菜单
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | strategic-compact |
| description | Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction. |
Suggests manual /compact at logical task boundaries rather than letting auto-compaction interrupt mid-task.
The suggest-compact.sh hook tracks tool calls and suggests compaction at a configurable threshold (default: 50), then reminds every 25 calls after that. The hook tells you when; you decide if.
Add to ~/.claude/settings.json:
{
"hooks": {
"PreToolUse": [{
"matcher": "tool == \"Edit\" || tool == \"Write\"",
"hooks": [{ "type": "command", "command": "~/.claude/skills/strategic-compact/suggest-compact.sh" }]
}]
}
}
Set COMPACT_THRESHOLD to override the default of 50.
Use when designing memory or persistent context for an agent — deciding what to persist vs. recompute, how to retrieve only what's relevant, and how to summarize/compact history to fit the context window. Use when an agent forgets, bloats its context, or repeats work.
Interactive installer for Rosetta. Guides users through selecting and installing skills and language-specific rules at user-level or project-level, verifies paths, and optionally optimizes installed files.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills, commands, and agents.
Use when building or reviewing an evaluation for an LLM feature — assembling a representative test set, choosing pass criteria (exact match, programmatic checks, rubric, or LLM-as-judge), and catching regressions. Use when asking "how do I know this prompt or model change is better?"
Use when writing or reviewing a prompt for an LLM — making it specific, structured, and testable (clear task, role/context, examples, an explicit output contract, decomposition, room to reason) and avoiding the anti-patterns that make prompts brittle. Provider-agnostic.
Pattern for progressively refining context retrieval to solve the subagent context problem.