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/research-schema.md
View on GitHub# Research Schema
Defines the structure of customer research artifacts in `.shaktra/research/`. Research feeds into personas, validates requirements, and provides evidence for product decisions.
## Interview Analysis Schema
```yaml
# .shaktra/research/{interview_id}.yml
id: string # required — unique identifier (e.g., "INT-001")
type: interview # required — "interview" | "survey" | "observation"
date: date # required — when conducted
participant:
role: string # required — job title or user type
segment: string # required — user segment
anonymized_id: string # required — anonymous identifier (e.g., "P12")
pain_points: # required — problems they described (min 1)
- id: string # unique within interview (e.g., "PP-01")
description: string # what hurts
severity: string # "high" | "medium" | "low"
frequency: string # "daily" | "weekly" | "monthly" | "rarely"
quote: string # verbatim quote if available
feature_requests: # optional — explicit asks
- id: string
description: string
priority: string # participant's stated priority
context: string # why they want it
jobs_to_be_done: # required — observed JTBD patterns (min 1)
- situation: string
motivation: string
outcome: string
current_solution: string # how they solve it today
competitor_mentions: # optional
- name: string
context: string # what they said about it
sentiment: string # "positive" | "negative" | "neutral"
key_quotes: # required — notable verbatim quotes (min 2)
- quote: string
context: string
theme: string # which theme this supports
notes: string # optional — analyst notes
```
## Research Synthesis Schema
```yaml
# .shaktra/research/synthesis.yml
id: string # required — synthesis identifier
created: date # required
updated: date # required
interview_ids: # required — which interviews inform this synthesis
- string
themes: # required — recurring patterns (min 2)
- id: string # e.g., "TH-01"
name: string # short theme name
description: string # what the theme represents
evidence_count: integer # how many interviews support it
confidence: string # "high" | "medium" | "low"
supporting_interviews:
- id: string
pain_point_id: string # reference to specific finding
patterns: # required — behavioral patterns observed
- name: string
description: string
frequency: string # "common" | "occasional" | "rare"
evidence:
- interview_id: string
observation: string
recommendations: # required — actionable insights (min 1)
- id: string # e.g., "REC-01"
recommendation: string
rationale: string
priority: string # "high" | "medium" | "low"
supporting_themes:
- string # theme IDs
confidence: string
gaps: # optional — areas needing more research
- area: string
reason: string
suggested_method: string
```
## Confidence Levels
| Level | Criteria |
|---|---|
| **High** | 3+ interviews with consistent findings |
| **Medium** | 2 interviews with aligned findings |
| **Low** | 1 interview or conflicting findings |
## Validation Rules
| Rule | Severity |
|---|---|
| Each interview has at least 1 pain point | P0 |
| Each interview has at least 1 JTBD | P0 |
| Synthesis has at least 2 themes | P0 |
| All theme evidence IDs reference existing interviews | P1 |
| Confidence levels match evidence count criteria | P1 |
## Storage
- Individual interviews: `.shaktra/research/{interview_id}.yml`
- Synthesis: `.shaktra/research/synthesis.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 |