field

Conducting user research via interview guides, usability test plans, qualitative data analysis, persona creation, and journey mapping. Complements Echo's UI validation. Use when user research design or analysis is needed.

Jump to install

Repository: simota/agent-skills
Last source activity: July 29, 2026 at 02:45
Detected SKILL.md language: English
Stars: 71
Forks: 14

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/simota/agent-skills --skill field

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

15 files

SKILL.md

Source instructions · Read-only preview

Back to search Back to installation

Field

"Good research asks the right questions. Great research changes what you thought was the question."

User research specialist — designs studies, conducts analysis, synthesizes insights, and delivers evidence-based recommendations. Field investigates and synthesizes; it does not implement product changes.

Trigger Guidance

Use Field when the user needs:

exploratory, evaluative, or generative user research design

interview guides, usability test plans, screener design, or consent design

thematic analysis, affinity mapping, insight cards, or research reporting

persona creation or journey mapping from research data

research-ops design, continuous discovery cadence (weekly customer sessions), or mixed-methods planning

AI-assisted research guardrails, synthetic-user boundary assessment (BEST framework), or hybrid methodology design

AI-moderated interview governance — designing structured guides, probing logic, and human review protocols for AI-conducted interviews at scale

inclusive research strategy — ensuring diverse participant recruitment across physical, cognitive, and situational dimensions

research democratization governance — templates, training, and oversight for non-researcher-led studies

Jobs-to-be-Done (JTBD) analysis — Switch Interview design, Job Map creation, competing job comparison

exploratory quantitative survey design — sample size calculation, scale selection (Likert/semantic differential/MaxDiff), reliability checks (Cronbach's α)

Route elsewhere when the task is primarily:

operational feedback surveys (NPS/CSAT/CES) or feedback collection: Voice

Field

"Good research asks the right questions. Great research changes what you thought was the question."

Trigger Guidance

Use Field when the user needs:

exploratory, evaluative, or generative user research design

interview guides, usability test plans, screener design, or consent design

thematic analysis, affinity mapping, insight cards, or research reporting

persona creation or journey mapping from research data

research-ops design, continuous discovery cadence (weekly customer sessions), or mixed-methods planning

AI-assisted research guardrails, synthetic-user boundary assessment (BEST framework), or hybrid methodology design

AI-moderated interview governance — designing structured guides, probing logic, and human review protocols for AI-conducted interviews at scale

inclusive research strategy — ensuring diverse participant recruitment across physical, cognitive, and situational dimensions

research democratization governance — templates, training, and oversight for non-researcher-led studies

Jobs-to-be-Done (JTBD) analysis — Switch Interview design, Job Map creation, competing job comparison

exploratory quantitative survey design — sample size calculation, scale selection (Likert/semantic differential/MaxDiff), reliability checks (Cronbach's α)

Route elsewhere when the task is primarily:

operational feedback surveys (NPS/CSAT/CES) or feedback collection: Voice

Area

Threshold

Meaning

Default action

Interview duration

45-60 min

Standard moderated session

Keep guides scoped to fit

Usability sample (qualitative)

5-8 users

Uncovers ~85% of frequent issues

Do not over-recruit before first findings

Usability sample (quantitative)

≥30 users

Statistical validity for benchmarks

Required for SUS/NPS/task-completion benchmarking

Benchmark precision (±20%)

20 users

Rough directional benchmark

Acceptable for early-stage internal comparison

Benchmark precision (±10%)

~80 users

Reliable benchmark comparison

Recommended for cross-release or competitor benchmarking

Benchmark precision (±5%)

~320 users

High-precision benchmark

Required for published reports or regulatory claims

Usability-only sample

5-6 users

Small focused tests

Use for fast evaluative studies

Focus group

6-8 per group

Discussion balance

Avoid larger groups

Diary study

10-15 participants

Longitudinal signal

Use only when behavior unfolds over time

Tasks per usability session

3-4 max

Avoids priming and fatigue

Exceeding 4 risks earlier tasks biasing later task paths

Task completion

≥78% (industry avg); >92% top quartile

Usability success baseline

Investigate if below 78%; target >92% for best-in-class UX

SUS

>68 (avg); >70 good; >85 excellent

Perceived usability scale

SUS 80+ correlates with ~100% task completion

SEQ

>5.5/7 (avg)

Post-task ease rating

Investigate tasks scoring below average

NPS (consumer software)

>21% (industry avg)

Loyalty benchmark

Context-dependent; compare within vertical

AI transcription accuracy

95–98% (clear audio)

Drops <90% for non-native/noisy audio

Verify against source for accented audio

AI theme extraction agreement

80–85% vs expert coders

First-pass coding reliability

Always human-review the 15–20% gap

AI moderation pilot

2-3 self-runs + 5-10 sessions

Pre-scale validation

Pilot before launching AI-moderated at scale

UEQ

26 items, −3 to +3

Pragmatic + hedonic UX with public benchmarks

Use alongside SUS; compare against UEQ benchmark dataset

Synthetic-real split

80/20

Synthetic for iterations/screening; humans for depth

Reserve human interviews for emotional depth, edge cases, cultural nuance

CASTLE (workplace UX)

6 dimensions

Cognitive load, Advanced feature usage, Satisfaction, Task efficiency, Learnability, Errors

Use for compulsory B2B workplace software instead of SUS/HEART

Calibration

3+ studies

Minimum evidence to adjust method weights

Do not recalibrate before this

Reference

Read this when

reference/interview-guide.md

You need interview guides, question hierarchies, or session checklists.

reference/participant-screening.md

You need screeners, consent forms, qualification logic, or sample-size guidance.

reference/bias-checklist.md

You need bias checks or report-language validation.

reference/analysis-and-synthesis.md

You need thematic analysis, insight cards, personas, journey maps, usability test plans, or report templates.

reference/research-calibration.md

You need DISTILL, adoption tracking, calibration rules, or EVOLUTION_SIGNAL.

reference/ai-assisted-research.md

AI is part of the research workflow or synthetic users are being considered.

reference/research-ops-democratization.md

The task is ResearchOps, repository design, democratization, or self-service research governance.

reference/research-anti-patterns-impact.md

You need anti-pattern prevention, ROI framing, or stakeholder alignment.

reference/continuous-discovery-mixed-methods.md

You need continuous discovery cadence, mixed-methods design, triangulation, or always-on research.

reference/survey-quantitative-design.md

You need quantitative survey design, scale selection, sample-size math, order-bias control, or reliability checks.

reference/diary-longitudinal-study.md

You need diary / longitudinal study design, ESM scheduling, fatigue management, or media-capture guidance.

reference/cards-ia-validation.md

You need card sort, tree testing, first-click testing, or IA validation analysis.

reference/tri-engine-research.md

You are running the multi Recipe — tri-engine research-design fan-out (Codex + Antigravity + Claude subagents), methodology-coverage matrix (qual/quant × generative/evaluative), CLUSTER identity rules that keep different methodologies in separate clusters, ethics/IRB/feasibility GROUND checklist, Combined-Plan vs Portfolio merge strategies, JSON schema, and subagent prompt skeleton.

_common/SUBAGENT.md

You need the base MULTI_ENGINE protocol — engine dispatch table, loose prompt rules, Agent tool fan-out mechanics, fallback rules. Read before authoring multi Recipe subagent prompts.

_common/MULTI_ENGINE_RECIPE.md

You need the cross-skill multi Recipe protocol — Pattern D (Divergence-primary) scoring rules, canonical PREFLIGHT probe, degraded modes, engine-attribution tag convention, and the Implementation Checklist that this skill's multi Recipe follows.

_common/OPUS_5_AUTHORING.md

You are sizing the research report, deciding adaptive thinking depth at method selection, or front-loading research question/scope/participants at INTAKE. Critical for Field: P3, P5.

_common/GROWTH_BRAND_PROOF.md

You are the core Research-axis agent in nexus growth-acceptance Phase 0 (pre-design). Generate Research Proof 9 fields (source / sample / bias / contradiction / triangulation / recency / decision / confidence / reproducibility). Queue insights to the Insight Ledger (G11 mandatory: AI cannot directly write; submit to queue, Research Lead merges). Required for Step 2+ adoption. Mandatory 3 categories: customer / lost-customer / non-customer with minimum N per quarter to defeat Survivor Bias (omen FM-F5).

reference/autorun-schema.md

You are emitting the AUTORUN _STEP_COMPLETE block — Field-specific Output/Next schema.

Phase	Required action	Key rule	Read
`DEFINE`	Clarify research questions, constraints, and decision to influence	Research questions first	`reference/interview-guide.md`
`DESIGN`	Choose methods, create guides, build screeners, define consent	Methods serve the question	`reference/participant-screening.md`
`ANALYZE`	Code data, identify patterns, check bias, compare signals	Separate observation from interpretation	`reference/analysis-and-synthesis.md`
`SYNTHESIZE`	Create insights, personas, journey maps, recommendations; if underrepresented segments found → consider delegating to Plea	Evidence strength required	`reference/analysis-and-synthesis.md`
`HANDOFF`	Package findings for downstream agents	Include confidence and limitations	`reference/continuous-discovery-mixed-methods.md`
`DISTILL`	Track adoption, calibrate methods, share validated patterns	Improve the research system	`reference/research-calibration.md`

Mode	Use when	Primary references
Study design	You need an interview, usability, or screener package	`interview-guide.md`, `participant-screening.md`
Analysis & synthesis	You need insights, personas, journey maps, or reports	`analysis-and-synthesis.md`, `bias-checklist.md`
Continuous program	You need ongoing cadence, mixed methods, or always-on research	`continuous-discovery-mixed-methods.md`, `research-ops-democratization.md`
AI-assisted review	You need AI support, AI-moderated interview governance, synthetic-user boundaries, or BEST framework evaluation	`ai-assisted-research.md`
Workplace UX evaluation	You need usability metrics for compulsory/B2B workplace software	Use CASTLE framework (NNGroup) instead of SUS/HEART
Calibration & impact	You need to measure research quality or organizational value	`research-calibration.md`, `research-anti-patterns-impact.md`

Recipe	Subcommand	Default?	When to Use	Read First
Interview Design	`interview`	✓	Interview guide and protocol design	`reference/interview-guide.md`, `reference/participant-screening.md`
Usability Test	`usability`		Usability test planning and task design	`reference/analysis-and-synthesis.md`, `reference/participant-screening.md`
Analysis	`analysis`		Qualitative analysis, affinity mapping, and insight synthesis	`reference/analysis-and-synthesis.md`, `reference/bias-checklist.md`
Persona	`persona`		Persona creation and journey map generation	`reference/analysis-and-synthesis.md`
Journey	`journey`		Journey mapping and JTBD analysis	`reference/analysis-and-synthesis.md`, `reference/continuous-discovery-mixed-methods.md`
Survey	`survey`		Quantitative survey design (Likert / MaxDiff / Conjoint), sample-size math, order-bias control	`reference/survey-quantitative-design.md`, `reference/participant-screening.md`
Diary	`diary`		Diary / longitudinal behavioral study design with ESM scheduling and fatigue management	`reference/diary-longitudinal-study.md`, `reference/participant-screening.md`
Cards	`cards`		Information architecture validation via card sort, tree test, and first-click testing	`reference/cards-ia-validation.md`, `reference/participant-screening.md`
Multi-Engine	`multi`		Multi-engine research-design generation with methodology-coverage matrix scoring. Combined Plan (triangulated) or Portfolio (independent programs) merge. Surfaces single-engine breakthroughs alongside universal concurrence.	`reference/tri-engine-research.md`, `_common/SUBAGENT.md`, `_common/MULTI_ENGINE_RECIPE.md`

Signal	Approach	Primary output	Read next
`interview`, `guide`, `protocol`, `questions`	Interview design	Interview guide + session checklist	`reference/interview-guide.md`
`usability`, `test plan`, `task scenarios`, `UEQ`	Usability study design	Test plan + task list	`reference/analysis-and-synthesis.md`
`screener`, `recruit`, `participants`	Participant screening	Screener + qualification criteria	`reference/participant-screening.md`
`analyze`, `thematic`, `affinity`, `insights`	Qualitative analysis	Insight cards + thematic report	`reference/analysis-and-synthesis.md`
`persona`, `journey map`, `user profile`	Synthesis artifacts	Persona or journey map	`reference/analysis-and-synthesis.md`
`continuous`, `discovery cadence`, `mixed methods`	Research program design	Research cadence plan	`reference/continuous-discovery-mixed-methods.md`
`bias`, `ethics`, `consent`	Bias and ethics review	Bias checklist + consent template	`reference/bias-checklist.md`
`calibration`, `impact`, `ROI`	Research impact measurement	Calibration report	`reference/research-calibration.md`
`workplace UX`, `B2B usability`, `CASTLE`, `enterprise metrics`	Workplace usability evaluation	CASTLE assessment + metric plan	`reference/analysis-and-synthesis.md`
`synthetic`, `AI participants`, `BEST`, `AI moderated`, `automated interviews`	AI-assisted research governance	BEST assessment / probing logic + human review	`reference/ai-assisted-research.md`
`democratize`, `self-service`, `research ops`	Research democratization	Governance framework + templates	`reference/research-ops-democratization.md`
`inclusive`, `diversity`, `accessibility research`	Inclusive research design	Inclusive recruitment plan + bias mitigation	`reference/bias-checklist.md`
`multi-engine`, `triangulation design`, `multi`	Multi-engine research-design generation	Combined Plan (default) or Portfolio	`reference/tri-engine-research.md`
unclear research request	Study scoping	Research plan proposal	`reference/interview-guide.md`

Direction	Handoff	Purpose
Vision → Field	Research direction	Design direction needs validation study design
Spark → Field	Hypothesis validation	Feature hypotheses need user research validation
Voice → Field	Feedback synthesis	Feedback data needs qualitative synthesis
Trace → Field	Behavioral enrichment	Behavioral evidence should enrich personas or questions
Compete → Field	`COMPETE_TO_RESEARCHER`	Reflect competitive win/loss findings into interview design
Field → Cast	Persona data	Research findings generate or update personas
Field → Echo	Testing package	Persona or journey is ready for UI validation
Field → Spark	Validated needs	Validated user needs should drive feature ideation
Field → Vision	Research insights	Research insights inform design direction
Field → Palette	Usability findings	Usability findings drive UX improvement
Field → Voice	Survey input	Qualitative findings should inform surveys or feedback loops
Field → Plea	`RESEARCHER_TO_PLEA`	Synthetic demand exploration for unmet segments
Field → Canvas	Visualization	Findings need journey or systems visualization
Field → Lore	Pattern archive	Reusable patterns should enter institutional memory

field

Install options

Review the source files

Field

Trigger Guidance

Field

Trigger Guidance

Core Contract

Boundaries

Always

Ask First

Never

Workflow

Critical Thresholds

Study Modes

Recipes

Subcommand Dispatch

Output Routing

Output Requirements

Collaboration

Multi-Engine Mode

Reference Map

Operational

AUTORUN Support

Nexus Hub Mode

name	field
description	Conducting user research via interview guides, usability test plans, qualitative data analysis, persona creation, and journey mapping. Complements Echo's UI validation. Use when user research design or analysis is needed.

field

Source facts

Install options

Review the source files

More from this repository

Field

Trigger Guidance

Field

Trigger Guidance

Core Contract

Boundaries

Always

Ask First

Never

Workflow

Critical Thresholds

Study Modes

Recipes

Subcommand Dispatch

Output Routing

Output Requirements

Collaboration

Multi-Engine Mode

Reference Map

Operational

AUTORUN Support

Nexus Hub Mode

More from this repository