Context Compression
上下文压缩省 Token。对话变长或开新任务时输出/使用 6 块压缩结构，总长 400~800 tokens。必加载。
Install
$ agentstack add skill-aiweline-welineframework-context-compression ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-aiweline-welineframework-context-compression) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
context-compression（极简版·必加载）
何时使用
- 对话 15~20 轮后、开新子任务、跨天继续
- 用户说「太长」「省 token」「压缩上下文」「继续上次」
必做
- 主动建议：当上下文明显变长时，提示用户可做一次压缩再继续
- 压缩输出严格按 6 块、总长 400~800 tokens
输出结构（6 块）
1) 当前目标（1~2 句） 2) 关键约束（≤8 条，可选摘录 dev/ai/global-constraints.md） 3) 已完成（≤8 条） 4) 待办（≤8 条） 5) 相关文件 路径+一句（≤12 个） 6) 风险/未知（≤5 条）
一键压缩指令（让用户贴上下文后发给模型）
把下面【输入】压缩成「最小可执行上下文」，按 6 块输出，总长 400~800 tokens：
1) 当前目标（1~2 句） 2) 关键约束（≤8 条） 3) 已完成（≤8 条）
4) 待办（≤8 条） 5) 相关文件 路径+一句（≤12 个） 6) 风险/未知（≤5 条）
删重复和噪音，保留影响正确性的约束与路径。规则/技能只写名+一句。
【输入】
（在这里粘贴要压缩的对话或摘要）固定约束（可附在压缩结果里）
- 完整禁止/必做清单：
dev/ai/global-constraints.md - 模块目录：
app/code/{Vendor}/{ModuleName}
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Aiweline
- Source: Aiweline/WelineFramework
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.