Future Tokens

Every AI output has structural blind spots determined by the generation process itself. Future Tokens operations are named, composable instruments that target specific blind spots. They surface new information on every pass because expanding the output changes the blind spot geometry.

66 stars 4 forksAI, LLMs & Agents

Install

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

npx skills add jordanrubin/FUTURE_TOKENS --skill future-tokens

Manual install

git clone --depth 1 https://github.com/jordanrubin/FUTURE_TOKENS.git /tmp/FUTURE_TOKENS
mkdir -p ~/.claude/skills
cp -r /tmp/FUTURE_TOKENS/. ~/.claude/skills/future-tokens

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

From the SKILL.md

# Future Tokens: Corrective Instruments for AI Reasoning

Every AI output has structural blind spots. Coherence optimization suppresses gaps. Token-level generation locks in frames before alternatives are considered. Confidence distributes smoothly over claims that deserve scrutiny in different places. These aren't random errors — they're predictable artifacts of how generation works.

Future Tokens operations are named, composable instruments that target specific blind spot types. Each one reliably surfaces information that the generation process systematically omits, because the blind spots are structural, not random. And they're generative — every pass changes the consideration space, shifting the blind spot geometry so the next pass finds new material.

Part of the [FUTURE TOKENS](https://jordanmrubin.substack.com/p/future-tokens) project.

This collection is compatible with both Claude and Codex workflows.

## When to use

If you just produced an output, it has predictable gaps. Match what you built to the operation that catches what it missed.

| you just built…                    | it probably missed…                                                    | run this                |
|------------------------------------|------------------------------------------------------------------------|-------------------------|
| a questionnaire or survey          | questions you couldn't think to ask because coherence suppresses gaps   | @negspace               |

Read the full skill on GitHub

Details

Skill name: future-tokens
Repository: jordanrubin/FUTURE_TOKENS
Repo updated: 19 February 2026

FAQ

What does the Future Tokens skill do?

How do I install the Future Tokens skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add jordanrubin/FUTURE_TOKENS --skill future-tokens. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Future Tokens popular?

It lives in jordanrubin/FUTURE_TOKENS, which has 66 GitHub stars and 4 forks.

Related skills

Humanize Mba Text

stephenlzc/humanize-mba-text-skill

去除中文文本中的 AI 生成痕迹，使其更符合中国 MBA 毕业论文的自然写作风格。当用户提到"去 AI 痕迹"、"去除 AI 写作痕迹"、"MBA 论文改写"、"让这段文字更像人写的"、"去除机器感"等关键词时触发。适用于需要降低文本 AI 特征、提升学术写作自然度的场景。

AI, LLMs & Agents

Clawteam Directors Orchestrator

momozi1996/DirectorAgents

ClawTeam导演智囊团——基于ClawTeam多智能体框架的世界著名导演协同创作系统。整合31位全球顶级导演的风格思想，通过多智能体协作机制（顺序链、辩论投票、主席团模式）辅助剧本创作、影像风格设计和叙事决策。触发词：「导演智囊团」「ClawTeam」「多导演协作」「剧本创作」「影像风格」适用场景：编剧、导演、创意策划、影视教育、AI影像创作

AI, LLMs & Agents

AI Script Generation

FeiFei-AIDev/ai-script-generation-skill

当用户需要创作小红书/抖音/视频号的短视频脚本时使用。生成30-40秒的AI教程短视频脚本，基于用户提供的主题（和可选的参考素材），结合爆款框架库和热点话题，一次性输出5个不同角度的脚本方案（干货效率型、痛点共鸣型、悬念反转型、对比冲击型、热点借势型）。适用场景：用户请求生成脚本、创作视频内容、需要多角度脚本方案、或想要小红书风格的短视频脚本 (project)

AI, LLMs & Agents10

AI Bounty Claim

aelf-hzz780/AI-bounty-skill

Use when claiming the AI bounty on the tDVV mainnet sidechain. This public claim skill now supports Portkey AA/CA only, requires CA sync and holder preflight before any write, and routes to AA/CA onboarding, AA/CA claim, or diagnostics-only stop handling.

AI, LLMs & Agents

Creating Claude Md

sruthik27/creating-claude-md

Use when the user wants to create a new CLAUDE.md from scratch for a repository, bootstrap project memory for a new repo, set up a repo for Claude Code for the first time, or completely rewrite an existing CLAUDE.md deemed unsalvageable. Produces a lean, high-signal file under 80 lines (120 hard cap) by scanning the repo for mechanical content (stack, commands, structure) and interviewing the user for judgment content (WHY, gotchas, out-of-scope, approval gates, testing philosophy, external docs like Confluence pages). NOT for auditing or incrementally improving an existing CLAUDE.md — that is

AI, LLMs & Agents

Ham

kromahlusenii-ops/ham

Set up Hierarchical Agent Memory (HAM) — scoped CLAUDE.md files per directory that reduce token spend. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings", "HAM stats", "HAM dashboard", "HAM sandwich", "HAM insights", "HAM carbon", or "ham sync".

AI, LLMs & Agents

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