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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is lean and highly actionable via a complete scheduled-prompt template, with clear guardrails and good organization. Its main gap is the absence of an explicit validation/verification checkpoint for the weekly batch read, which keeps workflow clarity at the mid level.

Suggestions

Add a verification step to the prompt's Rules, e.g. before saving confirm all four sections (Trends, Competitors, Ideas, Risks) are present and every claim has a Sources citation; if a section is empty, note that explicitly rather than omitting it.

Add a brief post-run check that the dated file was actually written to {{OUTPUT_FOLDER}} and that the returned link resolves, so the weekly batch has a validate-then-retry feedback loop.

Trim the opening tagline/intro paragraph, which restates the frontmatter description, to reduce redundancy with the description field.

Dimension	Reasoning	Score
Conciseness	The body is lean: a copy-paste prompt template, a compact setup table, a short placeholder list, and four brief tips, with no teaching of concepts Claude already knows. Not level 2 because there is no padded explanation; the intro tagline and paragraph are brief and earn their place.	3 / 3
Actionability	The prompt template is copy-paste ready with concrete section structure, citation format, file-naming (research-summary-YYYY-MM-DD.md), save target, and "Return the Drive link when done". Not level 2 because it gives fully executable guidance rather than pseudocode or vague direction.	3 / 3
Workflow Clarity	The prompt sequences read Drive → query Granola → search web → synthesize → save → return link, with guardrails ("skip it and note it at the top", "Do not overwrite existing summaries", "Cite every file"), but there is no explicit validation/verification checkpoint for this batch read. Not level 3 because the batch operation lacks a validate-then-fix feedback loop; not level 1 because steps and rules are present and ordered.	2 / 3
Progressive Disclosure	The skill is self-contained with well-organized sections (Prompt Template, Setup, Placeholders, Tips) and no broken or nested external references; the only mentions (competitor-monitoring skill, competitors.md) are user/data artifacts, not bundle files. Not level 2 because content is appropriately sectioned rather than a monolithic wall or inline reference dump.	3 / 3
	Total	11 / 12 Passed

Description

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.

A strong description: third-person, concrete about inputs and output structure, with an explicit Use-when trigger and a distinctive niche. It clearly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	"Synthesize Drive files, Granola meeting notes, and web signals into a weekly Markdown research summary with Trends, Competitors, Ideas, and Risks sections" names multiple concrete inputs and concrete output sections. Not level 2 because it lists several distinct specific actions rather than a single domain plus partial actions.	3 / 3
Completeness	It states what (synthesize three source types into a four-section weekly Markdown summary) and when ("Use when a PM wants to consolidate scattered research into a single weekly digest"), with an explicit Use-when clause. Not level 2 because the when trigger is explicit, not merely implied.	3 / 3
Trigger Term Quality	"Use when a PM wants to consolidate scattered research into a single weekly digest" plus "weekly Markdown research summary" covers natural phrasings a user would say (research digest, weekly summary, consolidate research). Not level 2 because it offers multiple natural variations rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	The Granola-meeting-notes + Drive + web-signal combination into a weekly research digest is a clear niche with distinct triggers unlikely to match generic summarization skills. Not level 2 because the data-source blend and weekly cadence make overlap with sibling skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: amplitude/builder-skills
Commit: 22b0634

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.