All skills
simota avatar

/atlas

@965f4f9
by shingo imotasimota/agent-skills85 stars
15

Analyzing dependencies, circular references, and God Classes; authoring ADRs/RFCs. Use for architecture improvement, module decomposition, and technical debt assessment.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/atlas

This session only. Nothing lands on disk.

referenceautorun-schema.md

≈370 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Atlas — AUTORUN _STEP_COMPLETE Schema

See _common/AUTORUN.md for the protocol (_AGENT_CONTEXT input, mode semantics, error handling).

_STEP_COMPLETE:
  Agent: Atlas
  Status: SUCCESS | PARTIAL | BLOCKED | FAILED
  Output:
    deliverable: [artifact path or inline]
    artifact_type: "[ADR | RFC | Dependency Analysis | Debt Assessment | Module Boundary Design | Health Score | Tri-Engine Consensus ADR]"
    parameters:
      analysis_scope: "[module | package | system]"
      coupling_score: "[metric]"
      debt_items: "[count]"
      migration_risk: "[Low | Medium | High]"
    tri_engine:                                  # present only when `multi` Recipe ran
      engines_run: [actual usable engines]  # authorized and actually invoked
      engines_failed: [list or none]
      smell_confidence:
        CONFIRMED: [count]
        LIKELY: [count]
        VERIFIED-CANDIDATE: [count]
      option_perspective:
        CONVERGENT: [count]
        CONVERGENT-PARTIAL: [count]
        DIVERGENT: [count]
      recommended_option_style: "[Layered | Hexagonal | DDD | Event-Driven | Modular-Monolith | Microservices | CQRS | Vertical-Slice | Pipeline | Plugin]"
      dissenting_option_styles: [list of architectural styles preserved as alternatives]
      rejected: [count + top categories — hallucinated-module / already-mitigated / infeasible / anti-pattern]
  Next: Zen | Quill | Sherpa | Canvas | Builder | DONE
  Reason: [Why this next step]

Source: SKILL.md on GitHub

No alerts13d5 checks · Risk SAFE
  • Gen Agent Trust Hub13d

    The 'atlas' skill is a professional architecture analysis agent designed to manage technical debt and architectural decisions. A security analysis identified no critical vulnerabilities such as credential theft, malicious code execution, or obfuscation. The skill presents a low-severity surface for indirect prompt injection because it is designed to ingest and analyze untrusted project data, including source code and dependency manifests. The skill incorporates defensive grounding mechanisms and recommends architectural fitness functions to mitigate risks associated with untrusted inputs.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: LOW · No issues

  • Runlayer6mo

    1/13 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 965f4f9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/atlas