research-synthesis

Synthesize user research into themes, insights, and recommendations. Use when you have interview transcripts, survey results, usability test notes, support tickets, or NPS responses that need to be distilled into patterns, user segments, and prioritized next steps.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

87%

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

A well-organized, actionable instruction skill: a complete output template and sharp tips make it immediately usable, and the file structure is clean with a single one-level reference. The main gap is workflow clarity — it never sequences the synthesis steps or adds any verification checkpoint.

Suggestions

Add a short numbered workflow before the Output template that sequences the synthesis (e.g., 1. ingest and normalize data → 2. tag observations → 3. cluster into themes → 4. map insights to opportunities → 5. prioritize recommendations), so the process is explicit rather than implied by the template.

Include a verification/sanity-check step, such as confirming every theme cites at least one supporting quote and that observations are separated from interpretations before drafting recommendations — this gives a feedback loop without adding a destructive-operation cap.

Tighten the 'If Connectors Available' section by signaling which connector findings should feed which output section (e.g., analytics → Impact column, support tickets → Supporting Evidence), making the integration more actionable.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: a structured output template, an accepted-inputs list, connector integration, and three concrete tips — no padding explaining what user research is, and every section earns its place.	3 / 3
Actionability	Provides a fully specified output template (themes with prevalence, supporting quotes, insights→opportunities table, segments, prioritized recommendations) plus concrete guidance such as '7 of 10 users' vs 'Most users', giving copy-paste-ready structure.	3 / 3
Workflow Clarity	Structure exists (accept → output → connectors → tips) but there is no explicit synthesis sequence or any validation/verification checkpoint; the implicit ingest→theme→evidence→recommend flow is not sequenced for the model.	2 / 3
Progressive Disclosure	Well-organized into clear single-purpose sections with a one-level-deep, clearly signaled reference to CONNECTORS.md and no nested file chains; the self-contained single-file structure is appropriate here.	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 actions, explicit 'Use when' trigger with natural data-source keywords, and a distinct niche that avoids skill conflicts. It is concise without fluff and clearly communicates both capability and invocation conditions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Synthesize user research into themes, insights, and recommendations' and 'distilled into patterns, user segments, and prioritized next steps' — matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers what ('synthesize... into themes, insights, and recommendations') and when ('Use when you have interview transcripts, survey results...'), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'interview transcripts, survey results, usability test notes, support tickets, or NPS responses' — with good variation across data-source types.	3 / 3
Distinctiveness Conflict Risk	The user-research-synthesis niche with its specific data-source triggers is clearly distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: anthropics/knowledge-work-plugins
Commit: f96c57c

Reviewed: 2 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.