Skip to content

im-shashanks/claude-plugins / shaktra/skills/shaktra-reference

shaktra-reference

Verified

Shared constants, quality standards, and state schemas for all Shaktra agents. Defines severity taxonomy, quality principles, guard tokens, review dimensions, and YAML schemas.

---
name: shaktra-reference
description: >
  Shared constants, quality standards, and state schemas for all Shaktra agents. Defines severity
  taxonomy, quality principles, guard tokens, review dimensions, and YAML schemas.
user-invocable: false
---

# Shaktra Reference — Single Source of Truth

This skill contains canonical definitions for the Shaktra framework. No other file may redefine the constants, taxonomies, or standards declared here. Agents and skills reference these files — they never duplicate them.

## Loading

Agents load this skill via their `skills` frontmatter. Story-related schemas (story-schema, story-tiers, sprint-schema) live in `shaktra-stories`. All other schemas and quality references live here.

## Sub-Files

| File | Purpose |
|---|---|
| `severity-taxonomy.md` | P0-P3 severity levels, examples, merge gate logic |
| `quality-principles.md` | 10 core principles with verification checks |
| `guard-tokens.md` | 14 core tokens for phase/quality/workflow signaling (domain skills define additional tokens) |
| `quality-dimensions.md` | 13 review dimensions (A-M) with key checks and P0 triggers |
| `schemas/handoff-schema.md` | TDD state machine — phases, transitions, validation rules |
| `schemas/settings-schema.md` | Framework config — types, defaults, consumer reference |
| `schemas/principles-schema.md` | Principles store — synthesized from observations, 14 categories, confidence lifecycle |
| `schemas/observations-schema.md` | Per-story observations — agent-written during workflow execution |
| `schemas/anti-patterns-schema.md` | Anti-patterns — failure patterns with recommended alternatives |
| `schemas/procedures-schema.md` | Procedures — workflow-level adaptation learnings |
| `schemas/briefing-schema.md` | Story briefings — filtered view of long-term knowledge |
| `schemas/design-doc-schema.md` | Design doc sections — tier-scaled structure |
| `schemas/refactoring-handoff-schema.md` | Refactoring state machine — phases, transitions, baseline metrics |
| `schemas/prd-schema.md` | PRD validation — required sections, quality checks |
| `schemas/persona-schema.md` | Persona YAML — fields, evidence requirements |
| `schemas/journey-schema.md` | Journey map YAML — stages, touchpoints, opportunities |
| `schemas/research-schema.md` | Research synthesis YAML — themes, patterns, recommendations |
| `schemas/analysis-manifest-schema.md` | Analysis checkpoint — dimension progress, resumability, status transitions |

**Moved to `shaktra-stories`:** story-schema.md, story-tiers.md, sprint-schema.md — loaded by agents that work with stories and sprints.

## Agent Loading Guide

| Agent Role | From shaktra-reference | From shaktra-stories |
|---|---|---|
| SW Quality | severity-taxonomy, quality-principles, quality-dimensions, schemas/handoff-schema, schemas/principles-schema | — |
| CR Analyzer | severity-taxonomy, quality-principles, quality-dimensions | — |
| SW Engineer, Developer | severity-taxonomy, quality-principles, guard-tokens, schemas/handoff-schema | story-schema, story-tiers |
| Test Agent | severity-taxonomy, guard-tokens, schemas/handoff-schema | — |
| TPM Quality | severity-taxonomy, quality-dimensions, guard-tokens, schemas/design-doc-schema | story-schema, story-tiers |
| Scrum Master | — | story-schema, story-tiers, sprint-schema |
| Architect | quality-principles, quality-dimensions, schemas/design-doc-schema | — |
| Memory Curator | schemas/principles-schema, schemas/observations-schema, schemas/anti-patterns-schema, schemas/procedures-schema, schemas/handoff-schema | — |
| Bug Diagnostician | severity-taxonomy, guard-tokens | story-schema |
| CBA Analyzer | quality-principles, schemas/principles-schema, schemas/analysis-manifest-schema | — |
| Product Manager | schemas/principles-schema, schemas/prd-schema, schemas/persona-schema, schemas/journey-schema, schemas/research-schema | story-schema, story-tiers, sprint-schema |

**Note:** Memory Curator also loads the `shaktra-memory` skill for consolidation algorithms.
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall