agentsclimarketplace

Strategy

Skill nathan8823/fairbill/.claude/skills/strategy

Turn your AI agent into a medical-bill negotiation advocate — an open-source playbook of skills, letters, and verified patient rights. Pay what's fair, nothing more.

Install
npx -y skills add nathan8823/fairbill --skill strategy

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Choose the negotiation play and write the game plan — target number, sequence, escalation ladder, deadlines. Use once evidence is gathered (bill audited, prices benchmarked, assistance screened).

SKILL.md

2.8 KB, 613 tokens by cl100k_base, as published. Nobody here has run it

Strategy — pick the play

Inputs from the case file: audit findings, benchmark table, assistance screening, insurance posture, collections status, what the user can pay. Output: a written game plan in case.md the user signs off on.

The decision tree (first match wins as PRIMARY play; others stack behind it)

  1. Court summons exists → not a negotiation. Legal aid, answer the summons, pause everything else.
  2. Collector involved & validation window open → validate first (collections skill), negotiate after.
  3. Charity-care screening says likely eligible → apply (financial- assistance); hold all payment; negotiation only for any remainder.
  4. No Surprises Act facts (OON provider at in-network facility, emergency OON, or bill > GFE + $400) → rights-based dispute / PPDR (rights-and-laws.md §1, templates/letters/nsa-complaint.md), not a discount request.
  5. Confirmed billing errors → error dispute letter first; negotiate the corrected balance after they respond.
  6. Insurance denied/underpaid wrongly → insurance-appeal before paying anything.
  7. Bill is real, priced absurdly (the common case) → evidence-based settlement: benchmark table + written offer.
  8. Bill is real and fairly priced (rare, but happens — say so honestly) → hardship adjustment request + interest-free payment plan sizing.

Writing the game plan

Put in case.md:

  • Primary play + stacked plays, in order, each with its trigger ("if FAP denied → settlement offer at $X").
  • Numbers: walk-away target, opening offer, absolute max the user can pay. Anchor all three to the benchmark table.
  • Channel sequence: written where possible; phone to locate the right human, letters to commit positions. Certified mail for anything rights-based (send-letter).
  • Deadlines: theirs and ours (validation clock, 240-day FAP window, PPDR 120 days, promised response dates). Every deadline gets a date.
  • Escalation ladder with the specific next rung named (knowledge/tactics.md).

Rules of engagement

  • One position at a time: never simultaneously claim "I can't afford this" and "I'll pay $X today" to the same office. Sequence: rights/errors → assistance → money.
  • Every phone commitment gets a same-day written recap.
  • No payment until settlement terms are confirmed in writing ("payment in full," account number, amount, signature block).
  • Present the plan to the user in dollars: "billed $14,200 → target $3,100, here's the path" — then get their go before executing.

Gives 0 of the 12 instructions most roadmap strategy skills give in 613 tokens

Counted across 591 of the 672 authors here whose files we hold, read 2026-08-06

  • read product marketing context before asking questionsin 21 of 591, across 10 files
  • base price on perceived value, not costin 15 of 591, across 4 files
  • compact after finalizing a planin 14 of 591, across 9 files
  • differentiate tiers using features, limits, or supportin 14 of 591, across 3 files
  • use Van Westendorp to find acceptable price rangein 13 of 591, across 2 files
  • use MaxDiff to identify highly valued featuresin 13 of 591, across 2 files
  • map topics to buyer journey stagesin 12 of 591, across 6 files
  • Extract domain capabilities and classify subdomainsin 11 of 591, across 1 file
  • Define bounded contexts around consistency and ownershipin 11 of 591, across 1 file
  • Establish a ubiquitous language glossary and anti-termsin 11 of 591, across 1 file
  • Capture context boundaries in ADRs before implementationin 11 of 591, across 1 file
  • Open the strategic design template if neededin 11 of 591, across 1 file

Said here and by no other author read

  • handle court summons before any negotiation
  • validate debt before negotiating with a collector
  • apply for charity-care before negotiating any remainder
  • dispute billing errors before negotiating the balance
  • appeal wrong insurance denials before paying anything
  • anchor walk-away target opening offer and maximum to benchmarks

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.