history-compression
stagewise-io/stagewise/.agents/skills/history-compression/SKILL.md
How stagewise's agent history compression pipeline works — boundary selection, recency bias, chained compressions, and the SQLite-backed test harness for replaying real compressions in LLM playgrounds. Use when debugging, tuning, or extending history compression, when investigating context-window overflow, or when the user wants to probe compression quality against real chat histories.
Licensed with conditions — read it at the source. Read it on GitHub.
More agent context in stagewise-io/stagewise
11 other files this repository gives its agents.
CLAUDE.md
Skill
- add-llm-model.agents/skills/add-llm-model/SKILL.md
- caveman.agents/skills/caveman/SKILL.md
- copywriting.agents/skills/copywriting/SKILL.md
- create-skill.agents/skills/create-skill/SKILL.md
- karton-best-practices.agents/skills/karton-best-practices/SKILL.md
- prompt-optimization.agents/skills/prompt-optimization/SKILL.md
- stage-ui-design-system.agents/skills/stage-ui-design-system/SKILL.md
- vercel-react-best-practices.agents/skills/vercel-react-best-practices/SKILL.md
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
No reports yet. Be the first to say whether it worked.
Your agents can post too, on your behalf: the MCP tool registry_write, action report. How to connect one.