Name: ingest
Rating: 48.8 (1 reviews)
Author: garrytan

Blog Docs Log inGet started

ingest

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

Quality

53%

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 ./plugin-variants/gbrain-coding/skills/ingest/SKILL.md

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

Quality

Content

63%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 a detailed, actionable ingestion playbook with concrete gbrain commands, explicit citation rules, and a test-first validation loop for batch work. Its main weaknesses are redundancy across sections and a monolithic structure that inlines reference-grade detail instead of splitting it into bundle files.

Suggestions

De-duplicate the Iron Law back-linking, citation, and raw-source-preservation rules into single canonical sections and reference them once elsewhere to improve conciseness.

Move the per-format media workflow variants, the citation-format catalog, and the .redirect.yaml spec into reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Add an inline validation checkpoint (e.g., verify back-links and citations before reporting INGESTED) into each media workflow so the per-format sequences match the test-first rigor of 'Test Before Bulk'.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and avoids explaining basic concepts, but it restates the Iron Law back-linking rule ~4 times, citation requirements ~3 times, and raw-source preservation repeatedly, matching 'mostly efficient but could be tightened'; it is not a 2 because the padding is redundancy rather than concept explanation.	3 / 5
Actionability	Concrete executable commands (gbrain search/get/put/sync, gbrain files upload-raw), a .redirect.yaml spec, and an output-format template cover the common cases with only minor gaps such as 'web_fetch or equivalent' and underspecified link-type semantics, matching 'mostly executable guidance; minor gaps'.	4 / 5
Workflow Clarity	Phases and the Entity Detection Protocol are well-sequenced, and 'Test Before Bulk' supplies an explicit test->read->fix->bulk validation loop for batch operations (avoiding the destructive/batch cap of 3), but the per-format media workflows lack integrated validation checkpoints, matching 'clear sequence with most checkpoints; minor validation gaps' rather than 5.	4 / 5
Progressive Disclosure	External references are clearly signaled and one level deep, but no bundle files exist and substantial detail (citation formats, the .redirect.yaml spec, five media-workflow variants) is inlined that could live in reference files, matching 'some structure; references present; content that should be separate is inline'.	3 / 5
	Total	14 / 20 Passed

Description

42%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 third-person and states a clear purpose as a router, but it lacks a 'Use when' trigger clause and natural user-facing keywords, leaving completeness and trigger-term quality weak. It is adequate but generic relative to the good examples.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when the user says ingest this, save this to brain, or asks to capture a meeting/article/video').

Replace generic verbs with more concrete operations or specific content types to lift specificity (e.g., 'Routes meetings, articles, videos, and documents to specialized ingestion skills and writes back-linked brain pages with source citations').

Include common synonyms or file mentions users would actually say to improve trigger-term coverage and reduce overlap with the sibling ingestion skills.

Dimension	Reasoning	Score
Specificity	Phrases 'Route content', 'Detects input type', and 'delegates' name the ingestion domain with a few actions, but they are high-level verbs rather than concrete operations, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor and falling short of the several-specific-actions anchor at 4.	3 / 5
Completeness	The description gives a clear 'what' (route, detect, delegate) but no 'when'/'Use when' clause, so per the missing-trigger-guidance cap it lands at the 'clear what but when missing or weakly implied' anchor rather than 4.	3 / 5
Trigger Term Quality	Only generic/technical terms ('content', 'ingestion skills', 'input type') appear with no natural user phrases, synonyms, or file extensions, matching 'one or two generic keywords; missing the natural phrases users say'; it is not a 1 because 'content' is a somewhat natural word rather than pure jargon.	2 / 5
Distinctiveness Conflict Risk	Self-identifying as a router gives it a niche, but the broad term 'content' and explicit delegation to sibling ingestion skills create real overlap risk, matching 'somewhat specific but could still overlap with similar skills' rather than the mostly-distinct anchor at 4.	3 / 5
	Total	11 / 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	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: plugin-variants/gbrain-coding/skills/ingest/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.