user-research

Plan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when the user needs help with any aspect of understanding their users through research.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

72%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 lean, well-organized reference for the user-research domain that never wastes tokens. Its weakness is depth of guidance: techniques and artifacts are named rather than operationalized, leaving Claude without concrete procedures for interviewing or synthesis.

Suggestions

Add 2-3 example interview questions or probes to the Interview Guide Structure so the guide is directly usable.

Give a one-line procedure for each Analysis Framework technique (e.g., how to run affinity mapping with raw notes, or what a jobs-to-be-done statement looks like).

Add brief decision guidance linking the Methods table to study objectives (e.g., 'choosing a method: start from the objective, then pick the smallest method that answers it') so the end-to-end workflow is explicit.

Dimension	Reasoning	Score
Conciseness	The 37-line body is lean and efficient: a compact methods table with sample sizes and timings, terse lists, and no padding or explanation of concepts Claude already knows. Every token is domain-specific signal, matching anchor 5.	5 / 5
Actionability	There are concrete specifics (5-8 participants, per-phase timings, named deliverables), but execution depth is missing: no example interview questions or probes, and analysis techniques like affinity mapping are named without any procedure for performing them. This sits between anchors 3 and 4, leaning 3 because key execution details are absent.	3 / 5
Workflow Clarity	The interview guide section is a clear timed sequence and sections loosely follow the research lifecycle, but there is no explicit end-to-end plan-then-execute-then-synthesize workflow and no checkpoints or decision guidance (e.g., how to pick a method from the table). Anchor 3: steps present but checkpoints implicit; no destructive/batch cap applies.	3 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into clear sections (methods, interview structure, analysis, deliverables). Per the rubric's simple-skill exception this scores 5.	5 / 5
	Total	16 / 20 Passed

Description

78%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 that clearly answers both what the skill does and when to use it, with natural trigger phrases and explicit trigger guidance. Its main weakness is specificity: the actions are lifecycle-generic rather than naming the concrete research activities it supports.

Suggestions

Replace or augment the generic verbs with concrete activities, e.g. "Design interview guides and surveys, run usability tests, and synthesize findings into themes and recommendations."

Add missing natural trigger synonyms such as "user interviews", "diary study", "card sorting", or "participant recruitment" to the trigger list.

Clarify what synthesis produces (e.g. themes, insights, prioritized recommendations) so the "what" is as concrete as the "when".

Dimension	Reasoning	Score
Specificity	"Plan, conduct, and synthesize user research" names the domain and lifecycle actions, but the verbs remain domain-generic without concrete sub-activities (interviews, surveys, usability sessions). It matches anchor 3 (domain plus limited concrete actions) rather than anchor 4, which expects several specific actions.	3 / 5
Completeness	It explicitly answers "what" (plan, conduct, synthesize user research) and "when" with concrete trigger phrases ("Trigger with ... or when the user needs help with any aspect of understanding their users through research"), matching anchor 5; the explicit trigger guidance means the missing-'Use when' cap does not apply.	5 / 5
Trigger Term Quality	Five natural trigger phrases ("user research plan", "interview guide", "usability test", "survey design", "research questions") plus a fallback clause give good coverage, but common synonyms like "user interviews", "diary study", or "card sorting" are missing — anchor 4, not the exhaustive synonym coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	"User research" is a clear niche with distinct triggers (interview guide, usability test), but "survey design" and "research questions" carry minor overlap risk with general research or academic-writing skills — anchor 4.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anthropics/knowledge-work-plugins
Path: design/skills/user-research/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.