brainstorm-ideas-new
Brainstorm feature ideas for a new product in initial discovery from PM, Designer, and Engineer perspectives. Use when starting product discovery for a new product, exploring features for a startup idea, or doing initial ideation.
76
69%
Does it follow best practices?
Impact
Pending
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-new/SKILL.mdQuality
Discovery
82%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 solid description that clearly communicates both what the skill does and when to use it, with good trigger term coverage. Its main weakness is that the core capability ('brainstorm feature ideas') is somewhat singular and vague — listing more specific concrete actions (e.g., generating user stories, mapping technical constraints, creating feature matrices) would strengthen it. The distinctiveness could also be improved to reduce potential overlap with general brainstorming or product management skills.
Suggestions
Add more specific concrete actions beyond 'brainstorm feature ideas' — e.g., 'generate feature matrices, map user needs to technical feasibility, produce prioritized feature lists from PM, Designer, and Engineer perspectives'
Sharpen distinctiveness by emphasizing what makes this different from general brainstorming — e.g., the structured multi-role perspective approach or the specific output format
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (product discovery/ideation) and mentions the multi-perspective approach (PM, Designer, Engineer), but the core action is essentially just 'brainstorm feature ideas' — a single, somewhat vague action rather than multiple concrete actions like 'generate user stories, prioritize features, map technical feasibility.' | 2 / 3 |
Completeness | Clearly answers both 'what' (brainstorm feature ideas from PM, Designer, and Engineer perspectives) and 'when' (explicit 'Use when' clause covering product discovery, startup idea exploration, and initial ideation). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'brainstorm', 'feature ideas', 'new product', 'product discovery', 'startup idea', 'ideation', 'PM', 'Designer', 'Engineer'. Good coverage of how users would phrase such requests. | 3 / 3 |
Distinctiveness Conflict Risk | The multi-perspective angle (PM, Designer, Engineer) and focus on 'initial discovery' provide some distinctiveness, but 'brainstorm feature ideas' could overlap with general brainstorming skills, product management skills, or ideation tools. The niche is somewhat specific but not sharply delineated. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a reasonably structured ideation skill with a clear multi-perspective framework, but it lacks concrete examples of expected output format and contains some unnecessary explanatory content (Initial vs Continuous Discovery distinction, external course links). Adding a sample output snippet and trimming the domain context explanation would significantly improve both actionability and conciseness.
Suggestions
Add a concrete example of what one prioritized feature idea should look like (name, description, perspective, reasoning, key assumptions to test) to improve actionability.
Remove or significantly trim the 'Domain Context' section — the distinction between initial and continuous discovery can be conveyed in one sentence rather than a full subsection.
Add an explicit step after step 1 to confirm understanding with the user before proceeding to ideation, improving workflow clarity.
Consider removing the 'Further Reading' links to external courses, as they are not actionable by Claude and consume tokens without adding value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'Domain Context' section explaining Initial vs Continuous Discovery is somewhat unnecessary — Claude can infer this from context. The 'Further Reading' links to external courses/articles add little actionable value. However, the core instructions are reasonably tight. | 2 / 3 |
Actionability | The skill provides a clear structured process (understand, ideate, prioritize, detail assumptions) but remains at the level of abstract instruction rather than concrete examples. No sample output format, no example feature ideas, and no template for how prioritized ideas should be presented. | 2 / 3 |
Workflow Clarity | The four steps are clearly sequenced and logical, but there are no validation checkpoints or feedback loops — e.g., no step to confirm understanding with the user before ideating, no explicit check that the output meets quality criteria. For a non-destructive ideation task this is less critical, but the lack of any user confirmation step weakens the workflow. | 2 / 3 |
Progressive Disclosure | For a skill of this size (~40 lines), the content is well-organized with clear sections (Context, Domain Context, Instructions, Further Reading). The further reading links provide one-level-deep references. No unnecessary nesting or monolithic blocks. | 3 / 3 |
Total | 9 / 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
36ccefd
- 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.