ingest

Route content to specialized ingestion skills. Detects input type and delegates.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/ingest/SKILL.md

Quality

Content

65%

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

The content is highly actionable with concrete gbrain commands, file paths, and citation formats, and its media workflows and Test-Before-Bulk loop are well sequenced. Its weaknesses are redundancy across repeated Iron Law/citation rules, missing inter-step validation in the core mutating Phases, and a monolithic structure with no bundle files to offload detail into.

Suggestions

Add explicit validation checkpoints between core Phases (e.g., verify each back-link and timeline entry was created before moving on) to lift workflow_clarity above 2 for the mutating/batch flow.

De-duplicate the Iron Law and citation rules by stating them once authoritatively and referencing that section elsewhere, removing the repetition across Contract, Phases, Quality Rules, and Anti-Patterns.

Move the detailed per-format media workflows and the .redirect.yaml spec into reference files under references/ and link to them from a concise overview, so the body stays a lean entry point.

Dimension	Reasoning	Score
Conciseness	The body is mostly action-oriented and assumes Claude's competence, but the Iron Law and citation rules are restated across Contract, Citation Requirements, Phases, Quality Rules, and Anti-Patterns, so it could be tightened — matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	It provides copy-paste-ready commands (gbrain search/put/sync, gbrain files upload-raw), concrete file paths, and exact citation/redirect.yaml formats, matching 'fully executable code/commands; specific examples; copy-paste ready.'	3 / 3
Workflow Clarity	Phases and media workflows are clearly sequenced with a strong Test-Before-Bulk feedback loop, but the core mutating/batch Phases lack inter-step validation checkpoints, and the rubric caps workflow_clarity at 2 when validation is missing for batch/destructive operations.	2 / 3
Progressive Disclosure	Headers organize the content well, but it is a ~287-line monolithic document with detailed media workflows and the .redirect.yaml spec inline, and the only referenced files (skills/_brain-filing-rules.md, skills/conventions/quality.md) live outside the absent bundle — fitting 'some structure but content that should be separate is inline.'	2 / 3
	Total	9 / 12 Passed

Description

35%

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 concise and third-person with a clear router role, but it lacks natural trigger terms and any 'Use when...' guidance, leaving it dependent on sibling skills for context. It is distinguishable but not self-contained enough to fully prevent overlap with the specialized ingestion skills it routes to.

Suggestions

Add a 'Use when...' clause naming concrete user triggers such as 'Use when the user shares a meeting transcript, article, video, or conversation to save into the brain.'

Replace internal jargon ('ingestion skills', 'input type', 'delegates') with natural language a user would say (e.g., 'save to brain', 'process this meeting', 'ingest this article').

Clarify the router boundary by stating what this skill handles directly vs. what it delegates, to reduce conflict risk with idea-ingest, media-ingest, and meeting-ingestion.

Dimension	Reasoning	Score
Specificity	Names the ingestion domain and concrete actions ('Route content', 'Detects input type', 'delegates') but stops short of listing multiple specific concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill does but offers no 'Use when...' or equivalent trigger guidance, so per the rubric a missing when-clause caps completeness at 2.	2 / 3
Trigger Term Quality	The phrasing relies on internal jargon ('specialized ingestion skills', 'input type', 'delegates') with no natural keywords a user would actually say, matching the 'no natural keywords; technical jargon or overly generic' anchor.	1 / 3
Distinctiveness Conflict Risk	'Route content to specialized ingestion skills' names a niche but explicitly routes to sibling skills (idea-ingest, media-ingest, meeting-ingestion) it could overlap with, fitting 'somewhat specific but could still overlap with similar skills.'	2 / 3
	Total	7 / 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/ingest/SKILL.md
Commit: 3fafb69

Reviewed: about 18 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.