All skills
simota avatar

/architect

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

Designing new skill agents via gap analysis, overlap detection, SKILL.md + reference generation, and Nexus integration. Not for task orchestration (Nexus) or format-only audits (Gauge).

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

This session only. Nothing lands on disk.

referencecreative-thinking.md

≈404 tokens on demand. Your agent reads this file only when SKILL.md points to it.

ENVISION: Value Before a New Agent

Read before drafting a new agent. Use the effort budget and completion gates in SKILL.md; record design decisions, not a prescribed private reasoning transcript.

Axis Question that changes the design Required outcome
HEIGHT Is a different framing or no new agent a better solution? Compare the proposed abstraction with alternatives
BREADTH Can existing owners or a combination of their capabilities satisfy the need? Identify reuse and the remaining gap
DEPTH Which root need would still fail after those alternatives? State the nontrivial capability the new owner must provide

Synthesize one design premise, its unique value and the constraints it implies. A candidate that adds only a new name or workflow wording does not close a gap.

Value-First Checklist

VALUE_FIRST_CHECKLIST:
  world_comparison:
    without_agent: "[current outcome]"
    with_agent: "[changed outcome]"
    delta: "[specific improvement]"
  primary_beneficiary:
    persona: "[who needs it]"
    pain_point: "[current failure]"
    frequency: "[how often it occurs]"
  success_metric:
    primary: "[measured outcome]"
    measurement: "[how it will be checked]"
    target: "[acceptance threshold]"

Before ANALYZE, verify that the problem is understood, all three axes were considered, the value record is complete, not building was considered, and extending an existing agent cannot deliver the required outcome. Missing evidence is a gap to resolve, not a reason to invent a benefit.

Source: SKILL.md on GitHub

2 warnings13d5 checks · Risk MEDIUM
  • Gen Agent Trust Hub13d

    The skill features a self-evolution capability that allows it to autonomously modify its own reference files and instructions. It also acts as an agent design tool, which introduces a surface for indirect prompt injection based on untrusted user requirements.

  • Socket13d

    No alerts

  • Snyk13d

    Risk: LOW · No issues

  • Runlayer6mo

    5/18 files flagged

  • ZeroLeaks5mo

    1 finding · Score: 69/100

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/architect