soul

Embody this digital identity. Read SOUL.md first, then STYLE.md, then examples/. Become the person—opinions, voice, worldview.

Quality

38%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./public/skills/aaronjmars/soul-md/SKILL.md

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured persona-embodiment skill with clear file hierarchy, reading order, and decision-making frameworks for handling novel topics. Its main weakness is moderate verbosity—some sections (anti-patterns, data usage) could be tightened since they partially overlap with referenced files. The skill would benefit from inline examples showing correct vs incorrect persona application rather than only pointing to external example files.

Suggestions

Add 1-2 inline before/after examples showing a generic AI response transformed into an in-character response, rather than relying entirely on external example files for calibration.

Trim the anti-patterns section to a brief pointer to examples/bad-outputs.md since the detailed list duplicates what should live there.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably well-organized but includes some unnecessary elaboration. The anti-patterns section partially duplicates what would be in STYLE.md and bad-outputs.md. The 'Operating Principles' section could be tighter—Claude doesn't need explanations of what 'staying in character' means. The modes section is useful but somewhat verbose.	2 / 3
Actionability	The skill provides clear behavioral directives (character integrity rules, interpolation rules, source priority) but lacks concrete examples of how to apply them. There are no executable code snippets (not expected for this type), but the guidance is more descriptive than demonstrative—it tells Claude what to do without showing input/output examples of correct behavior inline.	2 / 3
Workflow Clarity	The reading order is explicitly numbered and well-sequenced. The source priority hierarchy (1-4) provides a clear decision tree for handling different types of queries. The modes section clearly delineates different operating contexts. For a non-destructive, persona-embodiment skill, this level of workflow clarity is appropriate and sufficient.	3 / 3
Progressive Disclosure	The file hierarchy is clearly documented with a tree diagram. References to SOUL.md, STYLE.md, examples/, and data/ are well-signaled and one level deep. The skill appropriately serves as an overview/operating manual that points to detailed content in companion files, with clear navigation cues at the bottom.	3 / 3
	Total	10 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is highly abstract and imperative in tone, reading more like an internal instruction than a skill description. It lacks concrete actions, natural trigger terms, and any 'when to use' guidance, making it very difficult for Claude to correctly select this skill from a pool of options. The references to specific files (SOUL.md, STYLE.md) add slight distinctiveness but don't compensate for the fundamental lack of clarity.

Suggestions

Add a clear 'Use when...' clause specifying triggers, e.g., 'Use when the user asks to write, respond, or communicate as [persona name], or when adopting a specific voice/identity for content creation.'

Replace vague language with concrete actions, e.g., 'Writes responses, blog posts, and social media content in a specific persona's voice, tone, and worldview as defined in configuration files.'

Include natural trigger terms users might say, such as 'persona,' 'voice,' 'character,' 'write as,' 'tone,' or 'brand voice.'

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'embody this digital identity' and 'become the person.' No concrete actions are listed—there's no indication of what specific tasks this skill performs (e.g., writing in a persona's voice, responding to questions as a character).	1 / 3
Completeness	The 'what' is extremely vague ('embody this digital identity') and there is no 'when' clause at all. There are no explicit triggers or guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	There are no natural keywords a user would say when needing this skill. Terms like 'digital identity,' 'SOUL.md,' and 'STYLE.md' are internal/technical jargon, not phrases a user would naturally use in a request.	1 / 3
Distinctiveness Conflict Risk	The references to specific files (SOUL.md, STYLE.md, examples/) provide some distinctiveness, but the overall concept of 'embodying a persona' is broad enough to potentially overlap with other persona, voice, or tone-related skills.	2 / 3
	Total	5 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: Demerzels-lab/elsamultiskillagent
Commit: f45fcb5

Reviewed: about 1 month ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.