← 返回 Skills 市场
Context Rescue
作者
Peter Zsak
· GitHub ↗
· v1.0.0
· MIT-0
167
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install context-rescue
功能描述
Create a thread-based recovery summary when an agent loses the thread. Read the relevant conversation and canonical files, summarize what was done, where it...
使用说明 (SKILL.md)
Context Rescue
Use this skill when an agent is no longer fully sure where the work stands.
This is not for execution. This is for reorientation.
Trigger condition
Use this skill when any of these are true:
- the task feels blurry or fragmented
- too many side-tracks were followed
- the thread is long and the real next step is unclear
- a handoff or resume is happening after a gap
- you need to identify the real next step before doing more work
Core recovery prompt
Read back the full thread content and summarize what we have done so far, where the task is documented, and what the next step is. Do not go further, only produce this detailed summary.
Recovery workflow
- Read the relevant thread or message history.
- Read the canonical files:
state/HOLD.mdstate/ACTIVE.mdstate/DECISIONS.mdstate/CLOSED.mdif present- the canonical
task_plan.md - the canonical
notes.md
- Produce a focused summary with exactly these parts:
- what we did so far
- where the task is documented
- what the actual next step is
- Write a compressed snapshot to
state/ORIENT.md. - Stop. Do not execute the next step unless separately instructed.
Output format
## Reorientation summary
### What we did so far
- ...
- ...
### Where it is documented
- `...`
- `...`
### Actual next step
- ...
### Not the next step
- ...
- ...
### Closure criteria
- ...
- ...
state/ORIENT.md format
## Reorientation snapshot
**Thread / Context:** [which thread or task this is]
**What we did so far:**
- ...
- ...
**Where it is documented:**
- `state/ACTIVE.md`
- `projects/\x3Cslug>/task_plan.md`
- `projects/\x3Cslug>/notes.md`
**Actual next step:**
- ...
**Do not do instead:**
- ...
- ...
**Closure criteria:**
- ...
- ...
**Last updated:** YYYY-MM-DD HH:MM
Rules
- Do not continue into implementation.
- Do not create a new project if one already exists.
- Do not confuse logs with task progress.
- Prefer file truth over vague recollection.
- If the thread and the files conflict, explicitly call that out.
Why this exists
Long threads can consume context and blur the real task. A short, canonical reorientation summary restores focus without pretending the work is done.
安全使用建议
This skill is internally consistent and low-risk: it only reads conversation history and specific project state files and writes a short snapshot to state/ORIENT.md. Before installing, confirm (1) the agent will only have access to the threads and project files you want it to read (sensitive messages will be included if accessible), (2) writing state/ORIENT.md won't overwrite important content (back up if necessary), and (3) you are comfortable with the agent producing summaries of any sensitive context it can access. Because it's instruction-only, test it in a sandboxed project or repository first to verify behavior.
功能分析
Type: OpenClaw Skill
Name: context-rescue
Version: 1.0.0
The 'context-rescue' skill is a documentation-based workflow designed to help an AI agent reorient itself during long or complex tasks. It provides instructions for the agent to read local project state files (e.g., state/ACTIVE.md, task_plan.md) and generate a summary in state/ORIENT.md. The bundle contains no executable code, network requests, or malicious prompt injection, and its instructions focus on limiting agent behavior to summarization rather than unauthorized execution.
能力评估
Purpose & Capability
The name/description match the actual behavior: read thread and canonical project files, summarize progress, and write a snapshot. It does not request unrelated credentials, binaries, or external services.
Instruction Scope
SKILL.md narrowly instructs the agent to read the conversation and specific project files (state/*.md, task_plan.md, notes.md), produce a focused summary, and write state/ORIENT.md. It explicitly forbids continuing into implementation, and does not instruct broad data collection or external transmission.
Install Mechanism
This is an instruction-only skill with no install spec or code files, so nothing is written to disk beyond the artifact the skill itself directs (state/ORIENT.md). Low installation risk.
Credentials
The skill requires no environment variables, credentials, or config paths beyond reading/writing project/state files named in the workflow. The requested access is proportional to summarization and reorientation tasks.
Persistence & Privilege
The skill is not always-enabled and does not request elevated or cross-skill configuration. It writes a single snapshot file within the project state, which is consistent with its purpose.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install context-rescue - 安装完成后，直接呼叫该 Skill 的名称或使用
/context-rescue触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of thread-based context recovery mini-skill.
元数据
常见问题
Context Rescue 是什么？
Create a thread-based recovery summary when an agent loses the thread. Read the relevant conversation and canonical files, summarize what was done, where it... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 167 次。
如何安装 Context Rescue？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install context-rescue」即可一键安装，无需额外配置。
Context Rescue 是免费的吗？
是的，Context Rescue 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Context Rescue 支持哪些平台？
Context Rescue 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Context Rescue？
由 Peter Zsak（@wroadd）开发并维护，当前版本 v1.0.0。
推荐 Skills