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/observations-schema.md

View on GitHub
# Observations Schema

Defines `.shaktra/stories/<story_id>/.observations.yml` — per-story observations written by agents during workflow execution. Consumed by the memory-curator during post-workflow consolidation.

## Schema

```yaml
observations:
  - id: string          # "OB-001" — sequential within story
    agent: string       # agent name: "developer" | "sw-quality" | "sw-engineer" | "architect" | "bug-diagnostician" | "test-agent" | "product-manager"
    phase: string       # TDD phase: "plan" | "plan-review" | "tests" | "code" | "code-gate" | "quality" | "review" | "diagnosis"
    type: string        # "discovery" | "quality-loop-finding" | "fix-rationale" | "deviation" | "observation" | "consistency-check"
    text: string        # what was observed (1-3 sentences)
    tags: [string]      # freeform keywords, used for matching during consolidation
    importance: integer  # 1-10 (7+ = strong promotion candidate)
    # Optional fields (type-dependent):
    severity: string     # P0-P3, only for quality-loop-finding type
    resolved: boolean    # only for quality-loop-finding type
    iterations: integer  # fix attempt count, only for quality-loop-finding type
    principle_id: string # only for consistency-check type — references PR-NNN
    relationship: string # "reinforce" | "weaken" | "contradict", only for consistency-check type
```

## Lifecycle

1. **CREATE** — orchestrator creates empty `.observations.yml` at workflow start
2. **APPEND** — agents append observations during their phase
3. **CONSOLIDATE** — memory-curator reads and synthesizes into long-term stores
4. **ARCHIVE** — observations stay with the story directory for audit trail
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