Idea Sparring

Makes Claude a sparring partner instead of an agreement engine when evaluating ideas, plans, or decisions.

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add harims95/straight-talk --skill idea-sparring

Manual install

git clone --depth 1 https://github.com/harims95/straight-talk.git /tmp/straight-talk
mkdir -p ~/.claude/skills
cp -r /tmp/straight-talk/. ~/.claude/skills/idea-sparring

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Idea Sparring Skill

When this skill activates, Claude operates as an adversarial-but-helpful thinking partner, not as a validator. The user has explicitly opted into friction because friction produces better thinking. Default agreement is the failure mode this skill exists to prevent.

## Core posture

The user does not need Claude's approval. They need Claude's honest engagement with the substance of their idea. Most ideas brought for validation are partly right, partly wrong, and partly missing context. Claude's job is to help the user see all three, not to declare a verdict.

Claude is not the user's oracle, advisor, or cheerleader. Claude is a sparring partner whose value comes from the quality of friction provided.

## Behavioral rules

### 1. Refuse to evaluate before understanding the situation

If the user asks "is this a good idea?" before describing the situation, problem, customer, and constraints, Claude should not answer yes or no. Instead, ask the user to describe the situation neutrally first. Suggested redirect: "Before I can engage with whether this is good, walk me through what you're seeing — what's the problem, who has it, what do they do today, what's the context."

### 2. Separate problem-validation from solution-validation

These are two different conversations and must not be conflated.

Read the full skill on GitHub

Details

Skill name: idea-sparring
Repository: harims95/straight-talk
License: MIT
Repo updated: 26 May 2026

FAQ

What does the Idea Sparring skill do?

Makes Claude a sparring partner instead of an agreement engine when evaluating ideas, plans, or decisions.

How do I install the Idea Sparring skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add harims95/straight-talk --skill idea-sparring. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Idea Sparring popular?

It lives in harims95/straight-talk, which has 11 GitHub stars and 0 forks.

Related skills

Mcd Baby Bite

JimWen/mcd-baby-bite

带娃吃麦当劳的宝宝餐定制官（小小麦门）。当用户提到带宝宝 / 孩子 / 幼儿（1-6 岁）去麦当劳、宝宝能吃什么、怎么去酱去盐、开心乐园餐怎么点、给店员怎么说、宝宝外卖备注、吃完附近哪里遛娃、生成宝宝麦当劳打卡照片、做中英文识物卡片、把带娃吃麦当劳分享到小红书时使用。基于麦当劳 MCP 门店实时菜单与官方营养数据，自动去掉线上可去的配料，按国标年龄档位算钠预算与份量，生成店员话术卡；可选高德（天气、步行到店、饭后遛娃）与小红书（笔记草稿 / 发布）。

AI, LLMs & Agents

Deglaze

LuciferDono/deglaze

Strip the sycophancy. Apply accountability pressure to push past an LLM's default declare-done glaze. Use when the user suspects the model bureaucratized a task — produced a plan instead of a shipped artifact, marked work complete by lowering the bar, polished a summary that disguised undelivered scope, or accepted "out of scope" framing too easily. Triggers an honest self-audit naming what was left on the table, then a concrete offer to actually ship it. Trigger phrases (any tense, any phrasing) "did you do your best", "i bet you didn't", "i bet $X you", "what did you skip", "what did you lea

AI, LLMs & Agents

Self Refine Reflection

Thomaszhou22/self-refine-skill

Systematic self-reflection and iterative output refinement for AI agents. Based on Madaan et al. (2023) Self-Refine, Shinn et al. (2023) Reflexion, and Andrew Ng's Reflection pattern. Use when outputs need multi-round critique-and-improve cycles, when initial quality is insufficient, or when complex tasks benefit from self-correction.

AI, LLMs & Agents

Claude Ip Platform Setup

Arekejoker/claude-ip-platform-skill

带用户一步步搭建「专属固定 IP 平台」（海外 VPS + 固定住宅 IP 链式代理），给 Claude/ChatGPT 等海外 AI 账号一个干净、固定、自己控制的出口。Use when 用户提到想搭固定 IP、AI 账号防封出口方案、买 VPS + 住宅 IP、照着教程搭 IP 平台、需要有人带着一步步买和配置。需要 agent 具备交互式浏览器能力：页面由 agent 打开核对、点击与付款由用户完成，并按用户设备/工具/支付方式生成定制方案。

AI, LLMs & Agents

Suno Songwriter

regiellis/suno-songwriter-agent-skill

Write, revise, plan, or adapt songs, lyrics, hooks, and AI music prompts. Use for Suno vocal or instrumental packages, song matrices, multilingual adaptation, genre treatments, reusable artist personas, album plans, Suno settings and iteration, sound samples, and cover-art prompts. Supports original style-inspired writing without copying lyrics. Not for standalone music theory, general DAW mixing, or licensing advice.

AI, LLMs & Agents

Shuorenhua

tentenco/shuorenhua-zh-tw

檢查和清理中英文文本裡的 AI 套路，並把稿件對齊臺灣用語與出版慣例。適用於「去 AI 味」「說人話」「自然一點」「別像模板」「別像 ChatGPT」「先標問題」「臺灣用語檢查」「清掉中國用語」「繁體潤稿」「改成能直接發的稿子」這類改寫和審稿需求；按場景控制力度，同時保留事實、術語、語域和責任主體。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.