Agent skill

Medicaid Exemption Screener

by CALLE-AI in CALLE-AI/awesome-phone-call-agents

Run a consented outbound phone campaign that screens Medicaid enrollees for exemptions from the 2027 work requirement before their coverage check date - clearing whoever the state's own data already…

MITAuto-check passed

Install Medicaid Exemption Screener

skills CLI
$ npx skills add CALLE-AI/awesome-phone-call-agents --skill medicaid-exemption-screener -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install CALLE-AI/awesome-phone-call-agents medicaid-exemption-screener --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/medicaid-exemption-screener .claude/skills/medicaid-exemption-screener && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
medicaid-exemption-screener
GitHub stars
107
Token cost
~1.8k tokens
SKILL.md length
1,017 words
Files
6 (incl. references)
Skills in repo
101
Repo updated
First seen
Licence
MIT

At a glance

Run a consented outbound phone campaign that screens Medicaid enrollees for exemptions from the 2027 work requirement before their coverage check date - clearing whoever the state's own data already…

  • Works in 7 steps: Confirm consent and authorization. The… → Load the list and let the data clear… → Review the rule file.… → …
  • Coverage-retention outreach
  • SKILL.md covers The problem this solves, When To Use, When Not To Use and Core Workflow, plus 3 more sections
  • Needs CALLE_API_KEY

What it does

Medicaid Exemption Screener is an agent skill from CALLE-AI/awesome-phone-call-agents. Run a consented outbound phone campaign that screens Medicaid enrollees for exemptions from the 2027 work requirement before their coverage check date - clearing whoever the state's own data already clears without a call, explaining the rule in the person's language, asking only the exemption questions their record has not answered, and turning every call into a caseworker-reviewed worklist item. Use for coverage-retention outreach, exemption screening, renewal-risk campaigns, and any benefits outreach where the…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/cli.md`, `references/examples.md` and `references/registry-format.md`).

The repository describes itself as: Portable phone-call Agent Skills, apps, examples, adapters, and scheduler recipes for AI agents. The licence is MIT.

When your agent uses it

  • Coverage-retention outreach
  • Exemption screening
  • Renewal-risk campaigns
  • Any benefits outreach where the point is to find people who qualify but will not file the paperwork

Example prompts

  • “/medicaid-exemption-screener”

Requirements

  • A credential in CALLE_API_KEY

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Confirm consent and authorization. The user should say plainly that this is their own
  2. Load the list and let the data clear whoever it can. Run plan first, always. It places no
  3. Review the rule file. rules/federal-2027.json holds the threshold, the plain-language
  4. Rehearse in dry-run. run against the bundled fake CALL-E server exercises webhooks, retries,
  5. Go live only on explicit confirmation. Live mode requires SC_MODE=live, a CALLE_API_KEY,
  6. Hand over the worklist, not a verdict. Report outcomes as proposals: how many were cleared
  7. Resume rather than re-run. If a campaign was interrupted, resume settles pending calls and

What it can do on your machine

Read from SKILL.md and the folder at commit 38d4118. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • CALLE_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Medicaid Exemption Screener loads about 1.8k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 154 tokens; SKILL.md has 1,017 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~154
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from CALLE-AI/awesome-phone-call-agents at commit 38d4118, republished under its MIT licence (© CALLE-AI). 1,017 words, ~1,816 tokens.

Download SKILL.mdSave it as .claude/skills/medicaid-exemption-screener/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
medicaid-exemption-screener
description
Run a consented outbound phone campaign that screens Medicaid enrollees for exemptions from the 2027 work requirement before their coverage check date - clearing whoever the state's own data already clears without a call, explaining the rule in the person's language, asking only the exemption questions their record has not answered, and turning every call into a caseworker-reviewed worklist item. Use for coverage-retention outreach, exemption screening, renewal-risk campaigns, and any benefits outreach where the point is to find people who qualify but will not file the paperwork.
license
MIT

Medicaid Exemption Screener

Use this skill when someone needs to reach a list of benefits enrollees before a deadline and find out which of them are already exempt or already compliant - not to remind them that paperwork is due, but to ask the questions that decide it.

It wraps the apps/typescript/still-covered engine in this repository: ex parte clearing, wave planning by deadline and paperwork risk, one CALL-E call task per person, fail-closed classification, and a human worklist. An agent can drive a whole campaign without reimplementing any of it.

The problem this solves

From 1 January 2027, most adults aged 19-64 on Medicaid must show 80 hours a month of qualifying activity, or about $580 a month in earnings, to keep coverage (P.L. 119-21 section 71119; CMS interim final rule CMS-2454-IFC). Nine categories are exempt.

The evidence is unambiguous about what goes wrong. Arkansas ran a work requirement in 2018: more than 18,000 people lost coverage in seven months with no significant change in employment, because the people who lost coverage were overwhelmingly already working or already exempt and simply never completed the reporting (Sommers et al., NEJM 2019). In the 2023-24 unwinding, 69% of disenrollments were procedural.

So the job is not "remind them." The job is ask them, in a language they speak, and put a reviewable packet in front of a caseworker for everyone whose answers suggest they qualify.

When To Use

  • A state agency, health plan, or community organisation has a consented enrollee list with coverage check dates approaching, and wants to know who is exempt or compliant before the deadline.
  • The user asks to "screen," "check who qualifies," "find who is exempt," or "reach people before they lose coverage."
  • A prior campaign was interrupted and must be resumed without double-dialling anyone.
  • The user wants to rehearse the calls, hear the script, or show a stakeholder what the calls sound like without spending credits - run the dry-run path, which needs no key and places no call.

When Not To Use

  • Do not cold-call people who have not consented to be contacted about their coverage. This engine assumes a consented enrollee list and refuses rows whose consent column is not yes.
  • Do not use it to make or communicate a benefits determination. The agent is explicitly forbidden from telling anyone they are exempt; every verdict is a proposal awaiting a human.
  • Do not use it for marketing, enrolment sales, plan switching, or lead generation.
  • Do not run a live campaign without the user's explicit confirmation that the list is real, authorized, and consented, and without an allowlist during rehearsal.
  • Do not invent rules. If the user's state has its own exemption list, edit the rules file - do not let the agent improvise policy on the call.

Core Workflow

  1. Confirm consent and authorization. The user should say plainly that this is their own enrollee list and that these people agreed to be contacted about their coverage. If they cannot, stop.
  2. Load the list and let the data clear whoever it can. Run plan first, always. It places no call, prints who the state's own record already clears, shows the wave order, and prints the exact task text that would be spoken. See references/registry-format.md for the CSV columns and references/cli.md for the commands.
  3. Review the rule file. rules/federal-2027.json holds the threshold, the plain-language explanation, and all nine exemptions with their question text and order. If the user's state differs, edit the JSON. See references/rules-and-questions.md.
  4. Rehearse in dry-run. run against the bundled fake CALL-E server exercises webhooks, retries, idempotency and the full worklist with no network and no credentials.
  5. Go live only on explicit confirmation. Live mode requires SC_MODE=live, a CALLE_API_KEY, and --confirm. Set SC_LIVE_ALLOWLIST for any rehearsal so a real enrollee cannot be reached by accident. Read references/safety.md before this step, every time.
  6. Hand over the worklist, not a verdict. Report outcomes as proposals: how many were cleared without a call, how many look exempt and need a caseworker's review, how many are at risk, how many could not be reached and need a letter. Never tell the user that someone "is exempt."
  7. Resume rather than re-run. If a campaign was interrupted, resume settles pending calls and re-places refused tasks with their original idempotency keys. Re-running run is not the way to recover, and resume on a finished campaign places no new call at all.
Show full SKILL.md (284 more words)Show less

The Rules That Are Not Negotiable

These are enforced in code, not just in the prompt. Do not try to work around them.

  • Ex parte first. Anyone the state's data already clears is never called.
  • Fail closed. Silence, ambiguity, a cut-off call, or a health condition without a daily-activity limitation produces needs_review - never an exemption.
  • Identity before disclosure. Nothing about Medicaid or coverage is said until the person confirms their birth year, and the agent never says the year first.
  • The voicemail must not mention Medicaid. Validated when the state file loads.
  • Three calls, maximum, per person, per campaign. A hard cap independent of configuration.
  • A refused API request is not_attempted, never unreachable. Our failure never becomes the person's verdict.
  • Live campaigns start from the CLI only. The dashboard returns 403.

See references/safety.md for the complete boundary list, including what the agent may never ask for.

Worked Examples

references/examples.md walks through: a clean dry-run campaign and how to read its output; a Spanish-language call end to end; the person whose condition does not limit daily activities and why that becomes needs_review; the agent overclaiming an exemption and the correction call that follows; a platform outage; and a resumed campaign.

Reporting Results

Summarize in this shape, and in this order:

  • cleared by state data, no call needed
  • may qualify for an exemption - packet waiting on a caseworker
  • may already meet the requirement - needs to report hours
  • at risk - navigator callback booked
  • needs review / could not be reached - letter and community outreach
  • how many had never heard of the rule before the call

That last number is usually the one a programme director cares about most, and it is the one only a conversation can produce.

© CALLE-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/medicaid-exemption-screener of CALLE-AI/awesome-phone-call-agents.

  • SKILL.md
  • references/cli.md
  • references/examples.md
  • references/registry-format.md
  • references/rules-and-questions.md
  • references/safety.md

Open the folder on GitHubat commit 38d4118

Compare with similar skills

Medicaid Exemption Screener next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Medicaid Exemption Screener compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Medicaid Exemption Screener this skillCALLE-AI/awesome-phone-call-agents107—~1.8kAutomated safety check: PassMIT
PhoneBlockRunAI/ClawRouter6.6k—~2.4kAutomated safety check: PassMIT
Marketing Campaignaffaan-m/ECC277k1 repos~1.3kAutomated safety check: PassMIT
Cookie Consentthedaviddias/Front-End-Checklist74k—~637Automated safety check: PassMIT
Consent Modethedaviddias/Front-End-Checklist74k—~425Automated safety check: PassMIT
Quality Screenxbtlin/ai-berkshire17k—~1.2kAutomated safety check: PassMIT

Similar skills

  • Phone

    BlockRunAI/ClawRouter

    Verify phone numbers (carrier + SIM-swap fraud signals) and place AI-powered outbound voice calls via BlockRun's gateway (Twilio + Bland.ai).

    6.6k GitHub stars~2.4k tokensUpdated 5 days ago
    Auto-check passed
  • Marketing Campaign

    affaan-m/ECC

    End-to-end marketing campaign planning and execution. An agent skill from affaan-m/ECC.

    277k GitHub starsUsed in 1 repo~1.3k tokens
    Marketing & SEOAuto-check passed
  • Cookie Consent

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing a website for GDPR/CCPA compliance, specifically whether cookie consent is obtained before non-essential cookies are set.

    74k GitHub stars~637 tokensUpdated 4 days ago
    Legal & ComplianceAuto-check passed
  • Consent Mode

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Implement Google Consent Mode v2.

    74k GitHub stars~425 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Quality Screen

    xbtlin/ai-berkshire

    Screens companies against seven hard financial tests and exemption rules to rule out clearly non-top-tier businesses, for single stocks, industries or indexes.

    17k GitHub stars~1.2k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed
  • Bio Crispr Screens Screen Qc

    FreedomIntelligence/OpenClaw-Medical-Skills

    Quality control for pooled CRISPR screens. An agent skill from FreedomIntelligence/OpenClaw-Medical-Skills.

    3.1k GitHub stars~2.1k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed

More from CALLE-AI/awesome-phone-call-agents

All 101 skills in this repo
  • Accessible Outing Verifier

    CALLE-AI/awesome-phone-call-agents

    Demonstrates advisory accessibility-planning checks with offline fixtures and a proposed bounded CALL-E workflow; use for exploring unknown or qualified venue claims without making calls.

    107 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Ground Truth Gate

    CALLE-AI/awesome-phone-call-agents

    A skill your agent uses when an agent holds some evidence for a physical-world claim but the evidence is broader, narrower, or older than the exact question asked, and it must first decide whether a…

    107 GitHub stars~3.3k tokensUpdated yesterday
    Auto-check passed
  • Is It Accessible

    CALLE-AI/awesome-phone-call-agents

    Call a venue and ask the accessibility questions that matter to one specific person — step-free entry, hearing loop, guide dogs, quiet hours, changing places — then return a per-need verdict backed…

    107 GitHub stars~4.3k tokensUpdated yesterday
    Auto-check passed
  • Landmark Navigation Assist

    CALLE-AI/awesome-phone-call-agents

    Turns a pre-written, building-level location config into a CALL-E outbound phone-call task that guides a delivery driver through the last few hundred metres to a specific building using landmarks…

    107 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Research Gap Call Verifier

    CALLE-AI/awesome-phone-call-agents

    Turn cited business research into a bounded, approval-gated phone-call plan that asks only unresolved factual questions, then reconcile CALL-E-compatible results without treating voicemail, refusal…

    107 GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed
  • Structured Outcome Followup Call

    CALLE-AI/awesome-phone-call-agents

    Place a goal-driven CALL-E call that collects specific structured answers, score those answers against a deterministic rubric you supply, and conditionally trigger a follow-up action — all runnable…

    107 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Questions about Medicaid Exemption Screener

What does Medicaid Exemption Screener do?

Run a consented outbound phone campaign that screens Medicaid enrollees for exemptions from the 2027 work requirement before their coverage check date - clearing whoever the state's own data already…. Medicaid Exemption Screener is an agent skill from CALLE-AI/awesome-phone-call-agents. Run a consented outbound phone campaign that screens Medicaid enrollees for exemptions from the 2027 work requirement before their coverage check date - clearing whoever the state's own data already clears without a call, explaining the rule in the person's language, asking only the exemption questions their record has not answered, and turning every call into a caseworker-reviewed worklist item.

When should I use Medicaid Exemption Screener?

Medicaid Exemption Screener fits situations like: coverage-retention outreach; exemption screening; renewal-risk campaigns; any benefits outreach where the point is to find people who qualify but will not file the paperwork.

How do I install Medicaid Exemption Screener in Claude Code?

Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill medicaid-exemption-screener -a claude-code`. Or copy the skill folder (skills/medicaid-exemption-screener in CALLE-AI/awesome-phone-call-agents) into .claude/skills/medicaid-exemption-screener in your project. Claude Code loads it when a task matches its description.

How do I install Medicaid Exemption Screener in Codex?

Run `npx skills add CALLE-AI/awesome-phone-call-agents --skill medicaid-exemption-screener -a codex`. Or copy the skill folder (skills/medicaid-exemption-screener in CALLE-AI/awesome-phone-call-agents) into .agents/skills/medicaid-exemption-screener in your project. Codex loads it when a task matches its description.

Can I use Medicaid Exemption Screener in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add CALLE-AI/awesome-phone-call-agents --skill medicaid-exemption-screener -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/medicaid-exemption-screener, .gemini/skills/medicaid-exemption-screener, .github/skills/medicaid-exemption-screener and .opencode/skills/medicaid-exemption-screener in your project.

What does Medicaid Exemption Screener need to run?

Going by SKILL.md and its folder, Medicaid Exemption Screener needs credentials named CALLE_API_KEY. Our summary lists: A credential in CALLE_API_KEY.

Does Medicaid Exemption Screener access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Medicaid Exemption Screener safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Medicaid Exemption Screener use?

Medicaid Exemption Screener is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Medicaid Exemption Screener use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9k tokens, read only when the agent opens those files.

What are the alternatives to Medicaid Exemption Screener?

Skills that share tags, products or a category with Medicaid Exemption Screener: Phone (BlockRunAI/ClawRouter, 6.6k stars), Marketing Campaign (affaan-m/ECC, 277k stars), Cookie Consent (thedaviddias/Front-End-Checklist, 74k stars) and Consent Mode (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Medicaid Exemption Screener?

CALLE-AI (a GitHub organization) maintains it in CALLE-AI/awesome-phone-call-agents, which has 107 GitHub stars. The repository holds 101 skills in this directory. The repository was last updated on October 10, 2026.

Source: CALLE-AI/awesome-phone-call-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.