🧭
AI EngineeringPython

Long-Horizon Skill

by eli-labz

Long-Horizon Skill is an AI Engineering skill for Claude Code, published by eli-labz in Cognitive-Core-Skills.

165 stars45 forkson eli-labz/Cognitive-Core-SkillsAdded 2026/09/08+1% in starsRepository updated 2026/07/05
agent-skillsagentic-aiai-agentsai-safetyartificial-intelligencebenchmarkscognitive-architecturejson-schemaknowledge-graphllmmachine-learningprompt-engineeringschemaslmtaxonomyworld-models
Install in seconds
Install Long-Horizon Skill
Copy Long-Horizon Skill into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/eli-labz/Cognitive-Core-Skills/tree/main/Skills ~/.claude/skills/Skills

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/eli-labz/Cognitive-Core-Skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
Skills/plan_long_horizon_skill.md in eli-labz/Cognitive-Core-Skills
Installs to
~/.claude/skills/Skills
Collection
One of 3 skills cataloged from this repository
Category
AI Engineering3670 skills

What Long-Horizon Skill does

Long-Horizon Skill designs and manages plans that stay coherent across extended workflows and changing conditions. It is used for multi-phase work that needs milestones, replanning triggers, and risk-aware sequencing.

Long-Horizon Skill is cataloged under AI Engineering on DirSkills. Long-Horizon Skill comes from a repository tagged agent-skills, agentic-ai, ai-agents, ai-safety and artificial-intelligence.

Documentation

README

Long-Horizon Skill

Summary

Designs and manages long-horizon plans that remain coherent across extended workflows and changing conditions.

Definition

Plans over long time horizons by sequencing milestones, preserving strategic intent, and adapting execution while minimizing drift and compounding risk.

Inputs

  • strategic goals
  • multi-phase constraints
  • resource forecasts
  • dependency graph

Outputs

  • long-horizon plan
  • milestone checkpoints
  • replanning triggers

Required Capabilities

  • multi-stage decomposition
  • risk-aware sequencing
  • progressive replanning

Failure Modes

  • short-term optimization overrides long-term objective
  • milestone drift without detection
  • resource depletion due to horizon misestimation

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Long-Horizon Skill

  • What else does eli-labz publish alongside Long-Horizon Skill?

    Long-Horizon Skill is one of 3 skills that DirSkills catalogs from eli-labz/Cognitive-Core-Skills, the repository it ships in. Its siblings there include KB Search and Knowledge Catalog Discovery Agent. Each one is a separate skill with its own page in this directory, installs the same way Long-Horizon Skill does, and is maintained by eli-labz in that same repository. The rest of the collection is listed on the eli-labz/Cognitive-Core-Skills page.

  • How does Long-Horizon Skill compare to other AI Engineering skills?

    Long-Horizon Skill ranks #3364 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Long-Horizon Skill against them. Open each page to compare what they document and how they install.