← Back to Skills Marketplace
deepseek609609-collab

DAF Intent Guard — 意图漂移检测

by deepseek609609-collab · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
147
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install daf-intent-guard
Description
Tracks intent drift across multi-turn tasks. Before executing any multi-step task, call this to detect if the user's new instruction is a small patch, requir...
README (SKILL.md)

DAF Intent Guard

Use this skill when:

  • A user modifies an in-progress task
  • A user gives a new instruction that might conflict with what is already done
  • You need to decide whether to continue, roll back, or restart

How to use

Call the guard before executing any new instruction on an ongoing task:

python3 {baseDir}/daf_guard.py \
  --current-anchor \x3Cindex> \
  --old-constraints '\x3Cjson>' \
  --new-constraints '\x3Cjson>' \
  --new-action '\x3Caction>' \
  --requires '\x3Cjson_array>' \
  --anchors '\x3Cjson>'

Decision meanings

  • patch: Small change. Update parameters and continue from current anchor.
  • replan: Significant change. Roll back to anchor first_affected_anchor and re-execute from there.
  • abort: Task cancelled or too much has changed. Stop and confirm with user before restarting.

Example

User was booking a flight (seat locked at anchor 1), now says "change destination to New York":

  • old-constraints: {"destination":"KL","date":"today","cabin":"economy"}
  • new-constraints: {"destination":"New York","date":"today","cabin":"economy"}
  • Expected: replan (destination change affects anchor 0)
Usage Guidance
This skill appears internally coherent and low-risk: it runs a local Python script to compute intent-drift decisions and does not contact external endpoints or ask for credentials. Before installing, verify the file origin (source is listed as unknown) and review the daf_guard.py contents yourself (they are small and readable). When integrating, pass only non-sensitive JSON (the script logs/prints decisions) and test on safe example tasks to confirm behavior meets your agent's expectations.
Capability Analysis
Type: OpenClaw Skill Name: daf-intent-guard Version: 1.0.0 The daf-intent-guard skill is a utility designed to help AI agents manage state transitions by calculating the 'semantic distance' between old and new task constraints. The core logic in `daf_guard.py` uses basic heuristics (regex, hardcoded region lists, and date parsing) to determine if a user's change requires a minor update (patch), a partial rollback (replan), or a full stop (abort). The code is self-contained, lacks external dependencies, and performs no risky operations such as network calls, file system access, or command execution.
Capability Assessment
Purpose & Capability
Name/description (intent-drift detection) match the included Python implementation: the script computes semantic distance, anchor rollback, and emits patch/replan/abort decisions. Required binary (python3) is appropriate and proportionate.
Instruction Scope
SKILL.md instructs only running the local Python script with JSON arguments. The script reads only its CLI args and performs local computation; it does not read unrelated files, environment variables, or send data externally.
Install Mechanism
No installation/spec downloads are present; the skill is delivered as a small local Python file and README. There are no external install URLs or archive extraction steps.
Credentials
No environment variables, credentials, or config paths are requested. The script takes inputs via CLI JSON parameters only, which is proportional to the task.
Persistence & Privilege
always is false and the skill does not request to modify other skills or agent-wide settings. It does not attempt to persist secrets or alter system configuration.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install daf-intent-guard
  3. After installation, invoke the skill by name or use /daf-intent-guard
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
首次发布。支持多步任务中的意图漂移检测,自动判断patch/replan/abort
Metadata
Slug daf-intent-guard
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is DAF Intent Guard — 意图漂移检测?

Tracks intent drift across multi-turn tasks. Before executing any multi-step task, call this to detect if the user's new instruction is a small patch, requir... It is an AI Agent Skill for Claude Code / OpenClaw, with 147 downloads so far.

How do I install DAF Intent Guard — 意图漂移检测?

Run "/install daf-intent-guard" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is DAF Intent Guard — 意图漂移检测 free?

Yes, DAF Intent Guard — 意图漂移检测 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does DAF Intent Guard — 意图漂移检测 support?

DAF Intent Guard — 意图漂移检测 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created DAF Intent Guard — 意图漂移检测?

It is built and maintained by deepseek609609-collab (@deepseek609609-collab); the current version is v1.0.0.

💬 Comments