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/anti-patterns-schema.md

View on GitHub
# Anti-Patterns Schema

Defines `.shaktra/memory/anti-patterns.yml` — failure patterns with recommended alternatives. Created when repeated failures are detected on the same pattern.

## Schema

```yaml
anti_patterns:
  - id: string              # "AP-001" — sequential
    failed_approach: string  # what went wrong (1-3 sentences)
    failure_mode: string     # why it fails
    severity: string         # P0-P3 — highest severity from source observations
    recommended_approach: string # what to do instead
    trigger_patterns: [string]  # keywords for proactive surfacing
    confidence: float        # 0.2-1.0
    tags: [string]
    roles: [string]          # agents this anti-pattern is relevant to
    scope: string            # "project" | "universal"
    status: string           # "active" | "archived"
    source: string           # story_id where the pattern was first detected
    created: string          # ISO 8601 date
```

## Detection Rule

An anti-pattern is created when:
- 2+ failure observations (`type: quality-loop-finding`, `resolved: false`) on the **same pattern** within 3 stories
- Pattern match: overlapping tags and similar issue descriptions

## Proactive Surfacing

During briefing generation, anti-patterns are surfaced when their `trigger_patterns` match the story's keywords or scope. This enables proactive warnings before agents repeat known mistakes.

## Lifecycle

1. **DETECT** — memory-curator identifies repeated failure pattern
2. **CREATE** — anti-pattern entry created with trigger patterns
3. **SURFACE** — included in story briefings when trigger patterns match
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