CtrlK
BlogDocsLog inGet started
Tessl Logo

idea-ingest

Ingest links, articles, tweets, and ideas into the brain. Fetch content, save to brain with analysis, create author people page, and cross-link. Use when the user shares a link or says "read this", "save this", "think about this".

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is idea-ingest in garrytan/gbrain

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 well-structured, actionable instruction skill with concrete commands, templates, and a clear phased workflow. Mild redundancy and the absence of an explicit validation loop and bundle-file split keep it from the top band.

Suggestions

Add an explicit validation checkpoint in the phases (e.g., verify fetch returned real content and confirm no duplicate URL before writing), framed as a validate→fix→retry step.

De-duplicate the Contract and Phases sections so the people-page, cross-link, and citation requirements appear once, trimming tokens.

Move the output-format template and back-link format into a bundled references file and link to it, so the SKILL.md body stays a lean overview.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence, but the Contract and Phases sections partly restate each other (people page, cross-links, citations) and could be tightened.

4 / 5

Actionability

Concrete commands (`gbrain files upload-raw <file> --page <slug>`, `gbrain sync`), a back-link format string, slug examples, and a full output template make the guidance copy-ready.

5 / 5

Workflow Clarity

Six numbered phases are clearly sequenced with embedded verification (search-before-create, duplicate-URL check), but there is no explicit validate→fix→retry loop as a named checkpoint for the mutating writes.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled one-level-deep external references (the filing-rules blockquote, conventions note), but content is monolithic in one file with no bundle split and the referenced files live outside the bundle.

4 / 5

Total

17

/

20

Passed

Description

95%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 strong description that clearly states capability and trigger conditions with natural user language. Minor specificity gap (some backend steps unstated) keeps it just off perfect.

DimensionReasoningScore

Specificity

Names concrete actions — "Fetch content, save to brain with analysis, create author people page, and cross-link" — plus the ingest targets (links, articles, tweets, ideas), but omits some mechanics (upload-raw, sync) keeping it just short of comprehensive.

4 / 5

Completeness

Explicitly answers both what (ingest + fetch + analyze + author page + cross-link) and when ("Use when the user shares a link or says...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural verbal triggers a user would actually say — "read this", "save this", "think about this", plus "shares a link" — give comprehensive coverage of the skill's entry points.

5 / 5

Distinctiveness Conflict Risk

The brain-ingestion niche with link/share-triggered phrases is clearly distinct from other skills and unlikely to fire for the wrong one.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
garrytan/gbrain
Reviewed

Table of Contents

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.