes, contact details, hype words and dated status lines.
Vet Before You Install: twelve checks, a sandbox recipe and a tested vetting folder for third-party agent code
Decide whether a skill, plugin, mod, MCP server, connector, repo or model gets into your agent setup: sort the seat, read every file that runs, map reach and the data path, pin and vendor it, trial it in a sandbox with a planted fake key, then record a decision the owner approves at their own terminal. v1.1 adds a seat sort before any vetting, two new checks (data path and reach, approval surfaces), evidence tiers, twelve token classes including hidden text, encoded strings, startup file edits and approval hooks, a fresh-session second read, data path questions for proxies and routers, dependency and model weight pinning, a fifth decision (not vettable) with recheck dates and an approved shelf, more special cases, a vetting folder with a fifteen-check read-only checker and an owner approval helper, agent files for Grok Bot, Claude Code, Codex and Hermes, and twelve new prompts (27 in all). Price unchanged.
Price, pitch and follow up: prompts for solo founders selling services
15 prompts for pricing a service, writing a one-page offer and proposal, handling objections and following up on a schedule, plus a read-only checker that flags a price under your own minimum, numbers that are not in your notes and which follow-up is due for each lead.
Ask-first rules for AI agents: hard nos, approval cards and a test set
Paste-in rules that make an agent ask before it sends, spends, posts or deletes, define what a real yes is, and stop retries after a no, plus 12 test scenarios to check it.