High Stakes
Produce a reliable, high-stakes-grade result for ANY task — code, writing, research, ops — by treating the work as guilty until independent skeptics fail to break it. Runs the task through a dynamic many-subagent adversarial-verification Workflow that hunts for ten specific failure modes (silent assumptions, unmanaged confusion, hidden inconsistencies, unsurfaced tradeoffs, no pushback, sycophancy, subtle conceptual errors, overcomplication, dead code, orthogonal damage) and loops until they come back clean. Use this whenever the cost of a quiet mistake is high, when the user says "do this carefully / for real / no mistakes / high stakes", invokes /high-stakes, or asks for maximum effort / ultracode-grade rigor on a task they care about — even if they don't name the failure modes.
Security AStatic scan found no risk patternsHow grading works ›
From the source SKILL.md
The task to execute is in $ARGUMENTS. Treat that text as the work to deliver, not as a description to discuss.
What this skill does
High Stakes is a community-contributed Claude Code skill in the science-misc sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/high-stakes/ and loads when your prompt matches the skill's trigger.
Who uses this skill
The High Stakes Claude Code skill is built for researchers, data scientists, academics, and analysts working with complex data and scientific literature. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 161,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
How to install
Free
Manual install (2 steps)
mkdir -p ~/.claude/skills/high-stakes
curl -L https://claudskills.com/skills/high-stakes/SKILL.md \
-o ~/.claude/skills/high-stakes/SKILL.md
Or just download SKILL.md directly and drop it into ~/.claude/skills/high-stakes/. Claude Code auto-discovers it on next session.
Skills live at ~/.claude/skills/high-stakes/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\high-stakes\SKILL.md on Windows. See the full install guide for step-by-step instructions.
Telegram
📱 Install from your phone or desktop Telegram
Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →
Pro
One-click install via the desktop app
The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.
Pro
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
Frequently asked questions
How do I install the High Stakes Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy
SKILL.md from the source repository to
~/.claude/skills/high-stakes/SKILL.md and restart Claude Code. Both flows are detailed at
claudskills.com/install/.
What does the High Stakes skill do?
Produce a reliable, high-stakes-grade result for ANY task — code, writing, research, ops — by treating the work as guilty until independent skeptics fail to break it. Runs the task through a dynamic many-subagent adversarial-verification Workflow that hunts for ten specific failure modes (silent assumptions, unmanaged confusion, hidden inconsistencies, unsurfaced tradeoffs, no pushback, sycophancy, subtle conceptual errors, overcomplication, dead code, orthogonal damage) and loops until they come back clean. Use this whenever the cost of a quiet mistake is high, when the user says "do this carefully / for real / no mistakes / high stakes", invokes /high-stakes, or asks for maximum effort / ultracode-grade rigor on a task they care about — even if they don't name the failure modes.
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the High Stakes skill?
Use High Stakes when your Claude Code task falls under the Science & Research category — specifically in the science misc area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use High Stakes" or describe the task and let Claude pick). Browse related skills at
/category/science/.
What is a Claude Code skill and how does the High Stakes skill fit in?
A Claude Code skill is a
SKILL.md file that lives under
~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. High Stakes is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Science & Research category. Learn more at
/learn/what-is-a-claude-skill/.
Attribution & license
Cite this skill
If you reference this skill in a blog post, paper, or documentation, you can cite it as:
APA
titusz. (2026). High Stakes [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/high-stakes/
BibTeX
@misc{high-stakes-2026,
author = {titusz},
title = {High Stakes [Claude Code skill]},
year = {2026},
publisher = {ClaudSkills},
url = {https://claudskills.com/skills/high-stakes/}
}Embed this skill
Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →
Badge
[](https://claudskills.com/skills/high-stakes/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/high-stakes.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/high-stakes.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: High Stakes"></iframe>
Security scan
Grade A · scanned 2026-07-26 — free static scan against the OWASP Agentic Skills Top 10.
No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›
- ✓ Prompt injection
- ✓ Data exfiltration
- ✓ Supply chain
- ✓ Reverse shell
- ✓ Credentials
- ✓ Execution
- ✓ Filesystem
- ✓ Persistence
- ✓ Obfuscation
- ✓ Network
Show this grade on your repo (click to copy):
[](https://claudskills.com/skills/high-stakes/#security)
More Science & Research skills
Browse all Science & Research skills in the ClaudSkills registry, or explore these other picks from the same category:
Part of Acreator Store — Adam Lankamer's AI tools:
PerfectStudio ·
Ucaption ·
UTagger ·
AutoXPoster ·
TestYourSkills ·
AutomationFlows ·
Au Naturel ·
Telegram @acreatorstore