market-research-digest
Synthesize Drive files, Granola meeting notes, and web signals into a weekly Markdown research summary with Trends, Competitors, Ideas, and Risks sections. Use when a PM wants to consolidate scattered research into a single weekly digest.
68
61%
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 ./product-skills/skills/market-research-digest/SKILL.mdQuality
Discovery
85%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 strong skill description that clearly defines a specific workflow with concrete inputs, outputs, and structure. It includes an explicit 'Use when' clause targeting a specific persona and use case. The main weakness is that trigger terms could be broader to capture more natural user phrasings, particularly around Google Drive and alternative ways users might request research consolidation.
Suggestions
Expand trigger terms to include natural variations like 'Google Drive', 'weekly roundup', 'competitive analysis', 'market research digest', or 'research consolidation'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: synthesize Drive files, Granola meeting notes, and web signals into a weekly Markdown research summary with named sections (Trends, Competitors, Ideas, Risks). Very concrete about inputs, output format, and structure. | 3 / 3 |
Completeness | Clearly answers both what (synthesize Drive files, Granola meeting notes, and web signals into a weekly Markdown research summary with specific sections) and when ('Use when a PM wants to consolidate scattered research into a single weekly digest'). Explicit trigger guidance is present. | 3 / 3 |
Trigger Term Quality | Includes some good natural terms like 'Drive files', 'Granola meeting notes', 'weekly', 'research summary', and 'PM', but misses common variations users might say such as 'Google Drive', 'weekly roundup', 'competitive analysis', 'market research', or 'digest'. The term 'web signals' is somewhat jargon-y. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: the combination of specific input sources (Drive files, Granola meeting notes, web signals), specific output format (weekly Markdown with Trends/Competitors/Ideas/Risks sections), and specific persona (PM) makes this very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a prompt recipe than an actionable skill for Claude. It provides a well-structured output format but lacks concrete tool invocation examples, step-by-step workflow sequencing, and validation checkpoints. The content assumes a scheduling/orchestration capability without demonstrating how to actually execute each step using specific MCP tools.
Suggestions
Break the monolithic prompt template into a numbered workflow with discrete steps (e.g., 1. List files in Drive folder using drive MCP, 2. Read each file, 3. Query Granola API, 4. Search web, 5. Synthesize, 6. Validate output structure, 7. Save to Drive) with explicit validation between steps.
Add concrete MCP tool call examples showing how to read from Google Drive, query Granola, and save the output file — even if simplified, this makes the skill actionable rather than aspirational.
Add a validation checkpoint before saving: verify the output contains all four required sections, that Sources references match actual inputs consumed, and that the filename follows the correct date format.
Trim the introductory paragraph and let the prompt template and setup table speak for themselves — Claude doesn't need the narrative framing about scattered research.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary framing ('You have files in Google Drive, meeting notes in Granola...') and the intro paragraph explains what the skill does in a way Claude can infer. The tips section adds useful but somewhat verbose guidance. However, it's not egregiously padded. | 2 / 3 |
Actionability | The prompt template is fairly concrete and provides a clear structure for the output, but it's essentially a natural language prompt rather than executable code or specific MCP tool calls. There are no concrete API calls, tool invocation examples, or executable commands — it relies on Claude interpreting a scheduling directive and MCP names without showing how to actually call them. | 2 / 3 |
Workflow Clarity | There is no clear multi-step workflow with sequenced actions and validation checkpoints. The skill presents a single monolithic prompt template rather than breaking down the process into discrete steps (read Drive → query Granola → search web → synthesize → validate → save). There's no error recovery or validation beyond 'if any source is unavailable, skip it.' For an operation that writes files to Drive, the lack of verification steps is a significant gap. | 1 / 3 |
Progressive Disclosure | The content is reasonably organized with sections (Prompt Template, Setup, Placeholders, Tips) and references a companion 'competitor-monitoring' skill. However, there are no bundle files, no referenced external documents, and the prompt template section is quite long inline. The structure is adequate but not exemplary. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- amplitude/builder-skills
- Commit
221ffaa
- 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.