Agent skill

Second Opinion Request

by mohitagw15856 in mohitagw15856/pm-claude-skills

Get a second medical opinion without torching the first relationship — when it's warranted, how to raise it with the current doctor, the records package the consulting doctor needs, and how to weigh…

MITAuto-check passed

Install Second Opinion Request

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill second-opinion-request -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills second-opinion-request --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/second-opinion-request .claude/skills/second-opinion-request && 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
second-opinion-request
GitHub stars
1.4k
Token cost
~1.6k tokens
SKILL.md length
846 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Get a second medical opinion without torching the first relationship — when it's warranted, how to raise it with the current doctor, the records package the consulting doctor needs, and how to weigh…

  • Works in 5 steps: Warranted, plainly: major surgery,… → The doctor is not the obstacle: the… → Records make the consult real: imaging… → …
  • Asked should I get a second opinion
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: The Diligence Rules and Output Format, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Second Opinion Request is an agent skill from mohitagw15856/pm-claude-skills. Get a second medical opinion without torching the first relationship — when it's warranted, how to raise it with the current doctor, the records package the consulting doctor needs, and how to weigh two opinions that disagree. Use when asked should I get a second opinion, how do I ask for a second opinion without offending my doctor, what records do I send, or the two doctors disagree now what. Produces the warranted-or-not framing, the raising-it scripts, the records checklist, and the disagreement-weighing…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked should I get a second opinion
  • How do I ask for a second opinion without offending my doctor
  • What records do I send
  • The two doctors disagree now what

Example prompts

  • “/second-opinion-request”

Workflow steps

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

  1. Warranted, plainly: major surgery, cancer diagnoses and staging, rare conditions, treatments with lifelong consequences, a plan that isn't…
  2. The doctor is not the obstacle: the script is direct and unapologetic — "Before we proceed with something this significant, I'd like a…
  3. Records make the consult real: imaging (the actual images, not just reports), pathology slides/blocks where relevant, labs, the treatment…
  4. Independence matters: for major calls, a consultant outside the first doctor's immediate group reads with fresher eyes; for specialized…
  5. Disagreement is information, not deadlock: the move is structured follow-up, not coin-flipping — bring opinion B back to doctor A (and…

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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 no API keys, tokens, secrets or passwords.

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

Context cost

Second Opinion Request loads about 1.6k tokens when it runs. Until then it costs about 137 tokens; SKILL.md has 846 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~137
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 846 words, ~1,606 tokens.

Download SKILL.mdSave it as .claude/skills/second-opinion-request/SKILL.md (or your agent's skills folder).
name
second-opinion-request
description
Get a second medical opinion without torching the first relationship — when it's warranted, how to raise it with the current doctor, the records package the consulting doctor needs, and how to weigh two opinions that disagree. Use when asked should I get a second opinion, how do I ask for a second opinion without offending my doctor, what records do I send, or the two doctors disagree now what. Produces the warranted-or-not framing, the raising-it scripts, the records checklist, and the disagreement-weighing framework.

Second Opinion Request Skill

Second opinions change diagnoses or treatment plans often enough that for major decisions they're due diligence, not disloyalty — and good doctors know it, welcome it, and get them for their own families. The friction is social and logistical, not medical: how to say it to the current doctor, what to actually send, and what to do when the opinions differ. This skill handles exactly those three, and stays out of the medicine itself.

Not quite this? Use the-second-opinion when you want a thinking tool to argue against your own position, not a medical second opinion.

What This Skill Produces

  • The warranted check — the situations where second opinions earn their cost, honestly framed (and the ones where they mostly add delay)
  • The scripts — raising it with the current doctor, requesting the consult, and the insurance-coverage question
  • The records package checklist — what the consulting physician needs, so the visit reviews the case instead of restarting it
  • The disagreement framework — how to structure the follow-up questions when opinions differ, without playing referee on medicine

Required Inputs

Ask for these if not provided:

  • The situation — the diagnosis or recommended treatment, in the user's words; the stakes (surgery, long-term medication, serious diagnosis, "watch and wait" they're uneasy about)
  • The relationship — how the current doctor has responded to questions so far; whether the user fears the conversation (common, and addressable with the script)
  • The logistics — insurance shape, timeline pressure (some decisions have real clocks; the plan respects them), and access to a relevant specialist or center
  • What's driving the wish — uncertainty, a gut mismatch, something read, a family push — it shapes which questions the consult should answer

Framework: The Diligence Rules

  1. Warranted, plainly: major surgery, cancer diagnoses and staging, rare conditions, treatments with lifelong consequences, a plan that isn't working, or a diagnosis made quickly on thin workup. Less warranted: routine matters where delay costs more than confirmation adds — say so honestly; a second opinion is a tool, not a ritual.
  2. The doctor is not the obstacle: the script is direct and unapologetic — "Before we proceed with something this significant, I'd like a second opinion. Would you refer me, and have the records sent?" Good doctors say yes routinely. A doctor who bristles at diligence has become one of the findings.
  3. Records make the consult real: imaging (the actual images, not just reports), pathology slides/blocks where relevant, labs, the treatment plan, and clinic notes — requested per the records process (see medical-records-request). A consult without records is a conversation, not an opinion.
  4. Independence matters: for major calls, a consultant outside the first doctor's immediate group reads with fresher eyes; for specialized conditions, a high-volume center is the honest ask. Framed as considerations, not referrals — this skill names types of consultants, never specific ones.
  5. Disagreement is information, not deadlock: the move is structured follow-up, not coin-flipping — bring opinion B back to doctor A (and vice versa): "The consulting physician suggested X instead — what's your read on why you'd still recommend Y?" The reasons for the difference (different guidelines? risk tolerance? information one had and the other didn't?) are what the patient can actually evaluate; sometimes a third, tie-breaking consult at a referral center is the right spend, and the framework says when.
Show full SKILL.md (303 more words)Show less

Output Format

Second Opinion Plan: [situation]

Is It Warranted Here

[The honest read against the stakes and timeline — including the delay cost if the clock is real]

The Scripts

To your current doctor: "[verbatim — direct, warm, unapologetic]" Booking the consult: "[what to say, what to ask about records and timing]" Insurance: "[the coverage question — flagged plan-specific]"

The Records Package

ItemWhy the consultant needs itHow to get it

If They Disagree

[The take-B-back-to-A structure with verbatim questions · what differences to probe (guidelines, risk tolerance, information gaps) · when a third opinion at a referral center is worth it]

This skill organizes the process — the medical content of both opinions belongs entirely to the physicians. Coverage rules and records rights vary by jurisdiction and plan; verify the specifics.

Quality Checks

  • The warranted check is honest both directions — including when a second opinion mostly adds delay
  • The raising-it script contains zero apology and zero accusation
  • The records checklist includes actual images/slides, not just reports
  • The disagreement structure sends each opinion back to the other doctor, with verbatim questions
  • Timeline pressure is respected — diligence that misses a treatment window isn't diligence

Anti-Patterns

  • Do not weigh in on which opinion is medically right — structure the questions; the medicine is the doctors'
  • Do not script sneaking around the first doctor — the direct version works better and keeps the records flowing
  • Do not recommend specific physicians or centers — types and criteria only
  • Do not treat disagreement as a crisis — it's the process working; the framework exists for exactly this
  • Do not let diligence become avoidance — serial opinion-shopping past two (occasionally three) is a decision not being made, and the artifact should say so

Example Trigger Phrases

  • "Should I get a second opinion?"
  • "How do I ask for a second opinion without offending my doctor?"
  • "What records do I send?"

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/second-opinion-request of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Second Opinion Request 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.

Second Opinion Request compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Second Opinion Request this skillmohitagw15856/pm-claude-skills1.4k—~1.6kAutomated safety check: PassMIT
Second Opinionpeterkrueck/Claude-Code-Development-Kit1.4k—~2.4kAutomated safety check: WarnMIT
Second Opinion Code Reviewtrailofbits/skills7.4k—~1.3kAutomated safety check: NotesCC-BY-SA-4.0
Second Opinion Geminipeterkrueck/Claude-Code-Development-Kit1.4k—~2.3kAutomated safety check: WarnMIT
Claudex Second Opinionccplugins/awesome-claude-code-plugins970—~515Automated safety check: PassApache-2.0
Opinionalsk1992/CloddsBot2.9k—~497Automated safety check: PassMIT

Similar skills

  • Second Opinion

    peterkrueck/Claude-Code-Development-Kit

    Get a second opinion from OpenAI's Codex CLI running locally.

    1.4k GitHub stars~2.4k tokensUpdated 2 mo ago
    DevelopmentAuto-check: warnings
  • Second Opinion Code Review

    trailofbits/skills

    Official

    Runs an independent review of uncommitted changes, a branch diff or one commit through the Codex or Antigravity CLI, or both, and reports their findings.

    7.4k GitHub stars~1.3k tokensUpdated 2 days ago
    DevelopmentAuto-check: notes
  • Second Opinion Gemini

    peterkrueck/Claude-Code-Development-Kit

    Get a second opinion from Google's Gemini Pro via the locally installed Gemini CLI (defaults to gemini-3.1-pro-preview; override with the CLAUDESECONDOPINIONMODEL env var).

    1.4k GitHub stars~2.3k tokensUpdated 2 mo ago
    Auto-check: warnings
  • Claudex Second Opinion

    ccplugins/awesome-claude-code-plugins

    Suggests a cross-model second opinion after substantial or risky code changes.

    970 GitHub stars~515 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Opinion

    alsk1992/CloddsBot

    Opinion.trade prediction market (BNB Chain CLOB). An agent skill from alsk1992/CloddsBot.

    2.9k GitHub stars~497 tokensUpdated 7 days ago
    Business, Finance & HRAuto-check passed
  • Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Second Opinion Request

What does Second Opinion Request do?

Get a second medical opinion without torching the first relationship — when it's warranted, how to raise it with the current doctor, the records package the consulting doctor needs, and how to weigh…. Second Opinion Request is an agent skill from mohitagw15856/pm-claude-skills. Get a second medical opinion without torching the first relationship — when it's warranted, how to raise it with the current doctor, the records package the consulting doctor needs, and how to weigh two opinions that disagree.

When should I use Second Opinion Request?

Second Opinion Request fits situations like: asked should I get a second opinion; how do I ask for a second opinion without offending my doctor; what records do I send; the two doctors disagree now what.

How do I install Second Opinion Request in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill second-opinion-request -a claude-code`. Or copy the skill folder (skills/second-opinion-request in mohitagw15856/pm-claude-skills) into .claude/skills/second-opinion-request in your project. Claude Code loads it when a task matches its description.

How do I install Second Opinion Request in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill second-opinion-request -a codex`. Or copy the skill folder (skills/second-opinion-request in mohitagw15856/pm-claude-skills) into .agents/skills/second-opinion-request in your project. Codex loads it when a task matches its description.

Can I use Second Opinion Request 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 mohitagw15856/pm-claude-skills --skill second-opinion-request -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/second-opinion-request, .gemini/skills/second-opinion-request, .github/skills/second-opinion-request and .opencode/skills/second-opinion-request in your project.

What does Second Opinion Request need to run?

SKILL.md names no scripts, command-line tools or credentials: Second Opinion Request is instructions for the agent only.

Does Second Opinion Request 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 Second Opinion Request 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 Second Opinion Request use?

Second Opinion Request is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Second Opinion Request use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Second Opinion Request?

Skills that share tags, products or a category with Second Opinion Request: Second Opinion (peterkrueck/Claude-Code-Development-Kit, 1.4k stars), Second Opinion Code Review (trailofbits/skills, 7.4k stars), Second Opinion Gemini (peterkrueck/Claude-Code-Development-Kit, 1.4k stars) and Claudex Second Opinion (ccplugins/awesome-claude-code-plugins, 970 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Second Opinion Request?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,433 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 8, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.