brainstorm-ideas-existing
Brainstorm product ideas for an existing product using multi-perspective ideation from PM, Designer, and Engineer viewpoints. Use when generating new feature ideas, brainstorming solutions for an identified opportunity, or ideating with a product trio.
64
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./pm-product-discovery/skills/brainstorm-ideas-existing/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly communicates its purpose, methodology, and trigger conditions. It uses third person voice correctly, includes a comprehensive 'Use when' clause with natural trigger terms, and carves out a distinct niche through its multi-perspective product trio approach. The description is concise yet informative, hitting all the key criteria effectively.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: brainstorming product ideas, multi-perspective ideation from PM/Designer/Engineer viewpoints. The description names the methodology (multi-perspective ideation) and the specific roles involved. | 3 / 3 |
Completeness | Clearly answers both 'what' (brainstorm product ideas using multi-perspective ideation from PM, Designer, and Engineer viewpoints) and 'when' (explicit 'Use when' clause covering generating feature ideas, brainstorming solutions for opportunities, or ideating with a product trio). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'brainstorm', 'product ideas', 'feature ideas', 'ideating', 'product trio', 'PM', 'Designer', 'Engineer'. These cover common variations of how users would phrase such requests. | 3 / 3 |
Distinctiveness Conflict Risk | The combination of multi-perspective ideation with the specific PM/Designer/Engineer trio creates a clear niche. The focus on product ideation from these three viewpoints is distinctive enough to avoid conflicts with generic brainstorming or single-role skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable framework for multi-perspective product ideation but stays at an abstract instructional level without concrete examples of expected output format or quality anchors. The domain context section explains concepts Claude likely already knows, and the Further Reading links add little actionable value. The workflow is logical but lacks validation steps and iteration guidance.
Suggestions
Add a concrete example showing the expected output format for one prioritized idea (name, description, reasoning, assumptions) so Claude has a clear template to follow.
Remove or significantly trim the Domain Context section — Claude already knows about Product Trios and Opportunity Solution Trees; instead, just reference the framework name in the instructions.
Add an iteration/feedback loop step (e.g., 'Ask the user which ideas resonate before deep-diving' or 'If the user wants more ideas in a specific direction, loop back to step 2 with refined constraints').
Replace the Further Reading external URLs with a brief inline note or remove them entirely, as they consume tokens without being reliably accessible.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary context Claude already knows (e.g., explaining what a Product Trio is, quoting Teresa Torres). The 'Further Reading' links are not actionable by Claude in most contexts and consume tokens. The Domain Context section could be trimmed significantly. | 2 / 3 |
Actionability | The instructions provide a clear multi-step process but remain at the level of abstract guidance rather than concrete, executable examples. There are no example outputs showing what a well-formatted idea looks like, no template for the prioritized idea format, and no concrete example of input/output to anchor Claude's behavior. | 2 / 3 |
Workflow Clarity | The four steps are clearly sequenced and logical, but there are no validation checkpoints or feedback loops. Step 1 mentions asking for clarification, which is good, but there's no guidance on what to do if ideation quality is low, if the user wants to iterate, or how to handle ambiguity in prioritization criteria. The conditional 'save as markdown' at the end is vague ('if substantial'). | 2 / 3 |
Progressive Disclosure | The Further Reading section provides external references, but these are external URLs rather than companion files in the workspace. The skill is a single monolithic file with no clear split between quick-start overview and detailed guidance. For a skill of this length (~50 lines), the structure is acceptable but the Further Reading links are not useful as progressive disclosure since Claude cannot reliably access them without web search. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- phuryn/pm-skills
- Commit
020ee82
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.