$npx -y skills add Undertone0809/rudder --skill software-product-advisorCross-functional advisor for software product work when a feature, workflow, UI, spec, or implementation feels wrong but the user cannot yet express a precise critique. Use this whenever the user says a result feels off, too complex, too noisy, too generic, or not ready for anoth
| 1 | # Software Product Advisor |
| 2 | |
| 3 | This skill exists for the moments during software product development when the |
| 4 | current direction is weak, wrong, or under-specified, but the problem is still |
| 5 | fuzzy. |
| 6 | |
| 7 | It is not an implementation skill first. |
| 8 | It is a diagnosis, translation, and routing skill. |
| 9 | |
| 10 | Use it when the user needs an expert advisor to turn fuzzy discomfort into: |
| 11 | |
| 12 | - a clearer problem statement |
| 13 | - a professional diagnosis |
| 14 | - explicit evaluation criteria |
| 15 | - 2-3 realistic options |
| 16 | - one recommended next move |
| 17 | |
| 18 | ## What This Skill Does |
| 19 | |
| 20 | This skill acts like a cross-functional advisor spanning: |
| 21 | |
| 22 | - product framing |
| 23 | - user journey and information architecture |
| 24 | - interaction design and UX |
| 25 | - visual design and trust signals |
| 26 | - engineering shape and delivery strategy |
| 27 | - standards and review quality |
| 28 | |
| 29 | Its main job is to identify which layer is actually broken. |
| 30 | |
| 31 | Examples: |
| 32 | |
| 33 | - "This feature technically works, but it still feels wrong." |
| 34 | - "The team keeps iterating, but every version feels off. Help me critique it professionally." |
| 35 | - "Before we keep building, research best practices and tell me what we're missing." |
| 36 | - "Should we keep patching this or rewrite the spec, flow, or architecture?" |
| 37 | - "I know the result is too big, too noisy, or too complicated, but I need better language." |
| 38 | |
| 39 | ## What This Skill Does Not Do |
| 40 | |
| 41 | Do not treat this as a direct code-writing skill by default. |
| 42 | |
| 43 | It should not: |
| 44 | |
| 45 | - jump into implementation before diagnosis |
| 46 | - assume every problem is visual polish |
| 47 | - replace a clear debugging or root-cause investigation when the issue is mainly correctness |
| 48 | - produce vague advice like "make it cleaner" without criteria |
| 49 | - stay at the strategy level when a local critique would be enough |
| 50 | |
| 51 | If the correct outcome is to route to a more specialized skill, say so clearly. |
| 52 | |
| 53 | ## Distinguish From Nearby Skills |
| 54 | |
| 55 | Use this skill when the user is blocked on judgment, articulation, or deciding |
| 56 | which layer of the problem to fix first. |
| 57 | |
| 58 | Do not use it as the first tool when the main need is already clear: |
| 59 | |
| 60 | - use an ideation or market-framing skill when the product is still pre-build |
| 61 | - use a visual QA or design-review skill when the issue is clearly a live UI quality problem |
| 62 | - use an engineering plan or architecture-review skill when the main concern is system design |
| 63 | - use a debugging or investigation skill when the issue is mainly a bug, regression, or correctness failure |
| 64 | - use a workflow-routing skill when the user mainly needs help choosing a process, toolchain, or review chain |
| 65 | |
| 66 | ## Default Workflow |
| 67 | |
| 68 | Follow this sequence unless the user explicitly narrows the task. |
| 69 | |
| 70 | ### 1. Reframe The Ask |
| 71 | |
| 72 | State plainly: |
| 73 | |
| 74 | - what the user is trying to do |
| 75 | - what feels wrong |
| 76 | - what kind of help they actually need |
| 77 | |
| 78 | Example: |
| 79 | "You do not need another blind iteration. You need a professional diagnosis of why this result feels wrong, plus the right next move." |
| 80 | |
| 81 | ### 2. Diagnose The Layer |
| 82 | |
| 83 | Classify the problem into one primary layer, and one optional secondary layer: |
| 84 | |
| 85 | - product framing |
| 86 | - information architecture |
| 87 | - interaction design |
| 88 | - visual design |
| 89 | - engineering architecture |
| 90 | - correctness / debugging |
| 91 | - standards or governance gap |
| 92 | - workflow or review gap |
| 93 | |
| 94 | If several are plausible, pick the most upstream one. |
| 95 | |
| 96 | Rule: |
| 97 | If a standards gap is causing repeated low-quality output, call that out explicitly. |
| 98 | |
| 99 | ### 3. Search Before Advising |
| 100 | |
| 101 | Before giving recommendations, inspect the most relevant local context: |
| 102 | |
| 103 | - repo instructions or team guidelines |
| 104 | - product specs, PRDs, or tickets |
| 105 | - design systems, interaction standards, or past reviews |
| 106 | - the specific screen, flow, doc, code, or artifact under discussion |
| 107 | - nearby skills, templates, or review checklists that may already solve the problem |
| 108 | |
| 109 | When the topic is unstable or best-practice-driven, inspect primary external guidance before concluding. |
| 110 | |
| 111 | Do not guess if you can verify quickly. |
| 112 | |
| 113 | ### 4. Translate Vague Dissatisfaction Into Professional Language |
| 114 | |
| 115 | Turn the user's intuition into explicit critique. |
| 116 | |
| 117 | Examples: |
| 118 | |
| 119 | - "too big" -> poor surface ratio, oversized controls, inflated internal whitespace |
| 120 | - "too noisy" -> weak hierarchy, too many competing accents, helper copy overexposed |
| 121 | - "too complicated" -> poor progressive disclosure, secondary settings shown too early |
| 122 | - "feels generic" -> no product thesis, weak different |