← Back to Skills Marketplace
341
Downloads
1
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install model-resource-profiler
Description
Analyze model training or inference resource behavior from profiler artifacts, with focus on GPU memory (VRAM) and CPU hotspots. Uses JSON/JSON.GZ artifacts...
Usage Guidance
This skill appears coherent and local-only: it analyzes JSON/JSON.GZ profiler artifacts with the bundled script and does not ask for credentials or remote installs. Before installing, review the full scripts/analyze_profile.py file (the provided SKILL.md and snippet are consistent but the shipped code should be inspected end-to-end) and only run conversions (the torch example) inside your own trusted environment. Do not provide pickle or other binary serialized artifacts to the skill; follow its guidance to re-export as JSON in your environment to avoid executing untrusted code. If you need higher assurance, run the analyzer in an isolated environment (air-gapped or with limited network) and inspect the generated markdown/JSON outputs for any unexpected content.
Capability Analysis
Type: OpenClaw Skill
Name: model-resource-profiler
Version: 0.1.1
The skill bundle is benign. Both the `SKILL.md` and `scripts/analyze_profile.py` demonstrate a strong focus on security. The `SKILL.md` explicitly defines safety boundaries, instructing the AI agent to never deserialize pickle files, execute remote code, or access files beyond user-provided local paths. The Python script reinforces this by using safe `json.load` for parsing and explicitly raising a `SystemExit` if a `--memory-pickle` argument is provided, preventing unsafe deserialization. There is no evidence of data exfiltration, malicious execution, persistence, or prompt injection designed to bypass safety measures.
Capability Assessment
Purpose & Capability
Name/description (model resource profiling focused on GPU memory and CPU hotspots) match the included analyzer script and SKILL.md. No extra binaries, credentials, or unrelated config paths are requested.
Instruction Scope
SKILL.md restricts analysis to user-provided local JSON/JSON.GZ artifacts, explicitly forbids pickle/executable deserialization, remote code fetching, or executing commands embedded in artifacts, and instructs use of the local scripts/analyze_profile.py implementation. Example conversion code is provided but is explicitly intended for the user's trusted environment.
Install Mechanism
No install spec; this is instruction-only with a bundled analyzer script. The script uses only standard Python libs (gzip, json, pathlib, collections, math) and does not pull remote artifacts or install packages.
Credentials
The skill requests no environment variables, credentials, or config paths. The SKILL.md guidance to re-export pickles in a trusted environment is appropriate and keeps credential exposure minimal.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent presence or elevated system privileges and does not indicate modifying other skills or agent-wide settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install model-resource-profiler - After installation, invoke the skill by name or use
/model-resource-profiler - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.1
**Safer format: Now supports only JSON-based artifacts, disabling pickle support for improved security.**
- Only accepts profiler and memory snapshot artifacts in JSON/JSON.GZ; pickle input is no longer supported.
- Updated documentation and commands to reflect JSON-only usage.
- Added explicit workflow and safety instructions, including handling for users with legacy pickle files.
- Analysis logic remains unchanged; only data ingestion methods are different.
v0.1.0
Initial release of model-resource-profiler skill:
- Analyze PyTorch training/inference resources from memory snapshot pickles and profiler trace files.
- Automatically diagnoses GPU memory usage, fragmentation, and CPU bottlenecks.
- Provides actionable optimization suggestions, ranked by impact and confidence.
- Accepts both CPU and memory profiling data; produces markdown and JSON reports.
- Workflow includes artifact confirmation, analysis, rubric-based interpretation, and prioritized recommendations.
Metadata
Frequently Asked Questions
What is Model Resource Profiler?
Analyze model training or inference resource behavior from profiler artifacts, with focus on GPU memory (VRAM) and CPU hotspots. Uses JSON/JSON.GZ artifacts... It is an AI Agent Skill for Claude Code / OpenClaw, with 341 downloads so far.
How do I install Model Resource Profiler?
Run "/install model-resource-profiler" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Model Resource Profiler free?
Yes, Model Resource Profiler is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Model Resource Profiler support?
Model Resource Profiler is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Model Resource Profiler?
It is built and maintained by daiwk (@daiwk); the current version is v0.1.1.
More Skills