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.

schemas/procedures-schema.md

View on GitHub
# Procedures Schema

Defines `.shaktra/memory/procedures.yml` — workflow-level learnings that inform orchestration and process adaptation.

## Schema

```yaml
procedures:
  - id: string           # "PC-001" — sequential
    text: string         # workflow-level learning (1-3 sentences)
    confidence: float    # 0.2-1.0
    source_count: integer # number of supporting observations
    tags: [string]
    roles: [string]      # typically "sdm" for orchestrator-level
    applies_to: [string] # workflow types: "tdd" | "review" | "analysis" | "bugfix" | "tpm" | "pm" | "general"
    scope: string        # "project" | "universal"
    status: string       # "active" | "archived"
    source: string       # story_id where first observed
    created: string      # ISO 8601 date
    last_reinforced: string # ISO 8601 date (optional)
```

## Detection Rule

A procedure is created when:
- 3+ workflow-level observations (`type: observation` or `type: deviation`) across **different stories**
- Observations describe the same workflow adaptation or risk pattern

## Distinction from Principles

- **Principles** = code-level patterns (how to write code, what patterns to use)
- **Procedures** = workflow-level patterns (how to run the process, what steps to adapt)

Example principle: "Always use constructor injection for external service dependencies"
Example procedure: "Stories touching the auth module need extra security review in the PLAN phase"

## Lifecycle

1. **DETECT** — memory-curator identifies repeated workflow observation
2. **CREATE** — procedure entry created
3. **APPLY** — included in briefings for matching workflow types
4. **ARCHIVE** — confidence drops below threshold
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: 471kUpdated 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