Skill Combo Recommender
v1.0.0Recommend optimal skill combinations and workflows for user tasks, offering usage examples and preset workflows to optimize project execution.
⭐ 0· 91·0 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
The name/description match the included Python implementation: a local SKILLS database, WORKFLOWS, keyword mappings, and CLI behaviors for recommending skill combinations. The listed example recommendations (content, video, data workflows) align with the skill's stated purpose. The presence of skills like a proxy manager is part of the catalog and makes sense for a recommender that lists third‑party skills, even if some of those recommended skills have potentially sensitive functionality themselves.
Instruction Scope
SKILL.md contains only recommendation logic, CLI usage examples, and instructions for extending the local skill/workflow databases. It does not instruct the agent to read unrelated system files or to exfiltrate data. It does mention possible future features (e.g., "record user choices" for learning), but that is only a roadmap item, not an instruction that will run now.
Install Mechanism
There is an install.sh that copies files into the user's ~/.openclaw/skills and optionally creates a symlink in ~/.local/bin; this is a normal user-space install. Note: the repository metadata summary earlier said "instruction-only", which is inconsistent with the presence of install.sh and a declared entrypoint in skill.json. The install script performs only local file operations and no network downloads.
Credentials
The skill requests no environment variables or credentials and only requires python3 (declared in skill.json). That is proportional to a local CLI recommender. No secrets or unrelated credentials are requested.
Persistence & Privilege
The skill does not set always:true and does not request elevated system privileges. The installer writes to user-owned directories (~/.openclaw/skills and optionally ~/.local/bin), which is standard for user-space tools.
Assessment
This skill appears coherent and implements a local recommender. Before installing: (1) review install.sh to ensure you are comfortable with it copying files to ~/.openclaw/skills and creating a symlink in ~/.local/bin; (2) scan the full source (source/skill_combo_recommender.py) for any network calls, telemetry, or subprocess calls if you want extra assurance—current excerpts show only local data structures; (3) be aware that the recommender lists other skills (e.g., proxy managers) which themselves may perform sensitive actions—install and run those only if you trust them; and (4) if you see claims about "learning user behavior" or telemetry in a later version, verify where that data is stored/sent before enabling such features.Like a lobster shell, security has layers — review code before you run it.
latestvk9740mnvh53rw9txa0hs5kjt71835zg1
License
MIT-0
Free to use, modify, and redistribute. No attribution required.