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

57%

Does it follow best practices?

Impact

98%

1.38x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/digital-brain/SKILL.md

Quality

Content

53%Weight 40%Scale 1-5

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

The skill is well-structured with clear module separation and concrete file-path workflows, but it explains concepts Claude already knows, references module docs and scripts that are not in the bundle, and omits validation checkpoints for its append-only and weekly-review batch operations.

Suggestions

Cut explanatory padding Claude doesn't need (the rationale for JSONL/YAML/markdown/XML choices, the append-only integrity justification, and the integration/context-engineering section) to improve token efficiency.

Add explicit validation/verification steps to batch and destructive-adjacent workflows — e.g., after running weekly_review.py, verify metrics.jsonl updated correctly before planning; confirm archive status was set rather than an entry deleted.

Either include the referenced module .md files (identity/IDENTITY.md, content/CONTENT.md, network/NETWORK.md, operations/OPERATIONS.md, agents/AGENTS.md) and the agents/scripts/ files in the bundle, or remove the broken references so signaled navigation resolves.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-sectioned, but it restates concepts Claude already knows (explaining JSONL/YAML/markdown/XML format choices, append-only integrity rationale, progressive-disclosure architecture) and duplicates the trigger list and module inventory, adding padding that could be trimmed.	3 / 5
Actionability	Workflows give concrete file paths and sequences, but the runnable items are pseudo-commands or script references ('python agents/scripts/weekly_review.py') without showing actual executable code or the scripts' contents inline; guidance is specific to file targets but not copy-paste executable.	3 / 5
Workflow Clarity	Sequences are clearly listed (content creation, pre-meeting, weekly review), but the batch/destructive-adjacent operations lack validation checkpoints — the append-only archive rule has no verify step, and the weekly review run has no 'check output before proceeding' gate, capping clarity at 3 per the destructive/batch cap.	3 / 5
Progressive Disclosure	Structure is good: a three-level loading table, per-module overviews, and a References section with one-level-deep links to module .md files; however the referenced module docs (identity/IDENTITY.md, content/CONTENT.md, etc.) are not present in the bundle, so some signaled references are unresolved, a minor organization gap.	4 / 5
	Total	13 / 20 Passed

Description

61%Weight 40%Scale 1-5

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

The description is trigger-rich and clearly signals when to activate, but it leads with 'This skill should be used when...' and never states concretely what the skill does, leaving the 'what' implied and the capabilities generic.

Suggestions

Open with a concrete capability statement in third person (e.g., 'Manages a personal digital brain for content, contacts, goals, and knowledge...') before the trigger clause, so the 'what' is explicit rather than implied.

Replace generic verbs with specific actions the skill performs (e.g., 'drafts posts in the user's voice', 'logs contacts and interactions', 'tracks weekly goal progress') to lift specificity.

Tighten overlap-prone terms ('network management', 'track goals') with more niche-specific phrasing to reduce conflict with generic productivity/CRM skills.

Dimension	Reasoning	Score
Specificity	The description names the domain (personal brand, content, network, goals) but lists no concrete actions beyond quoted trigger phrases; it reads as a usage clause rather than a capability statement, and the actions are generic ('track goals', 'write a post') without naming specific operations.	2 / 5
Completeness	It answers 'when' explicitly and thoroughly with concrete trigger phrases, but the 'what' is only weakly implied through the trigger list rather than a clear statement of what the skill does; it lacks an explicit capability sentence.	4 / 5
Trigger Term Quality	Good coverage of natural phrases users would say ('write a post', 'check my voice', 'prepare for meeting', 'weekly review', 'track goals', 'look up contact'), plus domain synonyms (personal brand, content creation, network management); a few common variations or file-type cues are missing.	4 / 5
Distinctiveness Conflict Risk	The trigger set is fairly specific to a personal-operating-system niche, but broad terms like 'content creation', 'network management', and 'track goals' could overlap with general productivity or CRM skills, so overlap risk remains moderate.	3 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/digital-brain/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.