Common context optimization

Skill ComeOnOliver/skillshub/skills/HoangNguyen0403/agent-skills-standard/common-context-optimization

🧠 The right skill, one API call. AI agent skills registry with token-efficient skill resolution. 5,000+ skills from 500+ top repos.

Install

npx -y skills add ComeOnOliver/skillshub --skill common-context-optimization

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Techniques to maximize context window efficiency, reduce latency, and prevent 'lost in middle' issues through strategic masking and compaction. (triggers: *.log, chat-history.json, reduce tokens, optimize context, summarize history, clear output)

SKILL.md

2.0 KB, as published. Nobody here has run it

Priority: P1 (OPTIMIZATION)

Manage the Attention Budget. Treat context as a scarce resource.

1. Observation Masking (Noise Reduction)

Problem: Large tool outputs (logs, JSON lists) flood context and degrade reasoning. Solution: Replace raw output with semantic summaries after consumption.

Identify: outputs > 50 lines or > 1kb.
Extract: Read critical data points immediately.
Mask: Rewrite history to replace raw data with [Reference: <summary_of_findings>].
See: references/masking.md for patterns.

2. Context Compaction (State Preservation)

Problem: Long conversations drift from original intent. Solution: Recursive summarization that preserves State over Dialogue.

Trigger: Every 10 turns or 8k tokens.
Compact:
- Keep: User Goal, Active Task, Current Errors, Key Decisions.
- Drop: Chat chit-chat, intermediate tool calls, corrected assumptions.
Format: Update System Prompt or Memory File with compacted state.
See: references/compaction.md for algorithms.

3. KV-Cache Awareness (Latency)

Goal: Maximize pre-fill cache hits.

Static Prefix: strict ordering: System -> Tools -> RAG -> User.
Append-Only: Avoid inserting into the middle of history if possible.

References

Anti-Patterns

No raw tool dumps: Mask large outputs immediately after extracting data.
No append-only growth: Compact every 10 turns to preserve intent over dialogue.
No middle insertions: Append-only history maximizes KV cache hits.