article-enrichment

Transform raw article text dumps in the brain into structured pages with executive summary, verbatim quotes, key insights, why-it-matters, and cross-references. Replaces walls-of-text with quotable, actionable brain pages.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/article-enrichment/SKILL.md

Quality

Content

70%

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

The body is a well-structured, clearly sequenced skill with a quality-bar checklist and feedback loop for a batch/mutating operation, scoring well on workflow clarity and progressive disclosure. It loses points on conciseness (redundant Invocation re-walk and stub sections for a conformance test) and on actionability (the core enrichment and cross-link steps are described as intent rather than executable commands).

Suggestions

Collapse the "Invocation" section into the pipeline or reference it, since it re-states the same READ→WRITE→CROSS-LINK steps; remove the empty "Contract" and "Output Format" stubs or move their content into the sections they duplicate.

Make the cross-link step executable by giving the concrete gbrain command for adding a back-link rather than the comment "add a timeline back-link".

Drop or relocate the version-specific "v0.25.1" note to avoid time-sensitive detail degrading conciseness.

Dimension	Reasoning	Score
Conciseness	The body mostly assumes Claude's competence and avoids explaining basic concepts, but it carries redundancy (the "Invocation" section re-walks the same pipeline already in "The pipeline") and near-empty "Contract"/"Output Format" stubs that exist only for a conformance test. Not a 3 because those sections and the version-specific "v0.25.1" reference add tokens without user-facing value; not a 1 because the core guidance is lean and concrete.	2 / 3
Actionability	Provides concrete commands ("gbrain query 'needs_enrichment: true type:article' --limit 50", "gbrain get media/articles/<slug>") and a precise output spec, but the core ENRICH and cross-link steps are expressed as comments describing intent rather than executable operations, and "add a timeline back-link" lacks a concrete command. Not a 3 because the key transformation step is not copy-paste executable; not a 1 because real gbrain commands and a concrete section template are given.	2 / 3
Workflow Clarity	A clear 6-step pipeline (READ→SCAN→CONTEXT→ENRICH→WRITE→CROSS-LINK) with an explicit quality-bar checklist serving as validation and a spot-check LLM-judge eval as a feedback loop for this batch/mutating operation. Not a 2 because validation checkpoints and the idempotency guard ("check the needs_enrichment flag; skip if already false") are explicitly present.	3 / 3
Progressive Disclosure	Content is split into well-organized sections with one-level-deep, clearly signaled references ("[conventions/quality.md](../conventions/quality.md)", "[_brain-filing-rules.md](../_brain-filing-rules.md)"), and a Related skills list; no nested 2+ level reference chains. Not a 2 because references are clearly signaled and appropriately external rather than dumped inline.	3 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and clearly occupies a distinct niche, but it omits an explicit "Use when..." trigger clause and leans on internal jargon ("brain pages", "text dumps") rather than natural user phrasing, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit "Use when..." clause naming natural user phrases (e.g., "Use when an article brain page is a wall of raw text, or the user asks to enrich/summarize an article into quotable brain pages").

Soften internal jargon in the description ("text dumps in the brain", "brain pages") so the first line reads as something a user would naturally say.

Mirror one or two of the frontmatter triggers (e.g., "enrich this article") into the description so trigger-term coverage is visible there too.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and named outputs: "Transform raw article text dumps in the brain into structured pages with executive summary, verbatim quotes, key insights, why-it-matters, and cross-references." Not a 2 because it enumerates several specific transformations rather than naming only a domain and a few actions.	3 / 3
Completeness	Clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance in the description; per the judging guidelines a missing trigger clause caps completeness at 2. Not a 1 because the "what" is strong; not a 3 because "when" is only implied.	2 / 3
Trigger Term Quality	The description contains relevant domain terms ("article", "verbatim quotes", "insights") but uses jargon like "text dumps in the brain" and "brain pages" with no natural user-facing phrasing; the natural triggers live in the frontmatter triggers list rather than the description itself. Not a 1 because some relevant keywords are present, but not a 3 because common natural-language variations a user would say are absent from the description.	2 / 3
Distinctiveness Conflict Risk	The niche is specific (raw article dumps in a personal brain, walls-of-text, quotable actionable pages) making it unlikely to trigger for the wrong skill. Not a 2 because the framing is clearly distinct rather than a generic document operation.	3 / 3
	Total	10 / 12 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 missing, 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/article-enrichment/SKILL.md
Commit: c44cdb5

Reviewed: about 20 hours 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.