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.
62
72%
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-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 natural trigger terms. Its main weakness is that the core capability ('brainstorm feature ideas') is somewhat singular and could be more specific about the concrete outputs or actions involved. The multi-perspective angle (PM, Designer, Engineer) adds some distinctiveness but the description could benefit from more concrete action verbs.
Suggestions
Add more specific concrete actions beyond 'brainstorm' — e.g., 'generates feature lists, maps user needs, identifies technical constraints, and prioritizes ideas from PM, Designer, and Engineer perspectives'
Strengthen distinctiveness by clarifying what makes this different from general brainstorming — e.g., mention structured output formats like feature matrices or perspective-based categorization
| 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 just 'brainstorm feature ideas' — it doesn't list multiple concrete actions like generating user stories, prioritizing features, creating roadmaps, etc. | 2 / 3 |
Completeness | Clearly answers both what ('Brainstorm feature ideas for a new product in initial discovery from PM, Designer, and Engineer perspectives') and when ('Use when starting product discovery for a new product, exploring features for a startup idea, or doing initial ideation') with explicit triggers. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'feature ideas', 'product discovery', 'startup idea', 'ideation', 'brainstorm'. These are terms users would naturally use when seeking this kind of help. | 3 / 3 |
Distinctiveness Conflict Risk | The focus on multi-perspective brainstorming for new product discovery is somewhat distinctive, but it could overlap with general brainstorming skills, product management skills, or ideation tools. The PM/Designer/Engineer angle helps but doesn't fully eliminate conflict risk. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent brainstorming skill with a clear workflow and well-defined multi-perspective structure. Its main weaknesses are the lack of concrete output examples (what does a good feature idea look like?) and some unnecessary explanatory content. The external 'Further Reading' links add no value since Claude cannot access them during execution.
Suggestions
Add a concrete example of a prioritized feature idea with reasoning and assumptions to test, so Claude knows the expected output format and depth.
Remove or replace the 'Further Reading' section with external URLs — Claude cannot access these during execution. If the content is important, summarize key frameworks inline or in a bundle file.
Trim the 'Domain Context' section to a single sentence or remove it — the distinction between initial and continuous discovery is already implied by the skill's instructions and context.
| 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 are not actionable by Claude. However, the core instructions are reasonably tight. | 2 / 3 |
Actionability | The skill provides a clear multi-step process with specific perspectives and criteria, but it's entirely instructional with no concrete examples of what good output looks like (e.g., a sample feature idea with reasoning and assumptions). Without an example output format, Claude must guess at the expected structure and depth. | 2 / 3 |
Workflow Clarity | The four-step workflow is clearly sequenced and logical: understand → ideate → prioritize → detail assumptions. For a brainstorming/ideation skill (non-destructive, no batch operations), this level of workflow clarity is appropriate and sufficient without explicit validation checkpoints. | 3 / 3 |
Progressive Disclosure | The content is reasonably organized with clear sections, but the 'Further Reading' links point to external URLs that Claude cannot access or use during execution. There are no bundle files to reference, and the skill could benefit from a companion file with example outputs or evaluation criteria for generated ideas. | 2 / 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
d384f0c
- 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.