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

56%

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

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 body is well-structured and appropriately scoped to a single file with clear conventions and a sensible pipeline, but it has notable redundancy across sections, leaves the page-write and cross-link steps as vague comments rather than executable guidance, and lacks an in-pipeline validation checkpoint for a mutating batch operation. These place it just above the midpoint of the scale.

Suggestions

Add an explicit verification step to the pipeline (e.g. after WRITE: re-read the page and check it against the Quality bar checklist before proceeding to CROSS-LINK) to satisfy the batch/destructive-operation feedback-loop requirement.

Replace the comment-only write/cross-link steps with the actual gbrain put_page and back-link command syntax (or a concrete markdown template for the enriched page), so steps 4–6 are executable rather than descriptive.

Deduplicate "What this does" vs. "Quality bar" vs. the pipeline section, drop the inline "v0.25.1" version literal, and trim or remove the Contract/Output Format conformance boilerplate to recover token budget.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but "What this does" and "Quality bar" re-enumerate the same six sections, the pipeline and Invocation sections overlap, a time-sensitive version literal ("in v0.25.1") appears inline, and the Contract/Output Format sections are conformance-test boilerplate rather than agent-useful content.	3 / 5
Actionability	Concrete executable commands exist ("gbrain query \"needs_enrichment: true type:article\" --limit 50", "gbrain get media/articles/<slug>"), but the critical write steps are comment-only hints ("Use the put_page operation with the new structured markdown body") with no actual command syntax, leaving the guidance incomplete.	3 / 5
Workflow Clarity	The 6-step pipeline (READ→SCAN→CONTEXT→ENRICH→WRITE→CROSS-LINK) is clearly sequenced and includes an idempotency check, but this is a mutating batch operation and the pipeline has no validate-after-write checkpoint — the batch-operation cap of 3 applies despite the post-hoc spot-check advice in Model selection.	3 / 5
Progressive Disclosure	This is a single-file skill with well-organized sections and clearly signaled one-level-deep references to conventions/quality.md, _brain-filing-rules.md, and related skills, matching the 'good structure; minor organization gaps' anchor; the placeholder Contract/Output Format sections add slight navigational noise, keeping it below 5.	4 / 5
	Total	13 / 20 Passed

Description

58%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 concrete, third-person, and nicely distinct, enumerating the exact structured sections it produces. Its main weaknesses are the complete absence of a "when to use" clause and the omission of the skill's own primary trigger verb ("enrich") and its synonyms from the description text.

Suggestions

Append a trigger clause, e.g. "Use when the user says 'enrich this article' or when an article page lands with needs_enrichment: true or reads as a wall of raw text."

Include the verb "enrich" and natural synonyms (e.g. "summarize", "make brain pages useful") in the description so the primary trigger terms appear in the description text, not only in the frontmatter triggers list.

State what the skill operates on more explicitly as an action (e.g. "reads and rewrites article pages under media/articles/", including preserving raw source in a collapsed details block) to round out the action list.

Dimension	Reasoning	Score
Specificity	"Transform raw article text dumps in the brain into structured pages with executive summary, verbatim quotes, key insights, why-it-matters, and cross-references" names the domain plus five concrete output artifacts, matching the 'several specific actions; minor gaps' anchor. It stops short of anchor 5 because it describes one transform operation and its output components rather than a comprehensive set of distinct actions.	4 / 5
Completeness	The "what" is clear (transform raw article dumps into structured pages with named sections), but there is no "Use when…" clause or equivalent explicit trigger guidance in the description, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms like "article", "text dumps", "walls-of-text", and "brain pages" are present, but the primary verb "enrich" and common synonyms/variations (summarize, digest, make useful) are absent from the description text itself, so coverage is partial.	3 / 5
Distinctiveness Conflict Risk	Phrases like "raw article text dumps in the brain", "walls-of-text", and "quotable, actionable brain pages" establish a clear niche with mostly distinct triggers; only minor overlap risk exists with generic summarization skills, so it sits at anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	14 / 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 missing, 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/article-enrichment/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.