digital-brain

This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.

1.38x

Quality

43%

Does it follow best practices?

Impact

98%

1.38x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./examples/digital-brain-skill/SKILL.md

Quality

Discovery

29%

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 fundamentally flawed because it only specifies when to use the skill without ever explaining what the skill does. While it has good trigger term coverage, the complete absence of capability descriptions makes it impossible to understand the skill's purpose, and the broad trigger terms would likely cause conflicts with many other skills.

Suggestions

Add a clear 'what' statement at the beginning describing specific capabilities (e.g., 'Manages personal brand content, maintains voice consistency across posts, and tracks professional networking contacts.')

Narrow the scope or clarify how these disparate functions (content creation, contact lookup, meeting prep, goal tracking) relate to a single coherent skill to reduce conflict risk

Restructure to follow the pattern: '[Specific capabilities]. Use when [triggers]' rather than leading with triggers alone

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions - only trigger phrases. It never explains what the skill actually does, using only vague references like 'personal brand, content creation, network management' without specifying any capabilities.	1 / 3
Completeness	The description only addresses 'when' (trigger conditions) but completely omits 'what' - there is no explanation of what capabilities or actions this skill provides. This is the inverse of the typical problem.	1 / 3
Trigger Term Quality	Includes many natural trigger phrases users would say: 'write a post', 'check my voice', 'look up contact', 'prepare for meeting', 'weekly review', 'track goals'. These are conversational and cover multiple use cases.	3 / 3
Distinctiveness Conflict Risk	The triggers are extremely broad and would conflict with many other skills - 'write a post' could trigger writing skills, 'track goals' could trigger productivity skills, 'look up contact' could trigger CRM skills. No clear niche is established.	1 / 3
	Total	6 / 12 Passed

Implementation

57%

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

This skill demonstrates strong organizational structure and progressive disclosure, making it easy to navigate a complex personal operating system. However, it sacrifices actionability by describing workflows abstractly rather than providing executable code, and lacks validation checkpoints for error recovery. The content could be tightened by removing explanations of file formats and concepts Claude already understands.

Suggestions

Add executable code snippets for common operations like appending to JSONL files, reading voice.md, and searching contacts - replace pseudocode workflows with copy-paste ready examples

Include validation checkpoints in workflows (e.g., 'If contact not found in contacts.jsonl, ask user for details before proceeding')

Remove the 'File Format Strategy' section explaining what JSONL/YAML/Markdown are - Claude knows these formats

Add example JSONL entry structures showing the exact schema expected for ideas, posts, contacts, and interactions

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some unnecessary explanations (e.g., explaining what JSONL/YAML/Markdown are for, the 'Core Concepts' section explaining progressive disclosure architecture that Claude understands). The module overview table and file format strategy sections add bulk without proportional value.	2 / 3
Actionability	Workflows are listed as numbered steps but lack executable code examples. The 'Content Creation Workflow' and 'Pre-Meeting Preparation' sections describe what to do but don't show concrete commands or code snippets for file operations. The Python script references exist but aren't shown.	2 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (content creation, meeting prep, weekly review), but validation checkpoints are missing. There's no guidance on what to do if a contact isn't found, if voice.md is malformed, or how to verify successful logging to JSONL files.	2 / 3
Progressive Disclosure	Excellent structure with clear one-level-deep references to module-specific documentation. The skill explicitly states 'Only load what's needed for the current task' and provides well-organized navigation to IDENTITY.md, CONTENT.md, NETWORK.md, etc. The three-level loading pattern table is helpful.	3 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: muratcankoylan/Agent-Skills-for-Context-Engineering
Commit: 3ab8c94

Reviewed: 10 days 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.