im-shashanks/claude-plugins / shaktra/skills/shaktra-reference
shaktra-reference
VerifiedShared constants, quality standards, and state schemas for all Shaktra agents. Defines severity taxonomy, quality principles, guard tokens, review dimensions, and YAML schemas.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.0 KB |
| guard-tokens.md | markdown | 3.0 KB |
| quality-dimensions.md | markdown | 4.0 KB |
| quality-principles.md | markdown | 3.9 KB |
| schemas/analysis-manifest-schema.md | markdown | 2.8 KB |
| schemas/anti-patterns-schema.md | markdown | 1.6 KB |
| schemas/briefing-schema.md | markdown | 2.9 KB |
| schemas/design-doc-schema.md | markdown | 4.9 KB |
| schemas/handoff-schema.md | markdown | 4.2 KB |
| schemas/journey-schema.md | markdown | 3.4 KB |
| schemas/observations-schema.md | markdown | 1.7 KB |
| schemas/persona-schema.md | markdown | 2.8 KB |
| schemas/prd-schema.md | markdown | 3.3 KB |
| schemas/principles-schema.md | markdown | 2.3 KB |
| schemas/procedures-schema.md | markdown | 1.7 KB |
| schemas/refactoring-handoff-schema.md | markdown | 2.4 KB |
| schemas/research-schema.md | markdown | 3.7 KB |
| schemas/settings-schema.md | markdown | 7.7 KB |
| severity-taxonomy.md | markdown | 3.2 KB |
schemas/persona-schema.md
View on GitHub# Persona Schema
Defines the structure of user personas in `.shaktra/personas/`. Personas ground requirements in real user needs and enable traceability from research to PRD to stories.
## Schema
```yaml
# .shaktra/personas/{persona_id}.yml
id: string # required — unique identifier (e.g., "P-001")
name: string # required — archetype name (e.g., "Power User Paula")
role: string # required — job title or user type
segment: string # required — user segment (e.g., "enterprise", "prosumer", "casual")
demographics:
age_range: string # optional — e.g., "25-35"
location: string # optional — geographic context
tech_savviness: string # optional — "low" | "medium" | "high"
goals: # required — what they want to achieve (min 2)
- string
frustrations: # required — current pain points (min 2)
- string
behaviors: # required — how they currently work (min 2)
- string
jobs_to_be_done: # required — JTBD format (min 1)
- situation: string # "When I..."
motivation: string # "I want to..."
outcome: string # "So I can..."
evidence: # required — sources that informed this persona
- type: string # "interview" | "analytics" | "survey" | "support_ticket" | "observation"
id: string # reference ID (e.g., "INT-003", "analytics-q4-2024")
insight: string # what this source contributed
quote: string # optional — representative verbatim quote
created: date # required — ISO date
updated: date # required — last modification date
```
## Evidence Requirements
Personas must be grounded in real data, not assumptions:
| Evidence Type | Minimum Count | Notes |
|---|---|---|
| Interview | 1+ | Reference `.shaktra/research/` entries |
| Analytics | 0+ | Quantitative behavior patterns |
| Survey | 0+ | Self-reported preferences |
| Support ticket | 0+ | Real pain points from support |
| Observation | 0+ | Direct user observation |
**Total evidence entries:** Minimum 2 from any combination.
## JTBD Format
Jobs-to-be-Done follow the standard structure:
> "When [situation], I want to [motivation], so I can [outcome]."
Example:
```yaml
jobs_to_be_done:
- situation: "When I'm reviewing code at 2am before a release"
motivation: "I want to quickly identify security issues"
outcome: "So I can ship confidently without staying up longer"
```
## Validation Rules
| Rule | Severity |
|---|---|
| At least 2 evidence entries | P0 |
| At least 1 job-to-be-done | P0 |
| Goals and frustrations each have min 2 entries | P1 |
| All interview evidence IDs exist in `.shaktra/research/` | P1 |
## Storage
Personas are stored as individual YAML files: `.shaktra/personas/{persona_id}.yml`
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |