Agent skill

Rabbit Hole Rescue

by mohitagw15856 in mohitagw15856/pm-claude-skills

Talk to a family member or friend who's gone down a conspiracy, misinformation, or extremism rabbit hole — without blowing up the relationship or entrenching them further — using connection-first…

MITAuto-check passedProductivity & Automation

Install Rabbit Hole Rescue

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill rabbit-hole-rescue -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills rabbit-hole-rescue --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/rabbit-hole-rescue .claude/skills/rabbit-hole-rescue && 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
rabbit-hole-rescue
GitHub stars
1.4k
Token cost
~1.8k tokens
SKILL.md length
839 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Talk to a family member or friend who's gone down a conspiracy, misinformation, or extremism rabbit hole — without blowing up the relationship or entrenching them further — using connection-first…

  • Works in 5 steps: Understand the need, not just the… → Protect the relationship above all —… → Get curious, not combative. Replace… → …
  • Someone says my dad believes X now
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework and Output Format, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Rabbit Hole Rescue is an agent skill from mohitagw15856/pm-claude-skills. Talk to a family member or friend who's gone down a conspiracy, misinformation, or extremism rabbit hole — without blowing up the relationship or entrenching them further — using connection-first techniques that actually work instead of the facts-and-arguments that don't. Use when someone says 'my dad believes X now', 'my friend's gone down a conspiracy hole', 'how do I talk to them without a fight', or is losing someone to a belief spiral. Produces a conversation approach, what-not-to-do list, and a realistic…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation. 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

  • Someone says my dad believes X now
  • My friends gone down a conspiracy hole
  • How do I talk to them without a fight
  • Is losing someone to a belief spiral

Example prompts

  • “t. Use when someone says”
  • “my friend”
  • “how do I talk to them without a fight”
  • “/rabbit-hole-rescue”

Workflow steps

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

  1. Understand the need, not just the belief. Rabbit holes recruit people through
  2. Protect the relationship above all — it's your only leverage. People leave these
  3. Get curious, not combative. Replace assertions with questions asked in genuine
  4. Plant seeds; don't demand the harvest. The goal of a single conversation is at
  5. Guard your own wellbeing and draw the hard line. Keeping the door open is not

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

Rabbit Hole Rescue loads about 1.8k tokens when it runs. Until then it costs about 155 tokens; SKILL.md has 839 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~155
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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). 839 words, ~1,779 tokens.

Download SKILL.mdSave it as .claude/skills/rabbit-hole-rescue/SKILL.md (or your agent's skills folder).
name
rabbit-hole-rescue
description
Talk to a family member or friend who's gone down a conspiracy, misinformation, or extremism rabbit hole — without blowing up the relationship or entrenching them further — using connection-first techniques that actually work instead of the facts-and-arguments that don't. Use when someone says 'my dad believes X now', 'my friend's gone down a conspiracy hole', 'how do I talk to them without a fight', or is losing someone to a belief spiral. Produces a conversation approach, what-not-to-do list, and a realistic goal. Connection over winning — and it names when to step back for your own wellbeing.

Rabbit Hole Rescue Skill

Watching someone you love disappear into conspiracy theories, misinformation, or extremism is uniquely painful, and almost everything instinct tells you to do — send the debunk, argue the facts, mock the belief — makes it worse, because the belief isn't really about facts. It's usually meeting a need: belonging, certainty, feeling special or in-the-know, a sense of control in a scary world. This skill drops the losing game of fact-warfare and runs the approach researchers and exit-counselors actually use: preserve the relationship (your influence lives entirely in the relationship), stay curious instead of combative, and plant small doubts rather than demand surrender. The realistic goal isn't winning the argument tonight — it's keeping the door open so they have somewhere to come back to.

What This Skill Produces

  • A conversation approach for the specific person: how to engage the belief without attacking them, the questions that invite reflection instead of defense, and how to affirm the relationship even across the divide
  • A what-not-to-do list: the instinctive moves (debunk-dumping, ridicule, ultimatums, "how can you believe that") that entrench them, and why each backfires
  • A realistic goal-set: staged and honest — keep the relationship, keep the door open, plant a doubt, understand the underlying need — instead of the fantasy of a single conversation that snaps them out of it
  • Your own boundaries and wellbeing: what to do when the belief is hateful or the conversations are hurting you — because keeping the door open never means accepting abuse or dehydrating yourself trying to save them

Required Inputs

Ask for (if not already provided):

  • Who it is, the relationship, and how far in they are (dabbling vs deep, and whether it's harming them or others)
  • What they believe and — importantly — what you think it's doing for them (belonging? certainty? feeling important? fear?)
  • What's been tried and how it went (usually arguing; usually badly)
  • What the user actually wants and can sustain — and where their own limits are (hateful content, their own mental health)

Framework

  1. Understand the need, not just the belief. Rabbit holes recruit people through unmet needs — community, certainty in chaos, significance, distrust born of real grievance. The belief is the symptom; the need is the hook. You can't argue someone out of a need with facts. Identify what it's giving them; that's what any real off-ramp has to also provide.
  2. Protect the relationship above all — it's your only leverage. People leave these spirals through relationships with people who stayed kind, not through being defeated in debate. Every argument that damages the relationship reduces your influence to zero and pushes them deeper into the group that's still "loyal." The prime directive: don't become another person who left them.
  3. Get curious, not combative. Replace assertions with questions asked in genuine good faith: "what convinced you?", "is there anything that would change your mind?", "how do you know that source is right?" — Socratic, not gotcha. Sincere curiosity lowers defenses; it also occasionally surfaces the doubt they've been hiding even from themselves.
  4. Plant seeds; don't demand the harvest. The goal of a single conversation is at most one small crack — a question they can't quite answer, a fact that doesn't fit, a moment of feeling loved-anyway. Not a recantation. Entrenchment comes from being cornered; doubt grows in private, later, when they're not defending. Leave, don't press.
  5. Guard your own wellbeing and draw the hard line. Keeping the door open is not infinite tolerance. If the belief is hateful, targets others, or the person becomes abusive, boundaries come first: you can love someone and refuse to host their bigotry, and you can step back from conversations that are hurting you. The skill names when the healthy move is distance, not more rescue — and that walking away from an adult's choices is sometimes the only sane option, and not a failure.
Show full SKILL.md (201 more words)Show less

Output Format

## What the belief is doing for them
[The underlying need — belonging / certainty / significance / grievance / fear]

## Your approach (connection-first)
[How to engage the belief without attacking the person · the curious questions ·
affirming the relationship across the divide]

## Do NOT (and why it backfires)
[Debunk-dumping · ridicule · ultimatums · "how can you believe that" — each with the
entrenchment mechanism]

## The realistic goal (staged)
[Keep the relationship → keep the door open → plant one doubt → understand the need —
NOT win tonight]

## Your limits
[When the content is hateful / the person is abusive / this is hurting you → the
boundary, and permission to step back]

Quality Checks

  • The approach targets the underlying need, not just the false belief
  • Relationship-preservation is framed as the source of all influence
  • The what-not-to-do list explains the backfire mechanism, not just "don't"
  • The goal is realistic and staged — no fantasy of one conversation curing it
  • The user's own boundaries and wellbeing are protected, including permission to step back and the hard line on hateful content

Anti-Patterns

  • Do not supply debunk scripts or fact-arsenal as the primary tool — fact-warfare entrenches; this skill exists because that approach fails
  • Do not counsel ridicule, cornering, or ultimatums — they push people deeper
  • Do not promise the person can be argued back — set the honest, staged goal
  • Do not counsel infinite tolerance — hateful belief and abuse get boundaries, and the user's wellbeing outranks the rescue
  • Do not treat radicalization-with-violence-risk as a conversation problem — name plainly when it needs professional help, a support org for families, or safety authorities

[[aging-parent-talks]] and [[faith-transition-companion]] share the high-stakes-family engine; [[two-worlds-translator]] for other belief divides; [[scam-message-decoder]] and the pm-digital-safety bundle for the misinformation supply side.

Example Trigger Phrases

  • "My dad believes X now."
  • "My friend's gone down a conspiracy hole."
  • "How do I talk to them without a fight?"

© 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/rabbit-hole-rescue of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Rabbit Hole Rescue 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.

Rabbit Hole Rescue compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rabbit Hole Rescue this skillmohitagw15856/pm-claude-skills1.4k—~1.8kAutomated safety check: PassMIT
Agent Browserquran/quran.com-frontend-next1.9k40 repos~3.3kAutomated safety check: PassNone
Dependency Watchtelegramdesktop/tdesktop33k1 repos~2.2kAutomated safety check: PassGPL-3.0
Perform Tasktelegramdesktop/tdesktop33k2 repos~3kAutomated safety check: PassGPL-3.0
Brave Searchbadlogic/pi-skills2.6k5 repos~592Automated safety check: PassMIT
Garden Inboxpaperclipai/paperclip100k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Agent Browser

    quran/quran.com-frontend-next

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    1.9k GitHub starsUsed in 40 repos~3.3k tokens
    Productivity & AutomationAuto-check passed
  • Dependency Watch

    telegramdesktop/tdesktop

    Audit Telegram Desktop dependencies on freshly fetched origin/dev for releases and security fixes, including upstream lag and backport candidates in patched forks.

    33k GitHub starsUsed in 1 repo~2.2k tokens
    Productivity & AutomationAuto-check passed
  • Perform Task

    telegramdesktop/tdesktop

    Resolve, start or resume, implement, review, test, and publish exactly one existing ai-tdesktop task by short slug or full dated id, including rare blocked retries and split-required results.

    33k GitHub starsUsed in 2 repos~3k tokens
    Productivity & AutomationAuto-check passed
  • Brave Search

    badlogic/pi-skills

    Web search and content extraction via Brave Search API. An agent skill from badlogic/pi-skills.

    2.6k GitHub starsUsed in 5 repos~592 tokens
    Productivity & AutomationAuto-check passed
  • Garden Inbox

    paperclipai/paperclip

    Scan a Paperclip user's Mine inbox, classify reversible archive candidates, request checkbox confirmation, and archive only accepted selections.

    100k GitHub stars~1.1k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Continue

    telegramdesktop/tdesktop

    Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.

    33k GitHub starsUsed in 2 repos~9.4k tokens
    Productivity & AutomationAuto-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 2 days ago
    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 2 days ago
    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 2 days ago
    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 2 days ago
    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 2 days ago
    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 2 days ago
    Auto-check passed

Questions about Rabbit Hole Rescue

What does Rabbit Hole Rescue do?

Talk to a family member or friend who's gone down a conspiracy, misinformation, or extremism rabbit hole — without blowing up the relationship or entrenching them further — using connection-first…. Rabbit Hole Rescue is an agent skill from mohitagw15856/pm-claude-skills. Talk to a family member or friend who's gone down a conspiracy, misinformation, or extremism rabbit hole — without blowing up the relationship or entrenching them further — using connection-first techniques that actually work instead of the facts-and-arguments that don't.

When should I use Rabbit Hole Rescue?

Rabbit Hole Rescue fits situations like: someone says my dad believes X now; my friends gone down a conspiracy hole; how do I talk to them without a fight; is losing someone to a belief spiral.

How do I install Rabbit Hole Rescue in Claude Code?

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

How do I install Rabbit Hole Rescue in Codex?

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

Can I use Rabbit Hole Rescue 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 rabbit-hole-rescue -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rabbit-hole-rescue, .gemini/skills/rabbit-hole-rescue, .github/skills/rabbit-hole-rescue and .opencode/skills/rabbit-hole-rescue in your project.

What does Rabbit Hole Rescue need to run?

SKILL.md names no scripts, command-line tools or credentials: Rabbit Hole Rescue is instructions for the agent only.

Does Rabbit Hole Rescue 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 Rabbit Hole Rescue 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 Rabbit Hole Rescue use?

Rabbit Hole Rescue 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 Rabbit Hole Rescue use?

About 1.8k tokens (SKILL.md is roughly 7.1k 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 Rabbit Hole Rescue?

Skills that share tags, products or a category with Rabbit Hole Rescue: Agent Browser (quran/quran.com-frontend-next, 1.9k stars), Dependency Watch (telegramdesktop/tdesktop, 33k stars), Perform Task (telegramdesktop/tdesktop, 33k stars) and Brave Search (badlogic/pi-skills, 2.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Rabbit Hole Rescue?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 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.