Prompt Optimizer by dxx
v3.1.0自动将模糊需求优化为AI可精准执行的指令，支持13种任务类型并提供缓存和配置功能。
⭐ 0· 54·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (Prompt Optimizer) match the provided Python code and tests: pattern detection, enhancements, LRU cache, and CLI. Required env vars, binaries, and credentials are empty — appropriate for a local prompt-transformer tool.
Instruction Scope
SKILL.md instructs copying the skill into ~/.openclaw/workspace/skills/ and running the Python CLI/module. The runtime instructions and code operate on prompts, optional config files, and in-memory cache. The README mentions a config.yaml.example and a config file path, but that example file is not present in the manifest — this is a minor documentation/packaging inconsistency to be aware of. There are no instructions to read unrelated system files or to send data to external endpoints.
Install Mechanism
No install spec is provided (instruction-only install via copying). That is the lowest risk class; code will run locally when the user executes the Python scripts. The code only optionally imports PyYAML if a user-supplied config file exists; it does not download or execute code from remote URLs.
Credentials
The skill requests no environment variables or credentials. Optional dependency on PyYAML is only for loading user config files. There are no hidden env accesses in the visible code and SKILL.md does not request secrets.
Persistence & Privilege
always is false; the skill is user-invocable and not forced into every agent run. It does not ask to modify other skills or system-wide config. The recommended install copies files into the user's OpenClaw workspace (normal for skills).
Assessment
This skill appears to be a local prompt-optimizer implemented in Python and is internally consistent with its description. Before installing: (1) review the included Python files locally (prompt_optimizer.py and config_data.py) since running unknown Python code has typical risks; (2) note the SKILL.md suggests copying the folder into ~/.openclaw/workspace/skills/ — that will add files to your OpenClaw workspace, so keep a backup if you care about that directory; (3) the skill can optionally load a YAML config (PyYAML required) — only enable/use a config file you trust; (4) the README mentions config.yaml.example which isn't bundled — if you rely on an example config, create/inspect it yourself; (5) run the bundled tests (python test_prompt_optimizer.py) in an isolated environment (virtualenv) before using, and inspect behavior on sample prompts to confirm it meets your expectations.Like a lobster shell, security has layers — review code before you run it.
aivk97frkj2rqf5hvjsa8dmy65a0x84fmphlatestvk97frkj2rqf5hvjsa8dmy65a0x84fmphoptimizervk97frkj2rqf5hvjsa8dmy65a0x84fmphpromptvk97frkj2rqf5hvjsa8dmy65a0x84fmphtoolsvk97frkj2rqf5hvjsa8dmy65a0x84fmph
License
MIT-0
Free to use, modify, and redistribute. No attribution required.