Tessl • The management layer for AI agent skills

SkillPublic

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

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

Quality

Content

88%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 genuine validation and error-recovery loops appropriate to a batch, page-mutating skill. The only notable gap is structural: the single long file inlines template and version-specific detail that would sit better in one-level-deep reference files.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational — tables, a 7-step protocol, and templates with no explanations of concepts Claude already knows. Minor tightening is possible: "Don't overwrite user-written assessments with API boilerplate" appears in both the UPDATE path and Validation Rules, and a few prose passages (e.g., the Communication Style guidance) could be trimmed.	4 / 5
Actionability	Guidance is copy-paste ready: exact commands (`gbrain search "name"`, `gbrain schema show --json`, `gbrain sweep --once`, `gbrain timeline-add`), a concrete put_raw_data JSON payload, complete person/company page templates, and quantified validation thresholds ("Connection count < 20"). Flexible-tool mentions ("Perplexity, Brave Search, Exa, or equivalent") are appropriately justified since external APIs vary.	5 / 5
Workflow Clarity	The 7-step protocol is clearly sequenced with CREATE/UPDATE branch points, and this batch skill has real validation and feedback loops: test on 3–5 entities before bulk, commit every 5–10 entities, Validation Rules for wrong-person detection, and a "When it fails" section with explicit recovery steps (revision_conflict re-read/merge/resave, auto_links.errors fix via add_link).	5 / 5
Progressive Disclosure	References to filing rules, conventions, the taxonomist skill, and the agent-operator protocol are clearly signaled via blockquote callouts and one level deep, and sections are well organized. It stops short of a 5 because everything lives in one ~354-line file — the full page templates and the v0.10.1 auto-link mechanics note are candidates for separate reference files.	4 / 5
	Total	18 / 20 Passed

Description

71%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.

A solid description that states concrete capabilities and an explicit use-when clause for a clearly distinct niche. Its main weakness is trigger-term coverage: the natural user phrases that would invoke this skill are relegated to the separate triggers field instead of the description text.

Suggestions

Fold one or two natural user phrases into the description itself, e.g., "Use when the user asks 'who is this person' or 'look up this company', or when a new entity is mentioned."

Replace internal jargon ("tiered enrichment protocol", "compiled truth") with plainer wording, or briefly gloss it, so the capability is concrete to a reader outside this brain system.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions ("Creates and updates person/company pages with compiled truth, timeline, and cross-links") rather than vague claims, but internal jargon like "tiered enrichment protocol" and "compiled truth" keeps it short of comprehensive, fully concrete coverage.	4 / 5
Completeness	Both halves are present: a clear "what" (enrich, create, and update person/company pages with compiled truth, timeline, cross-links) and an explicit "Use when a new entity is mentioned or an existing page needs updating" clause. It falls short of a 5 because the "when" lacks concrete user-utterance trigger phrases.	4 / 5
Trigger Term Quality	It contains relevant keywords ("enrich", "person/company pages", "new entity is mentioned") but omits the natural phrases a user would actually say (e.g., "who is this person", "look up this company"), which exist only in the separate triggers field, not the description itself.	3 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche — brain-page enrichment for people and companies with compiled truth, timelines, and cross-links — so it is unlikely to fire for unrelated skills, and its trigger conditions are domain-specific.	5 / 5
	Total	16 / 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: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: plugin-variants/gbrain-coding/skills/enrich/SKILL.md
Revision: f4d1866

Reviewed: 7 hours ago

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.

enrich

Table of Contents

Is this your skill?