im-shashanks/claude-plugins / shaktra/skills/shaktra-pm
shaktra-pm
VerifiedProduct Manager workflow — PRD creation, user research analysis, persona generation, journey mapping, and feature prioritization. Entry point for product definition work.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.1 KB |
| agent-prompts.md | markdown | 3.4 KB |
| brainstorm-workflow.md | markdown | 4.9 KB |
| full-workflow-hypothesis.md | markdown | 5.0 KB |
| full-workflow-research.md | markdown | 4.8 KB |
| full-workflow.md | markdown | 3.0 KB |
| guided-entry.md | markdown | 5.5 KB |
| journey-workflow.md | markdown | 4.9 KB |
| persona-workflow.md | markdown | 4.0 KB |
| prd-workflow.md | markdown | 5.7 KB |
| prioritization-workflow.md | markdown | 5.6 KB |
| research-workflow.md | markdown | 5.2 KB |
| templates/prd-one-page.md | markdown | 1.7 KB |
| templates/prd-standard.md | markdown | 3.5 KB |
persona-workflow.md
View on GitHub# Persona Generation Workflow
Create evidence-based user personas from PRD user descriptions and research findings. Personas ground requirements in real user needs and enable traceability.
## Overview
Personas are generated by:
1. Identifying user segments from PRD
2. Enriching with research evidence (if available)
3. Defining JTBD, goals, frustrations
4. Validating evidence thresholds
---
## Steps
### Step 1 — Load Context
Read:
- `.shaktra/settings.yml` — project context
- `.shaktra/prd.md` — primary source for user segments (required)
- `.shaktra/research/synthesis.yml` — research evidence (if exists)
- `.shaktra/research/*.yml` — individual interviews for quotes
### Step 2 — Identify User Segments
Extract user segments from PRD:
- Section 2 (Users & Personas) defines target users
- Each segment becomes a candidate persona
If PRD has no user section:
- Ask user: "Who are the primary users of this product?"
- Capture at least: role, segment, key characteristic
### Step 3 — Generate Personas
For each user segment, spawn **product-manager** (mode: persona-create):
**Required fields:**
```yaml
id: P-001
name: "<Archetype Name — e.g., 'Power User Paula'>"
role: "<job title or user type>"
segment: "<user segment — enterprise, prosumer, casual>"
goals:
- "<what they want to achieve>"
- "<second goal>"
frustrations:
- "<current pain point>"
- "<second frustration>"
behaviors:
- "<how they currently work>"
- "<second behavior>"
jobs_to_be_done:
- situation: "When I..."
motivation: "I want to..."
outcome: "So I can..."
evidence:
- type: interview | analytics | survey | observation
id: "<reference ID>"
insight: "<what this source contributed>"
```
**Evidence sourcing:**
- If research exists: link to specific interviews, quotes, findings
- If no research: use PRD descriptions, mark as `type: assumption`
- Minimum 2 evidence entries required
### Step 4 — Enrich from Research
If `.shaktra/research/synthesis.yml` exists:
1. Match themes to personas by user segment
2. Add specific pain points as frustrations
3. Add JTBD patterns from interviews
4. Include verbatim quotes where powerful
5. Link evidence IDs
### Step 5 — Validate Personas
For each persona, verify:
| Check | Required | Severity |
|---|---|---|
| At least 2 evidence entries | Yes | P0 |
| At least 1 JTBD | Yes | P0 |
| Goals has min 2 entries | Yes | P1 |
| Frustrations has min 2 entries | Yes | P1 |
| Evidence IDs reference existing sources | Yes | P1 |
If validation fails:
- For missing evidence: ask user for additional input or accept with warning
- For missing fields: prompt user to provide
### Step 6 — Write Personas
Write each persona to `.shaktra/personas/{persona_id}.yml`.
Create directory if needed: `.shaktra/personas/`
### Step 7 — Present Summary
```
## Personas Created
**Total:** {count} personas
### Personas
| ID | Name | Segment | Evidence |
|---|---|---|---|
| P-001 | {name} | {segment} | {count} sources |
### Evidence Coverage
- Research-backed: {count} personas with interview evidence
- Assumption-based: {count} personas without research
### Top Jobs-to-be-Done
1. "{JTBD from primary persona}"
2. "{JTBD from secondary persona}"
### Files Created
- .shaktra/personas/P-001.yml
- .shaktra/personas/P-002.yml
### Next Steps
1. Run `/shaktra:pm journey` to create journey maps for each persona
2. Reference personas in PRD requirements: `/shaktra:pm prd`
3. If evidence is thin, gather more research: `/shaktra:pm research`
```
EMIT `PERSONAS_COMPLETE`
---
## Quality Tiers
Based on evidence quality:
| Tier | Evidence | Confidence |
|---|---|---|
| **Validated** | 3+ interview sources | High — use for Must Have requirements |
| **Supported** | 1-2 sources | Medium — use for Should Have requirements |
| **Hypothetical** | Assumptions only | Low — validate before major investment |
Mark each persona's evidence tier in the output summary.
---
## Persona Maintenance
Personas are living documents:
- Update when new research becomes available
- Increment version, add new evidence
- Archive superseded versions
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |