ClawHub

ai-product-manager-playbook

v1.0.0

A comprehensive operating system for AI Product Management. Use this skill when planning, prototyping, evaluating, or launching AI-native products. It provid...

⭐ 0· 35·0 current·0 all-time
byDaniel Foo Jun Wei@danielfoojunwei
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
CryptoCan make purchases
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (AI PM playbook) match the included content: templates, references, and a feedback-loop script. There are no unexpected binaries, credentials, or external services requested.
✓
Instruction Scope
SKILL.md instructs the agent to use local templates, references, and to run scripts/pm_feedback_loop.py on a provided telemetry JSON; the script only reads a local file, analyzes it, and prints suggestions. There are no instructions to read unrelated system files, access environment secrets, or transmit data externally.
✓
Install Mechanism
No install spec and no code that downloads or executes remote artifacts. This is instruction-only with bundled markdown files and a local Python script.
✓
Credentials
No required environment variables, credentials, or config paths are declared or referenced. The script only accepts a local telemetry JSON path as input.
✓
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills or system configurations. The script does not write files or enable itself automatically.
Assessment
This skill appears coherent and low-risk: it provides local docs/templates and a simple Python script that reads a telemetry JSON and prints improvement suggestions. Before running: (1) review the telemetry JSON you pass in to ensure it contains no sensitive data or secrets, (2) confirm you trust the skill source (the package lists no homepage and the owner is unknown), and (3) note the feedback script only prints suggestions — it does not automatically edit templates or send data externally. If you need automatic updates or networked telemetry collection, require additional review because that would increase risk.

Like a lobster shell, security has layers — review code before you run it.

latestvk97eth06j1e1fsapd0z7dnp8jh84tj34

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments