Product Strategist
v2.1.1Strategic product leadership toolkit for Head of Product covering OKR cascade generation, quarterly planning, competitive landscape analysis, product vision...
⭐ 3· 2k·17 current·18 all-time
byAlireza Rezvani@alirezarezvani
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The name/description map to a local OKR cascade generator (scripts/okr_cascade_generator.py) and supporting reference documents. No unrelated env vars, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent/user to run the included Python script with strategy/teams/metrics options and export JSON or dashboard output. The instructions do not ask the agent to read unrelated system files, access secrets, or post data to external endpoints.
Install Mechanism
No install spec is present (instruction-only). The only code is an included Python script; nothing is downloaded or installed by the skill metadata.
Credentials
No environment variables, credentials, or config paths are required. The script accepts runtime flags and JSON metrics only, which is proportionate to an OKR generator.
Persistence & Privilege
always is false and disable-model-invocation is the platform default (false). The skill does not request permanent system presence or modify other skills; standard autonomous invocation is possible but not elevated by this skill.
Assessment
This skill appears coherent for generating OKRs and related outputs. Before running it, review the full scripts/okr_cascade_generator.py file (the provided snippet is long and the file continues) to confirm there are no unexpected network calls, subprocess.exec usage, or writes to sensitive paths. Run it in a sandbox or non-sensitive environment first, pass only non-confidential sample metrics, and export to JSON rather than piping output blindly. If you plan to allow autonomous agent invocation, be aware the agent could run the script without interactive approval — disable model invocation if you want manual control. If anything in the rest of the script references external endpoints or executes arbitrary commands, reconsider installing or require code changes.Like a lobster shell, security has layers — review code before you run it.
latestvk97ct6ve0v5arv4fqhpjhp4w5h82j7wm
License
MIT-0
Free to use, modify, and redistribute. No attribution required.