Agent skill

The Third Answer

by mohitagw15856 in mohitagw15856/pm-claude-skills

Push past the first few obvious answers to a question and surface the non-obvious idea worth having.

MITAuto-check passed

Install The Third Answer

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill the-third-answer -a claude-code

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

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills the-third-answer --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/the-third-answer .claude/skills/the-third-answer && 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
the-third-answer
GitHub stars
1.4k
Token cost
~963 tokens
SKILL.md length
489 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Push past the first few obvious answers to a question and surface the non-obvious idea worth having.

  • Works in 5 steps: List the obvious out loud. Write the… → Set them aside. Treat every obvious… → Change the frame, not just the answer.… → …
  • Asked to give me a non-obvious idea
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: Name The Obvious,… and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The Third Answer is an agent skill from mohitagw15856/pm-claude-skills. Push past the first few obvious answers to a question and surface the non-obvious idea worth having. Use when asked to give me a non-obvious idea, don't give me the generic answer, think outside the box on, or what's the answer nobody else would give. Produces the obvious answers named and set aside (so we don't repeat them), then genuinely different angles found by continuing past where most thinking stops, each with why it's non-obvious and whether it actually holds up — trading textbook-correct for…

Its SKILL.md is about 960 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 to give me a non-obvious idea
  • Dont give me the generic answer
  • Think outside the box on
  • Whats the answer nobody else would give

Example prompts

  • “t give me the generic answer, think outside the box on, or what”
  • “/the-third-answer”

Workflow steps

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

  1. List the obvious out loud. Write the textbook answers explicitly — this is what stops us from unconsciously returning to them.
  2. Set them aside. Treat every obvious answer as off-limits; the interesting territory starts where they end.
  3. Change the frame, not just the answer. Re-ask the question from a different discipline, timescale, or actor — a new angle produces new…
  4. Chase the ones that feel slightly wrong. The idea you almost dismissed is often where the value is; develop it instead of discarding it.
  5. Then judge honestly. Separate the unconventional-and-useful from the unconventional-and-dumb — novelty without a reality check is noise.

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

The Third Answer loads about 963 tokens when it runs. Until then it costs about 137 tokens; SKILL.md has 489 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
~963

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). 489 words, ~963 tokens.

Download SKILL.mdSave it as .claude/skills/the-third-answer/SKILL.md (or your agent's skills folder).
name
the-third-answer
description
Push past the first few obvious answers to a question and surface the non-obvious idea worth having. Use when asked to give me a non-obvious idea, don't give me the generic answer, think outside the box on, or what's the answer nobody else would give. Produces the obvious answers named and set aside (so we don't repeat them), then genuinely different angles found by continuing past where most thinking stops, each with why it's non-obvious and whether it actually holds up — trading textbook-correct for surprising-and-useful.

The Third Answer

The first answer to any open question is the average of everything ever said about it — correct, safe, and forgettable. This skill deliberately names those obvious answers, sets them aside, and keeps going to the ideas most people never reach because they stopped at "good enough." The goal isn't cleverness for its own sake; it's the genuinely useful angle hiding past the generic ones.

What This Skill Produces

  • The obvious answers, named — the 2–4 things anyone (or any search) would say, listed so we explicitly don't settle for them
  • The non-obvious angles — ideas found by continuing past the obvious, each from a genuinely different frame
  • Why each is non-obvious — what assumption or default it breaks
  • A reality check — which of the unconventional ideas actually hold up vs. which are just different for the sake of it

Required Inputs

Ask for these if not provided:

  • The question or problem — the open-ended thing you want a fresh take on
  • What you've already considered — so we skip your obvious answers too
  • Constraints — what's actually fixed vs. what everyone just assumes is fixed
  • The bar — surprising-but-doable, or genuinely wild

Framework: Name The Obvious, Then Keep Going

  1. List the obvious out loud. Write the textbook answers explicitly — this is what stops us from unconsciously returning to them.
  2. Set them aside. Treat every obvious answer as off-limits; the interesting territory starts where they end.
  3. Change the frame, not just the answer. Re-ask the question from a different discipline, timescale, or actor — a new angle produces new answers, more thinking on the same angle doesn't.
  4. Chase the ones that feel slightly wrong. The idea you almost dismissed is often where the value is; develop it instead of discarding it.
  5. Then judge honestly. Separate the unconventional-and-useful from the unconventional-and-dumb — novelty without a reality check is noise.
Show full SKILL.md (183 more words)Show less

Output Format

Question: [the problem]

The obvious answers (we're skipping these): [2–4 generic ones].

Past the obvious

  1. [Angle] — [the idea]. Non-obvious because [assumption it breaks]. Holds up? [yes/partly/risky].
  2. [Angle] — …

Worth pursuing: [the 1–2 that survive scrutiny].

Quality Checks

  • The obvious answers are explicitly named and set aside
  • New ideas come from changed frames, not more of the same angle
  • Each non-obvious idea says what default it breaks
  • A genuine reality check separates useful from merely-different
  • The output would make someone go "oh — I hadn't thought of that"

Anti-Patterns

  • Dressing up the obvious answer in fancier words and calling it novel.
  • Different for the sake of different with no reality check.
  • Stopping at three ideas when the good one was the fifth.
  • Ignoring real constraints while breaking fake ones.

Example Trigger Phrases

  • "Give me a non-obvious angle on pricing my product."
  • "Don't give me the generic answer — how should I actually grow this?"
  • "What's an idea for this problem that nobody else would suggest?"
  • "Think outside the box on how to spend my Saturday."
  • "Skip the textbook answer — what's the interesting take?"

© 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/the-third-answer of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

The Third Answer 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.

The Third Answer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
The Third Answer this skillmohitagw15856/pm-claude-skills1.4k—~963Automated safety check: PassMIT
Multi-Symbol Market Scannertradesdontlie/tradingview-mcp6.8k2 repos~447Automated safety check: PassCustom licence
Pine Script Development Looptradesdontlie/tradingview-mcp6.8k2 repos~617Automated safety check: PassCustom licence
CCXT Crypto Exchange Library2025Emma/vibe-coding-cn23k1 repos~4.4kAutomated safety check: PassMIT
TqSdk Trading and Datashinnytech/tqsdk-python5.1k—~2kAutomated safety check: PassApache-2.0
Trader Memory Coretradermonty/claude-trading-skills3k2 repos~4.3kAutomated safety check: PassMIT

Similar skills

  • Multi-Symbol Market Scanner

    tradesdontlie/tradingview-mcp

    Scans a list of trading symbols in TradingView for setups, patterns or strategy results and reports them as a ranked comparison table.

    6.8k GitHub starsUsed in 2 repos~447 tokens
    Business, Finance & HRAuto-check passed
  • Pine Script Development Loop

    tradesdontlie/tradingview-mcp

    Runs a write, compile, fix and verify loop for TradingView Pine Script indicators and strategies, pushing code into the Pine Editor and checking it on the chart.

    6.8k GitHub starsUsed in 2 repos~617 tokens
    Business, Finance & HRAuto-check passed
  • CCXT Crypto Exchange Library

    2025Emma/vibe-coding-cn

    Reference help for the CCXT library covering crypto exchange APIs, market data, trading and order management across 150+ exchanges in JavaScript, Python and PHP.

    23k GitHub starsUsed in 1 repo~4.4k tokens
    Business, Finance & HRAuto-check passed
  • TqSdk Trading and Data

    shinnytech/tqsdk-python

    Answers TqSdk Python questions on market data, accounts, orders, margin trials, simulation and backtesting, using the library's own docs and examples.

    5.1k GitHub stars~2k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Trader Memory Core

    tradermonty/claude-trading-skills

    Track investment theses across their lifecycle — from screening idea to closed position with postmortem.

    3k GitHub starsUsed in 2 repos~4.3k tokens
    DevOps & CloudAuto-check passed
  • Connects an agent to the AI-Trader platform's API to publish trading signals and follow traders, routing to child skills for copy trading, trade sync and market data.

    23k GitHub stars~8.5k tokensUpdated 4 mo ago
    Business, Finance & HRAuto-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 The Third Answer

What does The Third Answer do?

Push past the first few obvious answers to a question and surface the non-obvious idea worth having. The Third Answer is an agent skill from mohitagw15856/pm-claude-skills. Push past the first few obvious answers to a question and surface the non-obvious idea worth having.

When should I use The Third Answer?

The Third Answer fits situations like: asked to give me a non-obvious idea; dont give me the generic answer; think outside the box on; whats the answer nobody else would give.

How do I install The Third Answer in Claude Code?

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

How do I install The Third Answer in Codex?

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

Can I use The Third Answer 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 the-third-answer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/the-third-answer, .gemini/skills/the-third-answer, .github/skills/the-third-answer and .opencode/skills/the-third-answer in your project.

What does The Third Answer need to run?

SKILL.md names no scripts, command-line tools or credentials: The Third Answer is instructions for the agent only.

Does The Third Answer 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 The Third Answer 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 The Third Answer use?

The Third Answer 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 The Third Answer use?

About 963 tokens (SKILL.md is roughly 3.9k 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 The Third Answer?

Skills that share tags, products or a category with The Third Answer: Multi-Symbol Market Scanner (tradesdontlie/tradingview-mcp, 6.8k stars), Pine Script Development Loop (tradesdontlie/tradingview-mcp, 6.8k stars), CCXT Crypto Exchange Library (2025Emma/vibe-coding-cn, 23k stars) and TqSdk Trading and Data (shinnytech/tqsdk-python, 5.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains The Third Answer?

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.