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 memi-design/design-skills --skill product-discovery-and-framinggit clone --depth 1 https://github.com/memi-design/design-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/memi-design/design-skills/product-discovery-and-framing)<a href="https://agentmods.dev/skills/memi-design/design-skills/product-discovery-and-framing"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/product-discovery-and-framing/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/memi-design/design-skills/product-discovery-and-framing"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/product-discovery-and-framing.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 | $0.00052 | $0.00600 |
| Opus 5.5 | $0.00021 | $0.00240 |
| Sonnet 5.5 | $0.00010 | $0.00120 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
product-discovery-and-framing 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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Discovery and Framing
Turn an ambiguous request into an evidence-backed decision frame. Do not use this skill to design screens, run evaluative usability testing, or justify a predetermined feature.
Required inputs
Collect what exists without blocking on perfect research:
- decision, deadline, and decision owner;
- affected users and current behavior;
- business outcome and constraints;
- existing research, product data, support evidence, and technical facts;
- assumptions already being treated as facts.
Label missing evidence instead of inventing it.
Workflow
- State the decision. Write one sentence describing what must be decided and by when.
- Build an evidence ledger. Separate observed evidence, stakeholder claims, assumptions, and unknowns. Attach a source and freshness date where possible.
- Model the current situation. Describe the actor, context, goal, present workaround, friction, and consequence. Avoid demographic personas without behavioral evidence.
- Frame the problem. Use:
[Actor] struggles to [goal] when [context], causing [consequence]. Evidence: [sources]. - Identify opportunities. Group needs by underlying outcome. Keep solution ideas separate until the opportunity set is visible.
- Prioritize. Score opportunities using user impact, strategic value, evidence strength, urgency, effort uncertainty, and reversibility. Show the reasoning, not just a number.
- Define hypotheses. Express the expected behavior change, who experiences it, why it should occur, and what evidence would disconfirm it.
- Set success criteria. Choose one primary outcome, supporting indicators, guardrails, and a time horizon. Do not use output volume as the outcome.
- Choose the next evidence step. Prefer the smallest study, prototype, data query, or technical spike that resolves the highest-risk uncertainty.
Output contract
Return:
- decision statement;
- evidence and assumptions table;
- current-state problem frame;
- prioritized opportunity list;
- hypothesis and success measures;
- constraints and non-goals;
- unresolved risks;
- recommended next evidence step.
What ships with it
2 files 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.
- 1mo ago First seen · 52 lines · 52 tokens per session scan A a8322c8b21ee
product-discovery-and-framing is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 600 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
contribution-workflow
Design or document how new work enters a design system: contribution types, proposal criteria, review stages, sign-off and release. Triggers: contribution process, how should someone contribute, contribution guidelines, adding a new component. Not for audit findings to tickets (backlog-generator).
backlog-generator
Turn existing audit findings into sprint-ready tickets with T-shirt estimates, acceptance criteria, dependencies and phases. Triggers: tickets from audit, backlog from findings, sprint planning from report. Not for the contribution process (contribution-workflow).
authoring-a-prd
Run this to turn a feature idea or brief into a house-style PRD BEFORE any branch is opened — whenever the user says "write a PRD", "help me write a PRD", "create a PRD for", "draft the requirements for", "spec this feature", "document this feature", "turn this brief into a PRD", or "publish this to the tracker". Also…
gspdev-dev
Read milestones, issues, and branch state to propose the next task for GSP development.
post-launch
Everything that happens after v1 ships. Crash reporting setup, TestFlight feedback processing, version management, the update cycle, and how to maintain an app without breaking what already works. Use this skill after your first App Store submission and for all subsequent updates.
batch-all-issues
Resolve every open issue one at a time: fact-check each with web research, close the ones that need no action, and run the goal-pr skill to fix, review, and merge the ones that do — repeating until no actionable issues remain.