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.

referencenaming-conventions.md

≈348 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Agent Naming

Run after the primary action, output and domain are known. Use 1–2 syllables where possible; 3 is acceptable, 4+ is avoided. Do not use numbers or special characters. Repository file/display conventions remain authoritative.

Candidate Score

Rate each dimension 1–5; multiply by its weight and sum. Select the highest-scoring candidate that passes conflict checks.

Dimension Weight
Brevity 20%
Evocativeness 30%
Memorability 20%
Uniqueness 15%
Typeability 15%

Required Records

FUNCTION_ANALYSIS:
  primary_action: "[what the agent does]"
  primary_output: "[owned deliverable]"
  primary_domain: "[scope]"
CONFLICT_CHECK:
  exact_match: "[current skill names checked]"
  phonetic_similar: "[confusable names]"
  abbreviation_conflict: "[confusable short forms]"
  semantic_conflict: "[roles the name could misroute to]"

Check the actual global and available project-local skill definitions, not a copied name bank. Reject exact conflicts; explain remaining ambiguity before selection. Avoid culturally offensive or misleading names and unsupported claims of trademark clearance.

Return the selected name, syllable count, weighted score and the conflict evidence. Do not retain illustrative names as a list of available names: installation and roster changes invalidate that assumption.

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