本文へ移動
cccskills
無料GitHub で公開

prd-v04-persona-definition

Synthesize behavioral personas from prior stage evidence for journey mapping and marketing during PRD v0.4 User Journeys. Triggers on requests to define personas, create user profiles, identify target users, or when user asks "who are our users?", "define personas", "user profiles", "target users", "persona creation", "who uses this product?". Consumes CFD- (v0.1-v0.3), BR- (targeting from v0.3 Moat), FEA- (v0.3 Feature Value Planning). Outputs PER- entries with behavioral profiles and feature relationships. Feeds v0.4 User Journey Mapping.

インストール方法を見る

含まれるファイル(3)

  • SKILL.md9.5 KB
  • assets/per.md1.2 KB
  • references/examples.md2.8 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Persona Definition

Position in workflow: v0.3 Feature Value Planning → v0.4 Persona Definition → v0.4 User Journey Mapping

Personas are not demographic profiles—they are behavioral models synthesized from evidence. Every persona must trace back to CFD- research, BR- targeting rules, and FEA- features they care about.

Consumes

This skill requires prior work from v0.1-v0.3:

  • CFD-* problem statements and pain points (from v0.1 Problem Framing) — Behavioral signals about what users struggle with
  • CFD-* value hypotheses (from v0.1 User Value Articulation) — Evidence about what users want to accomplish
  • CFD-* competitive intelligence and segment gaps (from v0.2 Competitive Landscape) — Market segmentation and underserved signals
  • BR-* targeting rules (from v0.3 Moat Definition) — Constraints on which segments to pursue (switchers vs. new-to-category, etc.)
  • BR-* product type classification (from v0.2 Product Type Classification) — Determines which personas matter (Clone = feature parity users; Undercut = price-sensitive niche)
  • FEA-* entries (from v0.3 Features Value Planning) — Feature list to validate which features each persona cares about
  • MVP-SCOPE artifact (from v0.3 Features Value Planning) — The explicit list of features defining MVP; personas map to MVP feature set only

This skill assumes v0.1-v0.3 work is complete.

Produces

This skill creates/updates:

  • PER-* entries (persona definitions, confidence 2-3/5) — Behavioral profiles tied to CFD/BR/FEA evidence with acquisition channels and pricing sensitivity
  • Persona coverage artifact — Map of which personas are Primary/Secondary and which product type segments they represent

All PER- entries should include:

  • confidence: 2-3/5 (based on evidence tier from CFD interviews and BR targeting decisions)
  • Evidence source citations (CFD-ID references + BR-ID targeting rules)
  • Forward target: "Would move to 4/5 if we validate persona behaviors with 5+ actual customers"

Example PER- entry with confidence:

PER-001: The Overwhelmed Ops Manager
Source IDs: CFD-003 (pain: manual tracking), CFD-012 (value: automation), BR-041 (targeting: switchers at renewal)
Type: Primary
Confidence: 3/5 (source: 4-customer-interviews-jan-2026 + competitive-landscape confirms segment underserved)
Segment: SMB SaaS companies (10-50 employees)

Demographics:
  Role: Operations Manager / Head of Ops
  Context: Growing startup, wearing multiple hats, no dedicated tools budget
  Technical Level: Intermediate (comfortable with SaaS, not a developer)

Behavioral Profile:
  Goals: Reduce time spent on manual reporting (CFD-012)
  Frustrations: Current tools require too much setup (CFD-003)
  Decision Factors: Ease of use > feature count, must show ROI to CEO (CFD-025)
  Current Workflow: Spreadsheets + manual data entry + weekly report compilation

Product Relationship:
  Primary Value: CFD-012 ("Save 5 hours/week on reporting")
  Key Features: FEA-001 (auto-sync), FEA-003 (one-click reports), FEA-007 (dashboard) — all in MVP-SCOPE
  Pricing Sensitivity: BR-030 (SMB tier ≤$50/mo)
  Acquisition Channel: BR-041 (target at contract renewal of competing tools)

Marketing Hook: "Stop building reports. Start using them."
Next Target: "Would move to 4/5 if 5+ actual SMB ops managers validate this behavior in paid usage"

Core Constraint

Maximum 5 personas. Most products need 1-2.

If you have more than 3, you're likely over-segmenting by demographics instead of behavior. Consolidate ruthlessly.

Persona Types

TypeDefinitionWhen to Create
PrimaryCore user, drives most revenueAlways (at least 1)
SecondaryImportant but not primary buyerIf distinct needs exist
NegativeWho we explicitly excludeIf exclusion is strategic
AspirationalFuture target, not current focusOnly for roadmap planning

Rule: Primary personas must link to primary revenue KPI-. If a persona doesn't influence revenue, question whether it's truly primary.

Evidence Requirements

Every persona field must link to prior stage evidence:

Persona FieldMust Link ToSource Stage
GoalsCFD- value hypothesisv0.1 User Value Articulation
FrustrationsCFD- pain pointsv0.1 Problem Framing
Decision FactorsCFD- competitive researchv0.2 Competitive Landscape
Key FeaturesFEA- entriesv0.3 Feature Value Planning
Pricing SensitivityBR- pricing rulesv0.3 Pricing Model
Acquisition ChannelBR- targeting rulesv0.3 Moat Definition

No link = No claim. If you can't cite evidence, the attribute is assumption, not fact.

Synthesis Process

  1. Pull USER TYPE from v0.1 Problem Framing (CFD-)

    • These are your candidate personas
  2. Pull SEGMENTS from v0.2 Market Definition (CFD-, BR-)

    • How is the market divided? Which segments are we targeting?
  3. Pull TARGETING RULES from v0.3 Moat Definition (BR-)

    • New-to-category vs. Switchers? Trigger moments?
  4. Synthesize behavioral patterns from all CFD- evidence

    • What goals unite this segment?
    • What frustrations are consistent?
  5. Map FEA- features to each persona

    • Which features matter most to each?
    • This informs journey mapping
  6. Create PER- entries with full traceability

PER- Output Template

PER-XXX: [Persona Name]
Source IDs: [CFD-XXX, CFD-YYY, BR-ZZZ that inform this persona]
Type: [Primary | Secondary | Negative | Aspirational]
Segment: [From v0.2 market segment]

Demographics:
  Role: [Job title / function]
  Context: [Company size, industry, team structure]
  Technical Level: [Novice | Intermediate | Expert]

Behavioral Profile:
  Goals: [What they're trying to achieve — link to CFD- value]
  Frustrations: [Current pain points — link to CFD- pain]
  Decision Factors: [What influences their choices — link to CFD- research]
  Current Workflow: [How they solve this today]

Product Relationship:
  Primary Value: [CFD- value hypothesis they care about most]
  Key Features: [FEA-XXX, FEA-YYY most relevant to them]
  Pricing Sensitivity: [From BR- pricing rules]
  Acquisition Channel: [How they'll find us — from BR- targeting]

Marketing Hook: [One-sentence pitch for this persona]

Example PER- entry:

PER-001: The Overwhelmed Ops Manager
Source IDs: CFD-003 (pain: manual tracking), CFD-012 (value: automation), BR-041 (target: switchers at renewal)
Type: Primary
Segment: SMB SaaS companies (10-50 employees)

Demographics:
  Role: Operations Manager / Head of Ops
  Context: Growing startup, wearing multiple hats, no dedicated tools budget
  Technical Level: Intermediate (comfortable with SaaS, not a developer)

Behavioral Profile:
  Goals: Reduce time spent on manual reporting (CFD-012)
  Frustrations: Current tools require too much setup (CFD-003)
  Decision Factors: Ease of use > feature count, must show ROI to CEO (CFD-025)
  Current Workflow: Spreadsheets + manual data entry + weekly report compilation

Product Relationship:
  Primary Value: CFD-012 ("Save 5 hours/week on reporting")
  Key Features: FEA-001 (auto-sync), FEA-003 (one-click reports), FEA-007 (dashboard)
  Pricing Sensitivity: BR-030 (SMB tier ≤$50/mo)
  Acquisition Channel: BR-041 (target at contract renewal of competing tools)

Marketing Hook: "Stop building reports. Start using them."

Anti-Patterns to Avoid

Anti-PatternSignalFix
Persona explosion>5 personasConsolidate by behavior, not demographics
Fictional personasNo CFD- linksEvery attribute needs evidence
Demographic-only"25-35 year old male"Focus on behaviors and goals
All personas are primary"Everyone is important"Rank by revenue potential
Copy-paste from competitorsGeneric descriptionsGround in YOUR research
Features without personasPersonas created but no FEA- linksMap features to who cares

Quality Gates

Before proceeding to User Journey Mapping:

  • Maximum 5 personas (ideally 1-3)
  • At least one Primary persona defined
  • Every persona has CFD- evidence links
  • Key Features mapped from FEA- entries
  • Acquisition Channel specified from BR- targeting
  • Marketing Hook is specific and testable

Downstream Connections

PER- entries feed into:

ConsumerWhat It UsesExample
v0.4 User Journey MappingEach UJ- references a PER-UJ-001 is for PER-001
v0.4 Screen Flow DefinitionPersona context shapes UISCR-001 optimized for PER-001 tech level
v0.9 GTMMarketing messaging per personaCampaign targeting PER-002 segment
Sales EnablementPersona-specific pitchesDiscovery questions per PER-

Detailed References

  • Persona creation examples: See references/examples.md
  • PER- entry template: See assets/per.md

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py). Returns a graduated PASS / WARN / BLOCK verdict with top blockers and their causal chain. Triggers before advancing from v0.X to v0.Y or explicit `/ghm-gate-check`.

日本語の概要は準備中です。原文の説明を表示しています。

mattgierhart/PRD-driven-context-engineering1812026年8月31日 更新

Extracts durable insights from temp/ files to SoT during EPIC Phase E. Triggers at EPIC completion or explicit `/ghm-harvest` invocation. Outputs new SoT entries and archive manifest.

日本語の概要は準備中です。原文の説明を表示しています。

mattgierhart/PRD-driven-context-engineering1812026年8月31日 更新

Validates and registers new SoT IDs with cross-reference integrity. Triggers when creating BR-XXX, UJ-XXX, API-XXX, or CFD-XXX entries. Outputs formatted SoT entry with validated cross-references.

日本語の概要は準備中です。原文の説明を表示しています。

mattgierhart/PRD-driven-context-engineering1812026年8月31日 更新

Install the PRD-Driven Context Engineering methodology into a fresh OR existing repository — the subscription-native alternative to forking the whole repo. Runs an interactive wizard that seeds the framework (.claude/ hooks, skills, agents, rules, scripts) without clobbering product content. Triggers on "install the methodology", "adopt this into my repo", "self-install", "set up PRD lifecycle here", "onboard existing project". Outputs an installed framework + a verification report.

日本語の概要は準備中です。原文の説明を表示しています。

mattgierhart/PRD-driven-context-engineering1812026年8月31日 更新

Creates new Source of Truth (SoT) files when existing templates don't fit your needs. Triggers on requests to create a new SoT file, add a new artifact type, or when user says "I need to track [X] but there's no SoT for it", "create SoT", "new source of truth". Outputs a properly structured SoT.*.md file with ID prefix, frontmatter, and update protocol.

日本語の概要は準備中です。原文の説明を表示しています。

mattgierhart/PRD-driven-context-engineering1812026年8月31日 更新

Synchronizes README.md Command Center with current project state. Triggers on gate changes, EPIC status changes, or explicit `/ghm-status-sync` invocation. Outputs updated README.md dashboard with current lifecycle stage, blockers, and metrics.

日本語の概要は準備中です。原文の説明を表示しています。

mattgierhart/PRD-driven-context-engineering1812026年8月31日 更新

mattgierhart のスキルをすべて見る

このスキルの問題を報告する