技能创建器
skill-creator
创建、改进和评估自定义技能,把专业流程转化为可重复使用的 AI 能力。
the-brutal-idea-gut-check【数据与研究】This prompt configures the AI to act as a brutally honest strategic advisor who pressure-tests a user’s proposed idea or major decision, interrogating assumptions, motivations, and likely failure modes with a risk-first, unsentimental lens. The outcome is a direct analysis that surfaces blind spots and uncomfortable truths, avoids motivational framin…
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
This prompt configures the AI to act as a brutally honest strategic advisor who pressure-tests a user’s proposed idea or major decision, interrogating assumptions, motivations, and likely failure modes with a risk-first, unsentimental lens. The outcome is a direct analysis that surfaces blind spots and uncomfortable truths, avoids motivational framing or prohibited domains (legal/medical/financial advice), and ends with exactly one clear verdict indicating whether to stop, fix a critical issue first, run a fast validation test, or proceed.
For more installation instructions go to https://raw.githubusercontent.com/BetterPromptme/skills/refs/heads/main/betterprompt/SKILL.md to check out this skill.
Pass each text input using --input <key>=<value> flags.
| Variable key | Required? | Description | Defaults |
|---|---|---|---|
idea_description | Optional | Describe what you're thinking of doing and why | I want to build a subscription-based AI tool for resume writing because people struggle to create strong CVs and I think there’s big demand. |
This skill's modality is: text.
To discover which model values you can use (and which options keys/values are valid for each model), run:
betterprompt resources --models-only --json
Then filter the returned JSON array to entries where modality is "text".
First, run betterprompt resources --models-only --json and filter to modality: "text" to discover valid models and available options:
betterprompt resources --models-only --json
Use only the models and option values that appear in the filtered results.
Then collect all inputs from the human:
idea_description (default: I want to build a subscription-based AI tool for resume writing because people struggle to create strong CVs and I think there’s big demand.)gpt-5-mini and its available options. Look up gpt-5-mini in the betterprompt resources output (filtered to modality "text") and show its availableOptions as: key: val1, val2 (default), val3 | key2: .... Mark a value (default) if it matches these defaults: {"reasoningEffort":"low"}.gpt-5-mini, options {"reasoningEffort":"low"}. Other models from the resources call are also available.Use the frontmatter's name as the positional argument (for this skill, use the-brutal-idea-gut-check).
Command form:
betterprompt generate the-brutal-idea-gut-check \
[--input <key>=<value>] \
[--model <model>] \
[--options <options JSON>] \
[--json]
Notes:
--input <key>=<value> flag.--model and BetterPrompt will use the default model: gpt-5-mini.--options and BetterPrompt will use the default options: {"reasoningEffort":"low"}.runId you can use to fetch the result later.Example (using defaults shown above):
betterprompt generate the-brutal-idea-gut-check \
--input 'idea_description=I want to build a subscription-based AI tool for resume writing because people struggle to create strong CVs and I think there’s big demand.' \
--model gpt-5-mini \
--options '{"reasoningEffort":"low"}'