SkillHone — tool profile and history

Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.

Active

Canonical source ↗

Language
Python
Created
Last activity
Topics
  • agent-skills
  • llm-agents
  • self-improving-agents
  • skill-optimization

Install git clone https://github.com/Tencent/SkillHone ~/.claude/skills/SkillHone

Current measurement

138GitHub stars+2 (+1.5 %)
measured growth

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

90 days · 90 maximum readings
DateValueMetric
138GitHub stars
136GitHub stars
135GitHub stars
135GitHub stars
135GitHub stars
137GitHub stars
136GitHub stars
134GitHub stars
131GitHub stars
131GitHub stars
129GitHub stars
128GitHub stars
127GitHub stars
127GitHub stars
127GitHub stars
126GitHub stars
123GitHub stars
123GitHub stars
123GitHub stars
123GitHub stars
122GitHub stars
119GitHub stars

Classifications

Domains
Type
Agent skills
Use cases

These entries declare the same topics. No similarity is inferred: only the shared topics are stated.