Name: enrich
Rating: 64.8 (1 reviews)
Author: garrytan

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

77%

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

Fix and improve this skill with Tessl

tessl review fix ./plugin-variants/gbrain-coding/skills/enrich/SKILL.md

The canonical home for this skill is enrich in garrytan/gbrain

Quality

Content

71%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.

A highly actionable, well-sequenced enrichment protocol with concrete commands, templates, and validation gates. Its weak spots are redundancy that bloats the token budget and progressive disclosure that leans on a monolithic file with references to non-bundled paths.

Suggestions

Remove the Output Format section or collapse it to a one-line pointer to the templates above, and de-duplicate the repeated 'don't overwrite user assessments' and 'check brain first' lines to tighten conciseness.

Promote validation into the main 7-step flow as an explicit validate-then-retry checkpoint (e.g., after Step 6 run Validation Rules before committing) to lift workflow clarity.

Move the full person/company page templates and the data-source tables into reference files under references/ and link to them one level deep, so SKILL.md stays an overview and the cited filing/quality rules resolve to real bundle files.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational, but the Output Format section restates the page templates, "don't overwrite user-written assessments with API boilerplate" repeats three times, and "check brain first" is stated repeatedly, so it could be tightened.	3 / 5
Actionability	Concrete commands (gbrain search, put_raw_data, gbrain timeline-add, gbrain sweep --once), copy-paste-ready person/company templates, specific source tables, and numeric validation thresholds give fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	The 7-step protocol with CREATE/UPDATE branches is clearly sequenced and includes validation (notability gate, "test on 3-5 entities first", Validation Rules), so it clears the batch/destructive cap; it stops short of 5 because validation lives in separate sections rather than inline validate-then-retry feedback loops in the main flow.	4 / 5
Progressive Disclosure	Section structure is good, but the referenced paths (skills/_brain-filing-rules.md, skills/conventions/quality.md) are not present in the bundle and the full page templates plus source tables are inlined rather than split into reference files.	3 / 5
	Total	15 / 20 Passed

Description

83%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 cleanly answers both what and when with concrete, third-person actions and a distinct brain-enrichment niche. Its main weakness is that the richest natural trigger synonyms are split off into the triggers field rather than the description itself.

Dimension	Reasoning	Score
Specificity	"Creates and updates person/company pages with compiled truth, timeline, and cross-links" names the domain and several concrete actions; not a 5 because "tiered enrichment protocol" stays abstract and coverage is not fully comprehensive.	4 / 5
Completeness	It explicitly states both what it does (creates/updates person/company pages with compiled truth, timeline, cross-links) and when to use it ("Use when a new entity is mentioned or an existing page needs updating") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Use when a new entity is mentioned or an existing page needs updating" gives natural trigger phrasing, but the most colloquial synonyms ("who is this person", "look up this company") live in the triggers field rather than the description, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The brain-page/person-company enrichment niche is mostly distinct with clear triggers, but there is minor overlap risk with generic web-research or contact-management skills, so it does not reach the minimal-conflict bar of 5.	4 / 5
	Total	17 / 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: plugin-variants/gbrain-coding/skills/enrich/SKILL.md
Commit: e78f1c3

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.