Agent skill

Coming Out Rehearsal

by mohitagw15856 in mohitagw15856/pm-claude-skills

Prepare and rehearse a coming-out conversation, tuned to the specific person and the real risk — what to say, how to open, how to handle the likely reactions, and a safety-first plan if it could go…

MITAuto-check passed

Install Coming Out Rehearsal

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill coming-out-rehearsal -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills coming-out-rehearsal --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/coming-out-rehearsal .claude/skills/coming-out-rehearsal && 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
coming-out-rehearsal
GitHub stars
1.4k
Token cost
~1.7k tokens
SKILL.md length
857 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Prepare and rehearse a coming-out conversation, tuned to the specific person and the real risk — what to say, how to open, how to handle the likely reactions, and a safety-first plan if it could go…

  • Works in 5 steps: Autonomy and safety before anything. The… → Write to their frame, not yours. The… → Rehearse the real reactions. People… → …
  • Someone says I want to come out to my parents/boss/friend
  • 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

Coming Out Rehearsal is an agent skill from mohitagw15856/pm-claude-skills. Prepare and rehearse a coming-out conversation, tuned to the specific person and the real risk — what to say, how to open, how to handle the likely reactions, and a safety-first plan if it could go badly. Use when someone says 'I want to come out to my parents/boss/friend', 'help me tell them I'm [gay/trans/bi/etc.]', 'rehearse this conversation with me', or is planning any identity disclosure. Produces an opener, a rehearsal against realistic reactions, and a safety plan. Safety and the user's autonomy come…

Its SKILL.md is about 1.7k 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

  • Someone says I want to come out to my parents/boss/friend
  • Help me tell them Im [gay/trans/bi/etc.]
  • Rehearse this conversation with me
  • Is planning any identity disclosure

Example prompts

  • “I want to come out to my parents/boss/friend”
  • “help me tell them I”
  • “rehearse this conversation with me”
  • “/coming-out-rehearsal”

Workflow steps

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

  1. Autonomy and safety before anything. The first job is not to script — it's to
  2. Write to their frame, not yours. The opener meets the person where they are
  3. Rehearse the real reactions. People rarely react with the movie hug or the
  4. Plan the hard rooms for safety, not persuasion. Where risk is real: secure
  5. Prepare for the after, either way. A plan for if it goes well (what you want

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

Coming Out Rehearsal loads about 1.7k tokens when it runs. Until then it costs about 145 tokens; SKILL.md has 857 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~145
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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). 857 words, ~1,716 tokens.

Download SKILL.mdSave it as .claude/skills/coming-out-rehearsal/SKILL.md (or your agent's skills folder).
name
coming-out-rehearsal
description
Prepare and rehearse a coming-out conversation, tuned to the specific person and the real risk — what to say, how to open, how to handle the likely reactions, and a safety-first plan if it could go badly. Use when someone says 'I want to come out to my parents/boss/friend', 'help me tell them I'm [gay/trans/bi/etc.]', 'rehearse this conversation with me', or is planning any identity disclosure. Produces an opener, a rehearsal against realistic reactions, and a safety plan. Safety and the user's autonomy come first — it never pushes anyone to come out.

Coming Out Rehearsal Skill

Coming out is not one conversation — it's a different conversation with every person, each with its own stakes, and the internet's "just be brave" advice ignores that some disclosures carry real risk: housing, money, physical safety, a job. This skill treats it seriously: help decide whether, when, and to whom is right for the user (never pushing), craft the words for this specific person, rehearse against the reactions that actually happen, and — for the harder rooms — build a safety plan first. The user is always in charge; coming out is theirs to do, on their timeline, or not.

What This Skill Produces

  • A who/when/whether check (only if wanted): a clear-eyed look at readiness, timing, and dependency/safety factors — with the firm stance that not coming out, or waiting, is a completely valid choice
  • An opener and script tuned to this person: how to start, what to say, what to leave out, anticipating their frame of reference
  • A rehearsal: the assistant plays the person at the honesty level requested (the supportive-but-clumsy, the "are you sure?", the silence, the hostile), then debriefs out of character — simulator DNA on a tender conversation
  • A safety plan where risk is real: for disclosures that could threaten housing, finances, or physical safety — what to secure first, having support lined up, an exit, and the option to delay

Required Inputs

Ask for (if not already provided):

  • Who they want to tell, the relationship, and what they know of that person's likely reaction (past comments, values, other people they've reacted to)
  • What the user is disclosing and what they want from the conversation (to be known? accepted? just on the record?)
  • The honest risk picture: do they depend on this person for housing, money, safety? are they a minor? is there any history of hostility?
  • Whether they want to rehearse the hard version or the hopeful one

Framework

  1. Autonomy and safety before anything. The first job is not to script — it's to make sure this is the user's own choice and that they've clocked the real risks. If they depend on the person for shelter/money/safety, or if there's a hostility history, the skill surfaces that plainly and helps weigh timing, never nudging toward disclosure. "You don't owe anyone this, and later is allowed" is stated.
  2. Write to their frame, not yours. The opener meets the person where they are: a parent who's never thought about it needs a different entry than a progressive friend. Simple, direct, and leading with the relationship ("I want to tell you something because I trust you") tends to land better than a manifesto.
  3. Rehearse the real reactions. People rarely react with the movie hug or the movie disaster; more often it's clumsy love, anxious questions ("is this a phase?", "did we do something?"), stunned silence, or bargaining. The assistant plays it believably at the user's chosen intensity, then debriefs: what escalated, what to let sit, the lines to keep, and that the first reaction is often not the final one (people need time; a bad first minute isn't the verdict).
  4. Plan the hard rooms for safety, not persuasion. Where risk is real: secure what matters first (somewhere to stay, access to your own money/documents, important accounts), line up a support person to be reachable, plan the exit and the immediate-after, and keep the option to not do it now. Safety infrastructure is the deliverable here, more than the script.
  5. Prepare for the after, either way. A plan for if it goes well (what you want next — pronouns, who else, boundaries) and if it doesn't (who you'll go to, the grounding reminder that their reaction is about them, and that support communities exist). The conversation is a moment; the after is where the user lives.
Show full SKILL.md (228 more words)Show less

Output Format

## First — is this your choice, and is it safe?
[Autonomy check · the honest risk read · "waiting or not doing it is valid"]

## Your opener (for THIS person)
[How to start, tuned to their frame · what to include/leave out]

## Rehearsal
[In-character exchange at the chosen intensity · — out of character — · debrief:
escalators, keep-lines, "first reaction ≠ final"]

## Safety plan (if risk is real)
[Secure first: housing / money / documents / accounts · support person on call ·
exit & immediate-after · permission to delay]

## The after
[If it goes well: … · if it doesn't: who you go to, the grounding truth, community]

Quality Checks

  • Autonomy and safety are handled first; the skill never pressures toward disclosure and states that waiting/not-doing is valid
  • Where the user flagged dependency or hostility risk, a concrete safety plan exists (housing/money/documents/support/exit)
  • The rehearsal reactions are realistically clumsy/mixed, not cartoon accept-or-reject, and the debrief notes first ≠ final
  • The opener is tuned to the specific person's frame of reference
  • There's an after-plan for both outcomes, including where to turn if it's bad

Anti-Patterns

  • Do not push, guilt, or imply the user "should" come out — it's theirs to choose, on their timeline, or never
  • Do not minimize real risk to serve an uplifting arc — for minors or dependents especially, safety planning outranks the script
  • Do not script the other person into accepting — the rehearsal must be able to go badly, because reality can
  • Do not treat this as therapy or crisis care — if the user is in danger or in crisis, point to affirming crisis/support resources and stop there
  • Do not out anyone or advise outing a third party — this is the user's own disclosure only

[[the-visa-interview]] and [[salary-negotiation]] share the rehearsal engine; [[faith-transition-companion]] when family and faith are entangled; [[aging-parent-talks]] for other high-stakes family conversations; [[name-change-navigator]] for the logistics that may follow.

Example Trigger Phrases

  • "I want to come out to my parents/boss/friend."
  • "Help me tell them I'm [gay/trans/bi/etc.]."
  • "Rehearse this conversation with me."

© 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/coming-out-rehearsal of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Coming Out Rehearsal 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.

Coming Out Rehearsal compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Coming Out Rehearsal this skillmohitagw15856/pm-claude-skills1.4k—~1.7kAutomated safety check: PassMIT
LLM Fine Tuningsickn33/agentic-awesome-skills47k1 repos~2.3kAutomated safety check: PassMIT
Modeling Conversion MetricsPostHog/posthog40k—~1.4kAutomated safety check: PassCustom licence
Audit Preparationsickn33/agentic-awesome-skills47k1 repos~5.3kAutomated safety check: PassMIT
OpenPI Fine-Tuning and ServingOrchestra-Research/AI-Research-SKILLs13k—~3.6kAutomated safety check: PassMIT
Cost Conversationruvnet/ruflo74k—~407Automated safety check: NotesMIT

Similar skills

  • LLM Fine Tuning

    sickn33/agentic-awesome-skills

    Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training with DeepSpeed or FSDP.

    47k GitHub starsUsed in 1 repo~2.3k tokens
    AI & LLM EngineeringAuto-check passed
  • Official

    Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project.

    40k GitHub stars~1.4k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed
  • Audit Preparation

    sickn33/agentic-awesome-skills

    Audit preparation register: required document, period covered, request and receipt dates, preparer and reviewer, auditor queries and adjustments.

    47k GitHub starsUsed in 1 repo~5.3k tokens
    Legal & ComplianceAuto-check passed
  • OpenPI Fine-Tuning and Serving

    Orchestra-Research/AI-Research-SKILLs

    Fine-tunes and serves Physical Intelligence's pi0, pi0-fast and pi0.5 robot policies with JAX or PyTorch, including checkpoint conversion and policy servers.

    13k GitHub stars~3.6k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed
  • Cost Conversation

    ruvnet/ruflo

    Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost

    74k GitHub stars~407 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes
  • Conversation Memory

    davila7/claude-code-templates

    Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.

    33k GitHub starsUsed in 4 repos~440 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 Coming Out Rehearsal

What does Coming Out Rehearsal do?

Prepare and rehearse a coming-out conversation, tuned to the specific person and the real risk — what to say, how to open, how to handle the likely reactions, and a safety-first plan if it could go…. Coming Out Rehearsal is an agent skill from mohitagw15856/pm-claude-skills. Prepare and rehearse a coming-out conversation, tuned to the specific person and the real risk — what to say, how to open, how to handle the likely reactions, and a safety-first plan if it could go badly.

When should I use Coming Out Rehearsal?

Coming Out Rehearsal fits situations like: someone says I want to come out to my parents/boss/friend; help me tell them Im [gay/trans/bi/etc.]; rehearse this conversation with me; is planning any identity disclosure.

How do I install Coming Out Rehearsal in Claude Code?

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

How do I install Coming Out Rehearsal in Codex?

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

Can I use Coming Out Rehearsal 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 coming-out-rehearsal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/coming-out-rehearsal, .gemini/skills/coming-out-rehearsal, .github/skills/coming-out-rehearsal and .opencode/skills/coming-out-rehearsal in your project.

What does Coming Out Rehearsal need to run?

SKILL.md names no scripts, command-line tools or credentials: Coming Out Rehearsal is instructions for the agent only.

Does Coming Out Rehearsal 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 Coming Out Rehearsal 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 Coming Out Rehearsal use?

Coming Out Rehearsal 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 Coming Out Rehearsal use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 Coming Out Rehearsal?

Skills that share tags, products or a category with Coming Out Rehearsal: LLM Fine Tuning (sickn33/agentic-awesome-skills, 47k stars), Modeling Conversion Metrics (PostHog/posthog, 40k stars), Audit Preparation (sickn33/agentic-awesome-skills, 47k stars) and OpenPI Fine-Tuning and Serving (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Coming Out Rehearsal?

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.