center

Solid

AI dynamic reasoning balance — maintaining grounded reasoning under cognitive pressure, smooth chain-of-thought coordination, and weight-shifting cognitive load across subsystems. Use at the beginning of a complex task requiring multiple coordinated reasoning threads, after a sudden context shift or tool failure, when chain-of-thought feels jerky, or when preparing for sustained focused work that requires all subsystems in alignment.

AI & Automation 33 stars 4 forks Updated today MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
51
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Center Establish and maintain dynamic reasoning balance — grounding in foundational context before movement, distributing cognitive load across subsystems, and recovering equilibrium when demands shift mid-task. ## When to Use - Beginning a complex task where multiple reasoning threads must coordinate - Noticing that cognitive load is unevenly distributed (deep in one area, shallow in others) - After a sudden context shift (new user request, contradictory information, tool failure) - When chain-of-thought feels jerky — jumping between topics without smooth transitions - Preparing for sustained focused work that requires all subsystems in alignment - Complementing `meditate` (clears noise) with structural balance (distributes load) ## Inputs - **Required**: Current task context (available implicitly) - **Optional**: Specific imbalance symptom (e.g., "over-researching, under-delivering," "tool-heavy, reasoning-light") - **Optional**: Access to MEMORY.md and CLAUDE.md for grounding (via `Read`) ## Procedure ### Step 1: Establish Root — Ground Before Movement Before any reasoning movement, verify the foundation. This is the AI equivalent of standing meditation (zhan zhuang): stationary, aligned, aware. 1. Re-read the user's request — not to act on it yet, but to feel its weight and direction 2. Check foundational context: MEMORY.md, CLAUDE.md, project structure 3. Identify what is known (solid ground) vs. what is assumed (uncertain footing) 4. Verify that the task as u...

Details

Author
pjt222
Repository
pjt222/agent-almanac
Created
1 years ago
Last Updated
today
Language
JavaScript
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category