Discovers product opportunities by analyzing Amplitude analytics, experiments, session replays, and customer feedback. Synthesizes evidence into prioritized, actionable opportunities with RICE scoring. Use when the user asks to "find opportunities", "what should we build", "where are we losing users", "product gaps", or wants a data-driven backlog of improvements.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 an excellent skill description that clearly articulates specific capabilities (Amplitude analytics analysis, RICE scoring, session replay analysis), provides explicit trigger guidance with natural user phrases, and occupies a distinct niche. It follows third-person voice throughout and is concise without unnecessary padding.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: analyzing Amplitude analytics, experiments, session replays, customer feedback, synthesizing evidence, prioritizing with RICE scoring, and generating actionable opportunities. | 3 / 3 |
Completeness | Clearly answers both 'what' (discovers product opportunities by analyzing Amplitude data, synthesizes into RICE-scored priorities) and 'when' (explicit 'Use when' clause with multiple trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes natural phrases users would actually say: 'find opportunities', 'what should we build', 'where are we losing users', 'product gaps', 'data-driven backlog of improvements'. These are realistic user queries. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific tool references (Amplitude), methodology (RICE scoring), and a clear niche (product opportunity discovery from analytics). Unlikely to conflict with generic analytics or product management skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill that provides Claude with a clear multi-phase workflow for product opportunity discovery. Its greatest strengths are the specific API call sequences with exact parameters, the rigorous RICE scoring framework with concrete anchors, and the thorough validation phase. The main weakness is length — at ~1800 words it could benefit from splitting reference material (RICE tables, output templates) into separate files, and some sections could be tightened.
Suggestions
Extract the RICE scoring table and effort/impact/confidence anchors into a separate RICE_SCORING.md reference file to reduce the main skill's token footprint.
Move the opportunity output template and writing standards into a separate REPORT_FORMAT.md file, referenced from the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is thorough but verbose at ~1800 words. Some sections could be tightened — the RICE scoring table with detailed anchors for effort and impact is useful reference material but takes significant space. The phase structure adds overhead, and some instructions (like 'Apply product management judgment') are unnecessary for Claude. However, most content is domain-specific and not explaining things Claude already knows. | 2 / 3 |
Actionability | Highly actionable with specific API calls (get_context, search with exact parameters like isOfficial: true, sortOrder: viewCount), concrete thresholds (>15% deviation, RICE >= 100 quality gate), exact output templates, and clear decision criteria. The guidance is specific enough that Claude knows exactly what to call, in what order, and how to interpret results. | 3 / 3 |
Workflow Clarity | Excellent 5-phase workflow with clear sequencing, parallel execution guidance ('run these in parallel, budget 10-15 tool calls'), explicit validation phase (Phase 4) with specific checks for partial-data artifacts, seasonality, already-shipped fixes, and correlation vs. causation. The 'quality gate' for RICE >= 100 acts as a checkpoint before presenting opportunities. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and phases, but it's a monolithic document with no references to supporting files. The RICE scoring anchors, opportunity template, and troubleshooting section could be split into separate reference files. However, since no bundle files exist, this is somewhat expected — the internal organization with phases and subsections provides reasonable navigation. | 2 / 3 |
Total | 10 / 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.
221ffaa
Table of Contents
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.