Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mshadmanrahman/pm-pilot --skill interview-snapshotgit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mshadmanrahman/pm-pilot/interview-snapshot)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/interview-snapshot"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/interview-snapshot.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00089 | $0.01183 |
| Opus 5 | $0.00044 | $0.00592 |
| Sonnet 5 | $0.00018 | $0.00237 |
| Haiku 4.5 | $0.00009 | $0.00118 |
Grade A, and why
interview-snapshot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Snapshot
One interview in, one structured markdown file out. Nothing else.
This is the atomic unit of customer research. Before ever running cross-interview synthesis, every interview passes through here first. Teresa Torres calls out combining synthesis steps as her single biggest anti-pattern; this skill is the guardrail that prevents it.
When to use
- Granola just synced a discovery interview transcript into the vault
- A recorded interview was transcribed via Fireflies, Otter, etc.
- You took live interview notes and want them structured
- You are about to run discovery-process Phase 4 (synthesis) and have raw transcripts
When NOT to use
- For internal team meetings (use post-meeting skill)
- For usability tests (they need a different schema: task-by-task observations)
- For NPS surveys or quantitative survey data
- To synthesize multiple interviews at once. Never. Run this skill once per interview, THEN move to cross-interview synthesis.
The schema (five sections, in order)
1. Experience Map
A timeline of what the participant actually did. First-person, past tense, concrete. Not what they would do or what they usually do, but what happened the most recent time.
Structure:
**Trigger:** What kicked off the experience
**First action:** Literal first thing they did
**Next steps:** Ordered sequence of what followed
**Tools / people touched:** Every app, site, document, human involved
**Outcome:** Did they finish? Abandon? Partially succeed?
**Time spent:** Actual duration if available, estimate if not
2. Opportunities
Moments where the participant hit friction, confusion, frustration, or made a workaround. One bullet per opportunity. Each bullet must include a direct quote.
- **[Label]**: [One-sentence description]. "[Verbatim quote]" (timestamp if available)
An "opportunity" in Teresa's vocabulary is not a solution idea. It's a problem moment worth addressing. Do not write solution hypotheses here.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 127 lines · 89 tokens per session scan A 105a2b80997e
interview-snapshot is a skill published in the GitHub repository mshadmanrahman/pm-pilot (20 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 1,183 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
analyze-codebase
Run comprehensive PLG analysis on a codebase to detect tech stack, existing growth features, and revenue opportunities. Use when the user says "analyze", "scan", "audit codebase", or "find growth opportunities".
build-implementation
Generate context-aware implementation prompts for a selected growth loop. Use when the user says "build", "implement", "generate code", "create prompt", or "how do I build this".
deploy-telemetry
Set up analytics and tracking infrastructure for growth loops. Use when the user says "deploy telemetry", "set up analytics", "tracking", "events", "push to supabase", or "skene push".
plan-growth-loop
Generate prioritized growth loops with implementation roadmaps based on codebase analysis. Use when the user says "plan", "growth loops", "prioritize", "what should I build", or "roadmap".
validate-loop
Check if growth loop requirements are actually implemented in the codebase. Use when the user says "validate", "check status", "skene status", "is it done", or "verify implementation".
initialize-config
Set up Skene configuration for a project. Use when starting a new PLG analysis, when .skene.config is missing, or when the user says "skene init", "set up skene", or "configure skene".