enrich

Enrich brain pages with tiered enrichment protocol. Creates and updates person/company pages with compiled truth, timeline, and cross-links. Use when a new entity is mentioned or an existing page needs updating.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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 content is a well-sequenced, actionable enrichment protocol with strong validation checkpoints for a mutating batch skill. Its main weakness is progressive disclosure: heavy inlined templates and absent reference bundle files keep it from a higher structure score.

Suggestions

Move the full person and company page templates into a separate references file (e.g. references/page-templates.md) and link to it from the protocol, keeping only a condensed inline example.

Extract the external data-source tables (4a-4e and the Data Need table) into a references file so the main flow stays scannable.

Trim the Output Format section since it restates the template contents, or collapse it into a one-line pointer to the templates.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, using tables and terse bullets without explaining concepts Claude already knows, but the Output Format section duplicates the templates and the Philosophy section carries light editorial prose that could be trimmed.	4 / 5
Actionability	It provides concrete gbrain commands, named external APIs, a JSON raw-data example, and copy-paste-ready page templates, but some lookup guidance ("Use Perplexity, Brave Search, Exa, or equivalent") stays high-level.	4 / 5
Workflow Clarity	The 7-step protocol is clearly sequenced with CREATE/UPDATE branches and explicit validation gates (notability gate, connection-count < 20 skip, bulk test-on-3-5-first, do-not-enrich list), satisfying the destructive/batch feedback-loop requirement.	5 / 5
Progressive Disclosure	Sections are well-organized and external references are clearly signaled via blockquote callouts, but no bundle files ship and two full page templates plus API-source tables are inlined rather than split into one-level-deep reference files.	3 / 5
	Total	16 / 20 Passed

Description

87%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 strong: it states concrete capabilities and pairs them with an explicit "Use when" trigger clause, covering both what and when. Minor room to surface more natural trigger phrasings directly in the description text.

Dimension	Reasoning	Score
Specificity	"Creates and updates person/company pages with compiled truth, timeline, and cross-links" names the domain plus several concrete actions and artifacts, but stops short of a fully comprehensive enumeration of the tiered protocol's capabilities.	4 / 5
Completeness	It explicitly answers both what ("Enrich brain pages... Creates and updates person/company pages with compiled truth, timeline, and cross-links") and when ("Use when a new entity is mentioned or an existing page needs updating") with concrete trigger phrases.	5 / 5
Trigger Term Quality	The "Use when a new entity is mentioned or an existing page needs updating" clause plus "enrich" gives good natural keyword coverage, though common phrasings like "who is this person" / "look up this company" live in the triggers field rather than the description itself.	4 / 5
Distinctiveness Conflict Risk	"Enrich brain pages with tiered enrichment protocol" carves a clear niche around person/company brain pages with distinct triggers, minimizing overlap with unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: garrytan/gbrain
Path: skills/enrich/SKILL.md
Commit: 43597b1

Reviewed: 5 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.