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.
59
68%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./design/skills/research-synthesis/SKILL.mdQuality
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 a strong skill description that clearly articulates what the skill does (synthesize user research into actionable outputs), when to use it (with specific input types like interview transcripts and survey results), and includes rich natural trigger terms. The only minor note is the use of second person 'you have' in the trigger clause, but this is within the 'Use when' guidance pattern and doesn't significantly detract from quality.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'synthesize user research into themes, insights, and recommendations' and further specifies 'distilled into patterns, user segments, and prioritized next steps.' These are concrete, actionable outputs. | 3 / 3 |
Completeness | Clearly 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 that need to be distilled into patterns, user segments, and prioritized next steps'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'interview transcripts', 'survey results', 'usability test notes', 'support tickets', 'NPS responses', 'user research', 'themes', 'insights', 'user segments'. These are terms a user would naturally use when seeking this kind of analysis. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly occupies a distinct niche around user research synthesis with specific input types (interview transcripts, survey results, usability test notes, support tickets, NPS responses) and specific outputs (themes, patterns, user segments, prioritized next steps). Unlikely to conflict with generic data analysis or other skills. | 3 / 3 |
Total | 12 / 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 provides a well-structured output template for research synthesis but critically lacks a workflow for how to actually perform the synthesis — the analytical process of coding data, identifying patterns, and validating themes is entirely absent. The output format is concrete and useful, but the skill reads more like an output specification than an actionable guide. Some content (tips, input list) explains things Claude already knows.
Suggestions
Add a step-by-step synthesis workflow: e.g., 1) Read all data, 2) Code recurring statements, 3) Group codes into themes, 4) Validate themes against data (check prevalence), 5) Generate insights, 6) Prioritize recommendations.
Remove or significantly trim the 'What I Accept' list and 'Tips' section — Claude already knows what research data looks like and understands the difference between observations and interpretations.
Add validation checkpoints such as 'Verify each theme is supported by at least 2 participants before including' or 'Cross-check that recommendations map back to specific insights.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary sections like 'What I Accept' which is a list Claude could infer, and the Tips section explains basic research methodology concepts (observations vs interpretations) that Claude already knows. The output template is detailed but justified as it defines the expected format. | 2 / 3 |
Actionability | The skill provides a detailed output template which is concrete and useful, but lacks executable steps for how to actually perform the synthesis — there's no process for coding transcripts, identifying themes, or resolving conflicting data. It describes what the output should look like but not how to get there. | 2 / 3 |
Workflow Clarity | There is no multi-step workflow defined at all. The skill jumps from 'here's what I accept' to 'here's the output format' with no synthesis process in between — no steps for reading data, coding themes, validating patterns, or iterating on insights. For a complex analytical task like research synthesis, this is a significant gap. | 1 / 3 |
Progressive Disclosure | References to CONNECTORS.md and a 'user-research' skill are present and one-level deep, which is good. However, there are no bundle files to support these references, and the output template is quite long inline content that could potentially be split out. The overall structure with clear sections is reasonable. | 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
- anthropics/knowledge-work-plugins
- Commit
3bf5929
- 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.