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".

Quality

86%

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

Quality

Content

72%

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

A well-organized, concise workflow with good external reference structure, but it leans on abstract direction for fetching and analysis and lacks the validation checkpoints expected of a mutating, page-writing skill.

Suggestions

Add explicit verification steps for the mutating operations — e.g., after creating/updating a page, confirm it exists and that bidirectional cross-links resolved before running 'gbrain sync'.

Replace the abstract fetch guidance in Phase 1 with concrete commands or tool calls per content type (web fetch URL pattern, tweet API invocation) so the workflow is fully executable.

Tighten the overlap between the Contract section and the Phases so guarantees are stated once, or explicitly frame the Contract as a checklist that the phases implement.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it gives workflow, commands, and templates without explaining concepts Claude already knows. Minor redundancy between Contract and Phases keeps it just at the efficient end rather than padded.	3 / 3
Actionability	Concrete pieces exist ('gbrain files upload-raw <file> --page <slug>', 'gbrain sync', the output-format and back-link templates, filing paths), but phases 1 and 5 stay abstract ('Use appropriate tools', 'Tell the user things they wouldn't have noticed') with no executable fetch/analyze commands — guidance is present but incomplete.	2 / 3
Workflow Clarity	Six numbered phases give a clear sequence, but this mutating skill (writes pages, mutating: true) has no validation/verification checkpoints — no 'confirm page created' or 'verify cross-links' step — so per the guidelines workflow clarity caps at 2.	2 / 3
Progressive Disclosure	The body is an overview with clearly signaled one-level-deep references — 'Read skills/_brain-filing-rules.md' and 'See skills/conventions/quality.md' — and externalizes filing rules and conventions rather than inlining them, matching the score-3 anchor.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 well-crafted description that names concrete capabilities, supplies natural trigger phrases, and clearly answers both 'what' and 'when'. It carves a distinct niche with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Fetch content, save to brain with analysis, create author people page, and cross-link' — rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	Explicitly states what it does (ingest/fetch/save/cross-link) AND when to use it ('Use when the user shares a link or says...'), satisfying both halves with explicit triggers.	3 / 3
Trigger Term Quality	Includes natural phrases a user would actually say — 'shares a link', 'read this', 'save this', 'think about this' — giving good coverage of likely utterances.	3 / 3
Distinctiveness Conflict Risk	The brain-ingest niche with 'read this'/'think about this'/'put this in brain' triggers is a clear, distinct use case unlikely to fire for unrelated skills, despite 'save this' being somewhat generic.	3 / 3
	Total	12 / 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	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/idea-ingest/SKILL.md
Commit: 3fafb69

Reviewed: about 21 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.