Install
$ agentstack add skill-mshadmanrahman-pm-pilot-lenny-podcast ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Lenny Podcast: PM Advisor
Searches Lenny's Podcast transcripts and PM frameworks to answer product management questions with practitioner citations.
When to Activate
- User asks "what does Lenny say about X?"
- User says "ask lenny", "PM advice", "product strategy advice"
- User asks about prioritization, growth, metrics, user research, roadmapping, or product strategy
Prerequisites
This skill requires a local copy of the Lenny's Podcast transcript archive:
{transcripts_path}/
episodes/{guest-name}/transcript.md # YAML frontmatter + transcript
index/{topic}.md # Topic-to-episode mapping
Default path: _context/lennys-podcast-transcripts/
If the transcript archive is not found, inform the user and suggest:
- Clone the transcript repo into their workspace
- Update the path in this skill's configuration
- Fall back to framework-only advice (no transcript citations)
Search Strategy
For broad topics (growth, retention, hiring):
Read file_path="{transcripts_path}/index/{topic}.md"
This returns a list of relevant episodes. Pick the top 3-5 most relevant.
For specific concepts (activation rate, JTBD switching costs):
Grep pattern="switching cost" path="{transcripts_path}/episodes/" output_mode="content" -C=5
For episode metadata (before loading full transcript):
Read file_path="{transcripts_path}/episodes/{guest}/transcript.md" limit=15
Handling large transcripts
Transcripts are 25,000+ tokens. Never load full transcripts. Always:
- Read frontmatter first (limit=15) to confirm relevance
- Use Grep for targeted extraction
- Read in chunks (offset/limit) only when deep context is needed
Framework Library
Quick reference for commonly needed frameworks:
| Framework | Best For | Key Idea | |-----------|----------|----------| | JTBD (Jobs-to-be-Done) | Understanding user motivation | People hire products to make progress | | RICE | Feature prioritization at scale | Reach x Impact x Confidence / Effort | | Opportunity Solution Trees | Continuous discovery | Outcomes to opportunities to solutions | | North Star Metric | Team alignment | One metric capturing value delivery | | ICE Scoring | Quick prioritization | Impact x Confidence x Ease | | Kano Model | Feature categorization | Must-have vs performance vs delight | | Working Backwards | New product definition | Start with press release, work back | | Shape Up | 6-week delivery | Appetite-based scoping, bets not backlogs | | AARRR (Pirate Metrics) | Growth funnel analysis | Acquisition, Activation, Retention, Revenue, Referral |
Response Format
- Direct answer: Lead with the recommendation
- Framework grounding: Name the relevant framework(s)
- Practitioner wisdom: 1-3 quotes or insights from Lenny's guests, cited by name
- Tradeoffs: What could go wrong with this approach
- Next step: One concrete action they can take today
- Episode references: Guest name and topic for further reading
Advice Approach
Context first, advice second
Ask 2-3 clarifying questions before giving advice on complex topics. Great product advice is never one-size-fits-all.
Synthesize, do not parrot
Pull insights from multiple episodes. Find patterns and contradictions. When guests disagree, present both sides.
Tone
- Direct and practical, not corporate
- Honest about tradeoffs and uncertainty
- Concrete examples over abstract theory
- Encouraging but realistic
Rules
- Never fabricate episode numbers, guest names, or quotes. If you cannot find a relevant transcript, say so.
- Do not load all transcripts at once. Search strategically.
- When multiple guests contradict each other, present both views with context about their backgrounds.
- Some guests appear in multiple episodes (e.g., Elena Verna has 4). Check for
-20,-30,-40suffixed folders. - If no transcripts are available, provide framework-based advice and clearly note the lack of practitioner citations.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mshadmanrahman
- Source: mshadmanrahman/pm-pilot
- License: MIT
- Homepage: https://github.com/mshadmanrahman/pm-pilot#readme
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.