Clmm Rebalance — Development skill for Claude Code
Simulate-first CLMM rebalance with mandatory typed human confirmation; never auto-fires.
How to install Clmm Rebalance
Installs to ~/.claude/skills/solanabr-position-manager-skill-clmm-rebalance/SKILL.md
mkdir -p ~/.claude/skills/solanabr-position-manager-skill-clmm-rebalance && curl -fsSL https://raw.githubusercontent.com/solanabr/position-manager-skill/HEAD/commands/clmm-rebalance.md -o ~/.claude/skills/solanabr-position-manager-skill-clmm-rebalance/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Clmm Rebalance does
Simulate-first CLMM rebalance with mandatory typed human confirmation; never auto-fires.
Alternatives in Development
- Brain Filing Rules — Brain Filing Rules -- MANDATORY for all skills that write to the brain 29.1k ★
- Maestro Learn — User-invoked learning toolkit — guided reading, investigation, pattern extraction, or second opinions 530 ★
- Simulate 401 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Dream
Overnight autoresearch + maintainer sweep that surfaces a MORNING REPORT — suggested changes, issues raised wi
Agent Speak Readability
An agent skill that makes an agent's natural-language output readable to a human: cross-language rules plus a
Screen Job
Screen a job advert against your CV: simulate the real first-stage filters and return an honest tailoring punc
Skill Promote
Promote a reviewed draft skill from ~/.claude/skills-pending/ / to the active ~/.claude/skills/ / after explic
Ship CI Review Loop
Use when monitoring CI and handling review comments during /ship. Details mandatory wait periods, auto-reviewe
Transcripto
Index your coding-agent transcripts, keep only the turns you actually typed, and grade them. Local, stdlib-onl
Related Agents
Auto Task Decomposer
Auto-Task Decomposer for the team-agents workflow — the first agent in the Mandatory Development Flow responsi
Applier 2
Generates copy-paste answers for job application forms based on pipeline research. Human-in-the-loop — never a
Premium Reasoner
Top-tier scoped reasoning on your highest-capability model. Use ONLY when the human explicitly authorized prem