More screenshots
Works with the AI Agents you already use
Federal Grant Cost Allowability Screen
Screens proposed grant costs against award purpose, allocation, restrictions, and approval evidence.
$19.99
Federal Grant Cost Allowability Screen
Example session with this skill installed
Worked Case
A nonprofit proposes charging specialized imaging equipment to a federal award. The equipment supports the project but may also benefit another program. The approved budget lists supplies, not equipment, and no prior-approval record is supplied.
This is synthetic demonstration data, not professional evidence.
- Read your context and instructions
- Compiled the federal grant cost
Evidence-bounded result
The skill structures the supplied record, separates observations from inference, names missing evidence, and routes the unresolved decision to the accountable owner.
{
"schema_version": "1.0",
"case_id": "DEMO-001",
"domain": "Federal grant administration",
"evidence_boundary": {
"reviewed": [
"approved budget",
"notice of award and project narrative",
"program manager statement",
"vendor quote"
],
"unavailable": [
"allocation_basis",
"prior_approval"
]
},
"evidence_ledger": [
{
"item": "award_purpose",
"status": "OBSERVED",
"finding": "award purpose is observed in the worked case.",
"source_refs": [
"notice of award and project narrative"
]
},
{
"item": "cost_description",
"status": "OBSERVED",
"finding": "cost description is observed in the worked case.",
"source_refs": [
"vendor quote"
]
},
{
"item": "project_benefit",
"status": "REPORTED",
"finding": "project benefit is reported in the worked case.",
"source_refs": [
"program manager statement"
]
},
{
"item": "allocation_basis",
"status": "MISSING",
"finding": "allocation basis is missing in the worked case.",
"source_refs": []
},
{
"item": "budget_treatment",
"status": "OBSERVED",
"finding": "budget treatment is observed in the worked case.",
"source_refs": [
"approved budget"
]
},
{
"item": "prior_approval",
"status": "MISSING",
"finding": "prior approval is missing in the worked case.",
"source_refs": []
}
],
"cost_review_route": "PRIOR_APPROVAL_REVIEW",
"allowability_decision": "NOT_MADE",
"dependency_map": [
"Final decision depends on Authorized grants officer or institutional finance owner and every route-changing missing artifact."
],
"next_evidence": [
"allocation_basis",
"prior_approval"
],
"decision_owner": "Authorized grants officer or institutional finance owner",
"limitations": [
"No allowability conclusion.",
"No expense posting.",
"No budget amendment.",
"No agency approval or audit assurance."
]
}
Next step: collect the named missing evidence and complete the authorized domain review before acting.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
A cost can appear necessary and budgeted while still failing award purpose, allocability, reasonableness, consistent treatment, exclusion, documentation, or prior-approval requirements.
What this skill delivers
Federal Grant Cost Allowability Screen turns a proposed or incurred cost into a reviewable 2 CFR Part 200 evidence record. It freezes the award and funding period, maps the cost to purpose, checks allocation and treatment, traces exclusions, credits, indirect-cost handling, procurement support, and prior written approval, then routes unresolved issues.
Why it is different
- Uses the G.R.A.N.T. method: Ground, Relate, Allocate, Note, Trace.
- Separates award terms, evidence, gaps, and accountable ownership.
- Maps dependencies that change prior-approval requirements.
- Does not confuse necessity or budget availability with allowability.
- Produces a consistent cost-review card and escalation route.
Included
Source Skill, domain capsule, source register, worked case, JSON output, validator, forward tests, and a six-page English buyer guide.
Boundaries
No allowability conclusion, expense posting, budget amendment, agency approval, or audit assurance.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
No final allowability conclusion, expense posting, budget amendment, agency approval, or audit assurance. Award terms and authorized grants-officer review remain controlling.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Permissions
No special permissions declared or detected