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 ianklassen/pm-skills --skill spec-from-conversationgit clone --depth 1 https://github.com/ianklassen/pm-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/ianklassen/pm-skills/spec-from-conversation)<a href="https://agentmods.dev/skills/ianklassen/pm-skills/spec-from-conversation"><img src="https://agentmods.dev/badge/skills/ianklassen/pm-skills/spec-from-conversation/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/ianklassen/pm-skills/spec-from-conversation"><img src="https://agentmods.dev/badge/skills/ianklassen/pm-skills/spec-from-conversation.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 | $0.00108 | $0.00551 |
| Opus 5 | $0.00054 | $0.00275 |
| Sonnet 5 | $0.00022 | $0.00110 |
| Haiku 4.5 | $0.00011 | $0.00055 |
Grade A, and why
spec-from-conversation 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec From Conversation
What this does
Takes messy input (a transcript, a thread, rambling notes) and produces a structured first-draft spec. This skill produces a draft to be argued with, not a final document. It should surface ambiguity the conversation left unresolved rather than silently resolving it for the reader.
Process
- Extract, don't invent. Pull the problem statement, goals, and constraints only from what was actually said. If the conversation didn't settle something (e.g., no one said what "done" looks like), write it into "Open Questions," don't guess a metric that sounds plausible.
- Separate stated goals from implied ones. If a stakeholder said "make it faster" but never gave a number, the spec should say "faster (no target given, needs follow-up)" rather than picking 200ms because it sounds reasonable.
- Draft non-goals explicitly, even if the conversation never mentioned them. A spec with no non-goals section is usually a spec that will grow scope silently later, so flag anything adjacent that was implicitly excluded (e.g., "web only, per the discussion; mobile wasn't mentioned either way, confirm").
- Flag conflicting statements rather than resolving them. If two people in the thread said different things, both go in with attribution, not a smoothed-over average.
Output structure
## Problem
[What's broken/missing, from the conversation, in plain terms]
## Goals
[What success looks like. Flag any goal stated without a measurable target]
## Non-Goals
[What's explicitly or implicitly out of scope]
## Success Metrics
[Only include metrics actually discussed; otherwise list under Open Questions]
## Open Questions
[Everything the conversation didn't resolve. This section should not be empty on a first draft]
What to watch for
Don't let this skill's output look more decided than the conversation actually was. A polished-looking doc with confident language creates false consensus, since stakeholders will assume agreement existed just because it's written down cleanly. When in doubt, under-resolve rather than over-resolve.
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 First seen · 41 lines · 108 tokens per session scan A 0f924702cd96
spec-from-conversation is a skill published in the GitHub repository ianklassen/pm-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 551 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
tool-foundation-sprint-founding-hypothesis
Day 2 end capstone move of a Foundation Sprint. Compresses the sprint's full strategic frame into a single canonical sentence (the Founding Hypothesis) plus an assumption scorecard, why-we-believe, what-could-prove-us-wrong, and recommended next validation step. Use after Magic Lenses is signed. Strict canonical…
apple-container
Apple's open-source container CLI to build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS — no Docker daemon required. Use when the user mentions the container CLI, "apple container", running or building containers on macOS without Docker/Podman, container run, container…
imagen
Generate images using Google Gemini's image generation capabilities. Use this skill when the user needs to create, generate, or produce images for any purpose including UI mockups, icons, illustrations, diagrams, concept art, placeholder images, or visual representations.
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
measure-survey-analysis
Analyze survey results into actionable PM insights. Produces persona segmentation, hypothesis validation status, thematic clustering of open-text responses, statistical confidence labels, prioritized recommendations, and what-NOT-to-conclude warnings. Refuses to overstate statistical significance from weak samples or…
tool-design-sprint-prototype-plan
Day 4 (Thursday) move of a Design Sprint that produces the planning artifact for the day. Output covers the prototype role plan (Maker, Stitcher, Writer, Asset Collector, Interviewer), prototype brief (what to build, fidelity bar, time allocation per role), canonical Five-Act Interview script (Welcome, Context, Intro…