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 stefanoskarakasis/Product-Marketing-Skills --skill interview-summarygit clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-SkillsWrote 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/stefanoskarakasis/product-marketing-skills/interview-summary)<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/interview-summary"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/interview-summary/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/interview-summary"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/interview-summary.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00094 | $0.03373 |
| Opus 5.5 | $0.00038 | $0.01349 |
| Sonnet 5.5 | $0.00019 | $0.00675 |
| Haiku 4.5 | $0.00009 | $0.00337 |
Grade A, and why
interview-summary 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 12d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
interview-summary — Customer Discovery Synthesis Engine
Transforms raw interview transcripts into structured intelligence. Not a transcription service. A synthesis engine that extracts Jobs, surfaces patterns, and flags contradictions with your positioning or ICP. Built on JTBD theory. Sharpened for B2B product and GTM contexts.
Trigger
- When: Any customer or prospect interview needs synthesis into structured discovery output. This includes: discovery calls, win/loss debriefs, churn interviews, competitive research interviews, onboarding feedback, feature validation calls, or any call where you need to extract Jobs, map solutions, and flag contradictions with your positioning or ICP.
- Not for:
- interview-summary is not a transcription tool — use Otter.ai or Fireflies for that.
- interview-summary is not for analyzing your own positioning or messaging in isolation.
If you need to check whether your messaging lands with buyers, route to
positioning-messagingorgaccs-brief. - interview-summary is not for building buyer personas from scratch without interviews. No dedicated persona-building skill exists yet; this skill synthesizes existing transcript data only.
- Example prompts:
- "Summarize this customer discovery call and flag which Jobs matter most"
- "I have a win/loss interview — help me extract what we lost and why"
- "Process this transcript. Flag any positioning signal that contradicts our current narrative"
- "Churn interview debrief — what Job did we fail to deliver on?"
Inputs
- Args: Path to a transcript file (
.txt,.md,.pdf), pasted plain text, structured note dump, or Otter/Fireflies/Rev transcription output. Optional: interview context (interviewee role, company, interview purpose). Free format — transcript alone is sufficient; context makes synthesis sharper. - Defaults: If no context provided, skill asks three orientation questions. If interviewee segment unknown, default to "Unclassified" in ICP match. If no interview type specified, default to "Discovery".
- Context keys:
/foundation/brain.md— optional. Section 2 (ICP, including the confirmed beachhead segment) and Section 3 (Alternatives & Positioning), used only to validate the ICP match and to compare named alternatives. Never used to shape what the transcript says.- Brain contract: Reads Sections 2, 3. Writes: none. Never writes to: Sections 1 to 8. Customer words, objections and switching forces from a summary are stored by
product-marketing-context(Add material) after you approve the Brain Diff. /context/meta-patterns.md— optional; recurring patterns the user has logged from prior interviews
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago Changed · -1 lines · -16 tokens per session 0a1df3b99866
- 17d ago Changed 8eb1af294567
- 20d ago Changed · +1 lines 6169e7f4383a
- 25d ago Changed · +2 lines 556523ff713e
- 26d ago Changed · +11 lines 92136c002d77
- 1mo ago Changed · +14 lines 342b3b5b0913
- 2mo ago First seen · 222 lines · 110 tokens per session scan A 9ce5d65b89bf
interview-summary is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (8 stars, last pushed 4d ago), licensed MIT. It adds 94 tokens to every session and 3,373 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
report
A way to export a chat card or reply as a standalone HTML report, meaning a file that can open in a browser without the chat application. It preserves the card template, including right-to-left Persian or left-to-right English layouts.
k8s-rightsize
Right-size Kubernetes CPU and memory requests from Prometheus usage (p95 CPU, p98 memory over 7 days), size the node count, tune KEDA autoscaling. Use when asked to rightsize workloads, cut node cost, or "how many nodes do we need".
owasp-security
Deep OWASP reference: Top 10 2025, ASVS 5.0, secure patterns, per-language quirks, LLM Top 10 and agentic AI security. Use for an in-depth security review, auth work, or hardening an LLM or agent app. For the everyday baseline use secure-coding.
fig
One self-contained HTML file holding a looping animated SVG, for ideas that move: flows, loops, retries, queues, fan-outs. Use when the user says "fig" or a diagram would be better animated.
brand
A project-specific visual identity for chat cards and saved reports, using the project's colors, logo, and fonts. It finds these details in the repository or asks the user for them, then stores the result in a committable `.readable/` folder.
workspace-rules
A set of guidelines for deciding which rules belong in a repository's workspace instructions and which should be enforced by its build or checks.