Shape vague feature ideas into decided product directions before designing screens
Shape/Review/Handoff modes, evidence ledger separating known from assumed, AI necessity gate, risk rating, smallest coherent end-to-end feature, and concrete interaction contracts with real labels and error copy
- What
- Shape/Review/Handoff modes, evidence ledger separating known from assumed, AI necessity gate, risk rating, smallest coherent end-to-end feature, and concrete interaction contracts with real labels and error copy
- Cost
- Free
- Needs
- a feature idea, concept, or product area to decide on (and optionally a .uxproof/ contract from om-ux-setup) — the skill decides direction, it does not implement
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @open-mercato's om-ux-shape skill: turn ambiguity into a decided direction before anyone draws screens. Three modes (Shape for vague opportunities, Review for existing concepts/flows, Handoff for implementation-ready behavior), an operating discipline of ten principles (start from the consequential problem, treat requirements as claims, label facts/inferences/assumptions/unknowns, recommend a direction rather than hiding behind menus, treat AI as a design material with uncertainty/latency/cost), an evidence ledger separating known from assumed, an AI necessity gate with a rules-based-alternative check, human-value metrics, four product-risk ratings plus AI-specific risks, generation of 2-3 meaningfully different mechanisms with an explicit trade-off call, the smallest coherent end-to-end feature (now/later/not-doing), and concrete interaction contracts — named screens, named components, real labels, empty/loading/error/permission states, undo/retry/fallback paths — with a quality rubric gate before delivery. Honest caveats: process-heavy by design — overkill for trivial tweaks (scale depth to decision risk); required references (decision-framework, ai-interaction, report-templates) live in the skill's `references/` and must be loaded when triggered; the `.uxproof/` design contract (from om-ux-setup) constrains the output when one exists. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Shape vague feature ideas into decided product directions is a free Muse skill that turns ambiguity into a decided direction before anyone draws screens. It offers Shape, Review and Handoff modes, an evidence ledger separating known from assumed, an AI necessity gate, risk rating, the smallest coherent end-to-end feature, and concrete interaction contracts with real labels and error copy.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 3fc5a1fStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a feature idea, concept, or product area to decide on (and optionally a .uxproof/ contract from om-ux-setup) — the skill decides direction, it does not implement Install "Shape vague feature ideas into decided product directions before designing screens" for me. It gives my agent @open-mercato's om-ux-shape workflow: choose the mode (Shape/Review/Handoff), write for the least-context reader, load the required references when triggered (decision-framework, ai-interaction, report-templates), build the evidence ledger, run the AI necessity gate, rate the four product risks, choose a direction from 2-3 mechanisms with an explicit trade-off, shape the smallest coherent end-to-end feature, and deliver a concrete interaction contract (real labels, states, recovery paths) checked against the quality rubric. MIT licensed. Repository: https://raw.githubusercontent.com/open-mercato/skills/3fc5a1fbd84d90c6f052f3c97cb1e54d2660eb22/skills/om-ux-shape/SKILL.md Pinned version: install the code at commit 3fc5a1fbd84d90c6f052f3c97cb1e54d2660eb22 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "om-ux-shape". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. tell the agent the feature idea or concept to shape and who the least-context reader is (builder/drawer); pair it with om-ux-setup's .uxproof/ contract when one exists — install om-ux-setup separately; keep the process depth proportional to the decision risk). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 3fc5a1f · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.