Portfolio Matrix
v1.0.0Evaluate strategic options by NPV vs ease of implementation. Use for project prioritization, resource allocation, and strategic decision making.
⭐ 0· 80·0 current·0 all-time
by@linuszz
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, and runtime instructions all align: the SKILL.md describes how to evaluate projects by NPV vs ease and produce a matrix and recommendations. There are no unrelated requirements (no binaries, env vars, or config paths).
Instruction Scope
Instructions are limited to defining criteria, scoring options, creating matrices, and producing recommendations. The document does not instruct reading files, accessing environment variables, calling external endpoints, or performing system actions outside the skill's analytical purpose.
Install Mechanism
No install spec and no code files — the skill is purely a set of prose instructions. This minimizes disk/network footprint and avoids arbitrary downloads.
Credentials
The skill requires no credentials, no environment variables, and no config paths. The level of access requested is proportional to an analytical/instructional skill.
Persistence & Privilege
always is false and there is no behavior that requests permanent presence or to modify system/other-skill settings. Autonomous invocation by the agent is the platform default and not a red flag here.
Assessment
This is an instruction-only, offline framework for prioritizing projects — it does not request credentials or install anything. Before installing, consider: (1) the skill's source and lack of homepage/author info means you can't audit provenance—use caution if you require formal provenance; (2) validate any NPV inputs and scoring methodology on representative sample data before using results for large financial decisions; (3) confirm that any sensitive project data you feed to the agent is handled according to your privacy requirements (the skill itself doesn't transmit data, but your agent may log or send prompts elsewhere); and (4) if you want reproducible outputs, capture the scoring rules and weighting you apply so results can be reviewed later.Like a lobster shell, security has layers — review code before you run it.
latestvk9720g4sw4zwz8b136jk5jxasn83d2kc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.