跳到正文
cccskills
免费在 GitHub 公开

closing-disclosure-decoder

Decode a mortgage Closing Disclosure line by line — which fees are real, which are shoppable or junk, and what changed since the Loan Estimate. Use when asked to decode my closing disclosure, review my closing costs, why did my costs go up, or which fees can I negotiate. Produces a section-by-section decode, the Loan-Estimate comparison with tolerance flags, the challenge list with scripts, and the cash-to-close verification.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(2)

  • SKILL.md4.8 KB
  • references/worked-example.md5.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Closing Disclosure Decoder Skill

The Closing Disclosure arrives three days before the biggest purchase of your life, formatted to discourage reading. This skill reads it: every section in plain English, every fee sorted into real / shoppable / challenge, and — the part with teeth — the comparison against the Loan Estimate, where regulated tolerance rules make some increases the lender's problem, not yours.

What This Skill Produces

  • Section decode — A through J in plain English, the three-day clock stated
  • Fee triage — real and fixed / shoppable-too-late-but-note-it / challenge-now, with amounts
  • The LE comparison — what moved since the Loan Estimate, tolerance category per change
  • Challenge scripts — exact wording for the lender call, ranked by recovery odds
  • Cash-to-close check — the bottom line reconciled against your own math

Required Inputs

Ask for these only if not provided:

  • The Closing Disclosure (page-by-page paste or the figures)
  • The Loan Estimate — the comparison is the leverage; without it, decode-only and say so
  • Closing date — the three-business-day review clock
  • Anything that changed — rate lock, loan amount, program — legitimate changes reset some tolerances

Framework

  1. The tolerance tiers do the work: some fee categories can't increase at all from the LE (lender fees, transfer taxes), some by a limited amount in aggregate (recording, required-provider services), some float freely (prepaids, per-diem interest). Sort every increase into its tier — over-tolerance increases are typically refundable at or after closing. Flag with "tolerance rules per applicable regulation — verify jurisdiction specifics."
  2. Junk-fee pattern list: processing + underwriting + application fees stacked (same work, three names), courier/email fees, padded "doc prep," title add-ons never requested. Challenge with the script, not with anger.
  3. Prepaids aren't fees: escrow, insurance, per-diem interest are your money moving early — decode them as such so the outrage lands only on actual costs.
  4. The math check: loan amount + closing costs − deposits/credits = cash to close. Recompute it; transposition errors at closing are rarer than folklore says but catastrophic when real.
  5. Three days is enough if used: the review clock exists precisely for this reading — schedule the lender call for day one.

Output Format

Closing Disclosure Decode: [property] — closing [date], review clock ends [date]

Verdict: clean / call the lender today about [n] items / discrepancy needs resolution before signing

Sections A–J, decoded [table: line · plain English · triage] Changed since the Loan Estimate | Fee | LE | CD | Δ | Tolerance tier | Your move | The challenge list — ranked, with scripts ("Line B-4 increased $310 beyond the Loan Estimate; that category has zero tolerance — please correct or document the changed circumstance.") Cash to close, reconciled: [their number] vs [computed] — [match/discrepancy]

End verbatim: "This is a plain-language reading, not legal or lending advice — disclosure and tolerance rules vary by jurisdiction and loan type; confirm anything load-bearing with your closing attorney or settlement agent before signing."

Quality Checks

  • Every LE→CD increase is assigned a tolerance tier
  • Prepaids are decoded as your-money-moving, separate from fees
  • Challenge scripts quote line numbers and amounts
  • Cash-to-close is independently recomputed
  • The three-day clock dates appear in the header
  • The disclaimer appears verbatim

Anti-Patterns

  • Do not rage at the total — the leverage lives line-by-line in the tolerance tiers
  • Do not treat prepaid escrow as a junk fee — misdirected outrage burns the real challenges
  • Do not accept "that's standard" on stacked processing fees — standard is not a tolerance category
  • Do not let the clock expire politely — the review period is for reviewing; day one, not day three
  • Do not present tolerance rules as universal law — flag jurisdiction/loan-type variation and refer to the settlement agent

Example Trigger Phrases

  • "Decode my closing disclosure."
  • "Review my closing costs."
  • "Why did my costs go up?"
  • "Which fees can I negotiate?"

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Design a 360-degree feedback survey or write a structured 360 feedback report. Use when asked to build a 360 feedback process, write 360 feedback for a colleague, design a feedback survey, or produce a feedback report. Produces either a complete survey instrument with rating scales and open-ended questions, or a structured narrative feedback report with themes, strengths, and development areas.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14782026年10月21日 更新

Decode a 401k or workplace retirement plan — the real cost of its funds, the match's fine print, vesting math, and the plan features worth using or avoiding. Use when someone asks 'is my 401k any good', 'decode my 401k plan', 'which funds should I look at', or 'what fees am I paying'. Produces a fee decode in dollars-over-time, match and vesting math, a fund-lineup triage by cost, and the questions for HR or the plan administrator.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14782026年10月21日 更新

Design statistically rigorous A/B tests for product features, UI changes, onboarding flows, and pricing experiments. Use when asked to set up an experiment, design an A/B test, calculate sample size, or interpret test results. Produces a complete test plan with hypothesis, variant definitions, sample size, duration estimate, guardrail metrics, and a results interpretation guide.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14782026年10月21日 更新

Analyse a finished A/B test and write the readout — the result, whether it's statistically and practically significant, what it means, and the ship/no-ship call. Use when asked to analyse experiment results, write an A/B test readout, interpret test data, or decide whether to ship a variant. Produces a clear verdict with the lift and confidence, segment cuts, the risks (peeking, novelty, sample), and a recommendation. Distinct from planning a test — this reads results.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14782026年10月21日 更新

Build or tailor an academic CV for faculty, postdoc, research or fellowship applications: publications, grants, teaching, supervision and service in the order the field expects, with consistent citations. Use when asked to write my academic CV, update my CV for a lectureship, tenure-track or postdoc application, format my publications list, or adapt my academic CV for an industry research role. Produces the full academic CV, a field-appropriate section order, a clean publications list in one citation style, and a two-page summary version when asked.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14782026年10月21日 更新

Generate a WCAG 2.2 accessibility audit checklist and remediation suggestions for any UI or design. Use when asked to audit for accessibility, check WCAG compliance, review a design for a11y issues, or create an accessibility remediation plan. Produces a prioritised checklist with pass/fail assessments and specific fixes.

中文简介正在准备中。当前显示原文说明。

mohitagw15856/pm-claude-skills14782026年10月21日 更新

查看 mohitagw15856 的全部技能

报告此技能的问题