跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
搜索与研究

soul-grader

Use when grading, reviewing, rewriting, or approving a Hermes Agent SOUL.md. Uses the SOUL.md field-guide research artifacts as the only normative source for what makes a good SOUL.md.

cobibean · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add cobibean/soul-grader-skill --skill soul-grader

技能说明


name: soul-grader description: Use when grading, reviewing, rewriting, or approving a Hermes Agent SOUL.md. Uses the SOUL.md field-guide research artifacts as the only normative source for what makes a good SOUL.md. version: 1.1.0 author: cobibean license: MIT metadata: hermes: tags: [soul-md, grading, hermes-agent, agent-identity, review, rubric] related_skills: [hermes-agent]

SOUL Grader

Linked references

  • references/fleet-soul-grading-workflow.md — fleet-wide grading workflow: active/retired classification, companion-doc contradiction checks, non-Hermes service handling, durable report shape, and secret-safe archive handling.
  • references/research-deliverable-and-fleet-remediation.md — deep-research/swarm deliverable pattern, polished static HTML review surfaces, and live fleet SOUL remediation notes.
  • references/phase-coupled-soul-refresh.md — refresh pattern for a deployed agent whose durable identity has fallen behind its current phase, including unscored companion-doc placement checks.
  • references/live-soul-upgrade-production-handoff.md — production handoff pattern for backup, target-score iteration, live profile verification, safe refresh, and behavior smoke testing.

Overview

Use this skill to grade a Hermes Agent SOUL.md, draft a SOUL review, or turn a weak SOUL into a stronger one. The grading standard is intentionally narrow: use the linked SOUL.md research artifacts as the only normative source for what makes a good SOUL.md.

Do not import generic prompt-engineering advice, personal taste, web articles, model-provider docs, or vibes into the grade. You may use tools to read the SOUL being graded and to verify Hermes runtime facts, but quality judgments must come from the research artifacts bundled with this skill.

Public / SSR publication posture

This is an unofficial community skill for Hermes Agent. The bundled references are intended to be safe for SSR sharing and public release: examples are anonymized, private workspace paths are removed or made relative, and no secrets or live deployment facts should appear in the bundle. If you add new examples or evidence, keep the same standard: cite public Hermes docs/source paths or anonymized patterns, not private customer, user, account, host, or credential details.

Required source files

Before grading, load at least the grading standard reference:

skill_view(name="soul-grader", file_path="references/soul-md-grading-standard.md")

Use the other references when you need more detail or citations:

skill_view(name="soul-grader", file_path="references/soul-md-field-guide.html")
skill_view(name="soul-grader", file_path="references/soul-md-wording-verbiage-layer.md")

Source hierarchy for grading:

  1. references/soul-md-grading-standard.md — canonical grader rubric and procedure.
  2. references/soul-md-wording-verbiage-layer.md — supporting wording examples interpreted through the canonical standard.
  3. references/soul-md-field-guide.html — historical research background; non-normative where it conflicts with the canonical standard.

If these references conflict, use the higher-ranked source. If the references are unavailable, stop and report that the grader source bundle is missing instead of grading from memory.

When to use

Use when the user asks to:

  • grade, score, audit, review, or approve a SOUL.md
  • compare two SOUL.md files
  • rewrite or improve a SOUL.md
  • upgrade a SOUL.md to production handoff quality and iterate until a user-chosen score target is met
  • check whether a new agent identity is ready to deploy
  • create acceptance criteria for a SOUL file
  • diagnose agent identity drift, overreach, genericness, or approval-boundary failures
  • decide what belongs in SOUL.md versus CLAUDE.md, AGENTS.md, skills, memory, manifests, or operator guides

Do not use as the sole workflow for:

  • installing or configuring Hermes itself — load hermes-agent
  • full new-agent intake/design — load the project’s new-agent intake or design skill too, if one is available
  • authoring a new skill — load hermes-agent-skill-authoring too
  • editing a user’s actual SOUL file without permission

Strict source rule

The target SOUL.md being graded is evidence, not a standard. Runtime/tool output is evidence about deployment state, not a standard. The bundled references are the standard.

Allowed sources:

  • the user-provided SOUL text or file path
  • optional adjacent files only for placement, contradiction, or system-level deployability evidence; never score their prose as part of the SOUL grade
  • live Hermes/runtime output only for runtime hygiene checks
  • this skill’s linked references

Not allowed as grading sources:

  • generic prompt-engineering heuristics not present in the references
  • web search results
  • model-provider documentation
  • personal preference unless the user explicitly asks for a custom overlay after the source-grounded grade
  • unstated assumptions about a deployed agent’s access, host, credentials, or service state

Grading rubric

Score out of 100 using the reference-defined categories:

CategoryPointsWhat to evaluate
Mission clarity15Names who/what the agent serves and what outcome matters.
Identity + positive role boundaries12Defines role, ownership, layer, and adjacent responsibilities positively.
Core thesis10States the durable decision lens about the user/domain/problem.
Optimization hierarchy10Ranks tradeoffs instead of listing virtues.
Judgment + decision ownership10Explains tradeoff judgment and preserves consequential operator decisions.
Soft preferences8Separates scoring signals from bans.
Relationship + authority posture10Defines initiative, challenge, correction, and operator authority.
Voice + truthfulness posture10Covers distinctive voice plus candor and evidence orientation.
Success orientation
阅读完整来源 ↗