All skills
simota avatar

/vision

@c805268
by shingo imotasimota/agent-skills85 stars
15

Directing UI/UX creative work — redesigns, new designs, trend application, Design System construction, Muse/Palette/Flow/Forge orchestration. Use for design direction. Offers a co-design pair mode.

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

This session only. Nothing lands on disk.

referenceautorun-schema.md

≈403 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Vision — AUTORUN _STEP_COMPLETE Schema

When Vision receives _AGENT_CONTEXT, parse task_type, description, and Constraints, execute the standard workflow, and return _STEP_COMPLETE.

The pair recipe is INTERACTIVE and cannot run unattended — under AUTORUN, run UNDERSTAND, draft the ordered decision plan + the first decision's options, and set Next: USER (pair-ready) rather than locking decisions without confirmation.

_STEP_COMPLETE

_STEP_COMPLETE:
  Agent: Vision
  Status: SUCCESS | PARTIAL | BLOCKED | FAILED
  Output:
    deliverable: [primary artifact]
    parameters:
      task_type: "[task type]"
      scope: "[scope]"
    tri_engine:                                  # present only when `multi` Recipe ran
      engines_run: [actual usable engines]  # authorized and actually invoked
      engines_failed: [list or none]
      merge_strategy: "[Portfolio | Compete]"
      concurrence_distribution:
        UNIVERSAL: [count]
        LIKELY: [count]
        VERIFIED-DIVERGENT: [count]
      spectrum_coverage:
        positions: [list of distinct spectrum_position values across surviving directions]
        spread_ok: [true | false]
      rejected: [count + top categories — brand-drift / persona-mismatch / a11y / hallucination / vague-outcome / ai-trust]
      lead_recommendation: "[direction concept_name]"
      challenger: "[direction concept_name or none]"
  Validations:
    completeness: "[complete | partial | blocked]"
    quality_check: "[passed | flagged | skipped]"
  Next: [recommended next agent or DONE]
  Reason: [Why this next step]

Source: SKILL.md on GitHub

No alerts14d5 checks · Risk SAFE
  • Gen Agent Trust Hub14d

    The 'vision' skill is a comprehensive design-direction tool that operates by defining strategies and delegating work to other specialized agents. It contains robust internal guardrails, including mandatory accessibility standards (WCAG 2.2 AA) and ethical AI principles. No security risks were identified.

  • Socket14d

    No alerts

  • Snyk14d

    Risk: LOW · No issues

  • Runlayer6mo

    9 files scanned · No issues

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at c805268. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 weeks ago

README badge

README badge for simota/agent-skills/vision