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 | $0.00026 | $0.00300 |
| Sonnet 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 9d 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.
- 9d 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 $0.0003 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 2026-09-03.
Other skills, from other repositories
execute-round
Use when a planned round handoff exists and needs to be implemented end-to-end via the 4-commit chain (entry-admin → BA design → dev body with inline CR + SE → state refresh + self-audit). Dispatches ba-designer / developer / cr-reviewer / se-contract sequentially.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
post-issue-comment
Post a reply comment on a GitHub issue in English with a natural, concise writing style, based on the intent passed as arguments.
orchestrate
Pipeline orchestration: dispatch the highest-priority ready tasks/work units to agents, manage capacity, and coordinate the Todo to Done flow. Invoked as /agiflow:orchestrate. Uses listtasks, listactivetasksbyorg, listmembers, updatetask, getworkunitprogress.
ticket-craft
Create Jira/Asana/Linear tickets optimized for Claude Code execution - AI-native ticket writing.
project-plan
Turn a product goal or feature request into a clear Agiflow project plan with small, testable tasks in Planning status. Use when starting a project, decomposing a feature, clarifying requirements, or converting an idea into an actionable backlog.