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

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./design/skills/research-synthesis/SKILL.md

Quality

Content

68%Weight 40%Scale 1-5

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

A well-organized, instruction-only skill whose main strength is a concrete, copy-adaptable output template; its main weaknesses are an implicit rather than explicit synthesis workflow with no validation checkpoints, and a dangling external CONNECTORS.md reference with broken connector-name syntax.

Suggestions

Add an explicit numbered synthesis workflow (e.g., extract quotes → cluster into themes → count prevalence per theme → map insights to opportunities → draft recommendations) so the sequence and its checkpoints are visible, not implied by section order.

Fix or remove the dangling [CONNECTORS.md](../../CONNECTORS.md) link and the malformed '~~user feedback'-style connector placeholders, replacing them with clearly named connector identifiers.

Include a short filled-in example (one theme with a real quote and prevalence count) to show the template in use, closing the gap between format skeleton and copy-paste-ready guidance.

Dimension	Reasoning	Score
Conciseness	The body is efficient — the output template is the actual deliverable spec and the tips are non-obvious craft guidance — but the opening line restates the description ('Synthesize user research data into actionable insights') and the connector sections could be tightened, leaving minor trim opportunities.	4 / 5
Actionability	The full markdown output template (theme blocks with prevalence/quotes/implication, insights-to-opportunities table, segment table, prioritized recommendations) is concrete and directly usable, but it is a format skeleton with no worked example showing a filled-in synthesis, leaving a minor gap against the copy-paste-ready anchor.	4 / 5
Workflow Clarity	The sequence (accept inputs → produce the templated output) is only implicit in the section ordering; there are no explicit analysis steps (e.g., read data → extract quotes → cluster into themes → quantify prevalence → map to opportunities) and no checkpoints such as verifying theme prevalence against the participant count. Not destructive/batch, so the cap doesn't apply, but it clearly sits below the 'clear sequence with most checkpoints' anchor.	3 / 5
Progressive Disclosure	The ~93-line body is well-sectioned and self-contained, with a one-level-deep pointer to the user-research skill for methods. However, the reference to [CONNECTORS.md](../../CONNECTORS.md) points outside the bundle to a file that doesn't exist in it, and the connector sections use malformed '~~name' strikethrough-style placeholders, which slightly muddies navigation.	4 / 5
	Total	15 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 with an explicit 'Use when' trigger clause, concrete deliverables, and natural input-type keywords. Its only gaps are a single-verb action statement and minor overlap with the adjacent user-research skill.

Dimension	Reasoning	Score
Specificity	The description names the domain ('user research') and concrete deliverables ('themes, insights, and recommendations', 'patterns, user segments, and prioritized next steps') with comprehensive input coverage, but relies on a single action verb ('Synthesize... distilled into') rather than multiple distinct actions, so it sits just below the comprehensive anchor.	4 / 5
Completeness	It explicitly answers both what ('Synthesize user research into themes, insights, and recommendations') and when ('Use when you have interview transcripts, survey results, usability test notes, support tickets, or NPS responses') with concrete trigger phrases, matching the top anchor exactly.	5 / 5
Trigger Term Quality	Natural trigger terms are strong ('interview transcripts, survey results, usability test notes, support tickets, or NPS responses'), but a few common variations users would say are missing (e.g., 'user feedback', 'customer research', 'focus groups'), placing it just below the comprehensive-synonyms anchor.	4 / 5
Distinctiveness Conflict Risk	The synthesis focus ('distilled into patterns, user segments, and prioritized next steps') is a clear niche, but the phrase 'user research' broadly overlaps with the sibling user-research skill this file itself references, creating minor conflict risk.	4 / 5
	Total	17 / 20 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
Path: design/skills/research-synthesis/SKILL.md
Commit: 8444efc

Reviewed: 6 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.