product-thinking-pack — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited product-thinking-pack (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Part of the agent-reliability approach — applying production agent verification discipline to product thinking. For the underlying mechanisms, start there.
7 product-thinking skills that make an AI agent reason like a sharp PM before it acts — instead of producing gut-feel output.
Each skill is a self-contained methodology (no external dependencies). When the agent hits a matching situation, the skill forces explicit, dimension-by-dimension structure.
| Skill | Forces |
|---|---|
rice-prioritization | RICE / ICE / WSJF / MoSCoW — rank ideas by Reach × Impact × Confidence ÷ Effort instead of "feels important" |
jtbd-framework | Jobs-to-be-Done + Persona + Empathy map — what users actually want vs what they say |
pre-mortem | Imagine it already failed in 6 months — write the autopsy + risk register before shipping |
root-cause | 5 Whys + Fishbone + Pareto — find the root cause, not the symptom |
story-splitting | INVEST + SPIDR — split an epic too big for one PR into vertical slices + acceptance criteria + edge cases |
journey-mapping | Customer Journey + Service Blueprint — map the whole flow, find drop-off, separate frontstage from backstage |
decision-matrix | Pugh matrix + MCDA — choose among options across weighted criteria, surface hidden disagreement |
LLMs default to plausible-sounding output. These skills install a thinking discipline: define the dimensions, score them explicitly, and make the trade-off visible — so the decision is reasoned, not asserted.
⭐ Star if this catches a flaw in one of your AI-generated plans — and tell me what it caught: @marsloting on X
Drop into your agent's skill/plugin directory (e.g. ~/.claude/skills/, or install as a plugin where your agent supports a marketplace). Each skill triggers on its matching situation automatically.
MIT © marsloting
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.