brain-ingest-gate

Pre-write quality gate for content entering the brain. No raw copies: a bare cp/mv into the brain repo is a bug. Before any new page lands, resolve named entities registry-first (a vector score is a floor for prose, never a gate for named things), then run the read-the-top-hit dedup decision tree (clear-dup / plausible-dup / clear). Owns dedup; delegates enrichment to the shipped ingestion skills. Routing convention, not an operation-boundary enforcement.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugin-variants/gbrain-coding/skills/brain-ingest-gate/SKILL.md

Quality

Content

67%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 well-structured, actionable gate with concrete commands, a clear two-stage workflow, a decision tree, and explicit verification with a feedback loop — appropriate for a batch/mutating skill. Its main weakness is conciseness: rationale and restated-contract sections add tokens without proportional value.

Suggestions

Trim or collapse the 'Why gbrain needs this gate' and 'Why a gate and not a memory note' rationale sections to one or two lines each, or move them to a reference file.

Remove or condense the Contract section that self-admittedly restates the body ('this section exists for the conformance test'), keeping only the conformance-critical guarantees.

Make the verification feedback loop an explicit pass/fail gate ('do not declare ingest done until check-backlinks check reports 0 gaps') rather than a conditional note.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but includes rationale sections ('Why gbrain needs this gate', 'Why a gate and not a memory note') and a Contract section that explicitly restates the body ('this section exists for the conformance test'), adding tokens that could be trimmed. Not 4 because several padded passages do not earn their place.	3 / 5
Actionability	Provides concrete copy-paste commands throughout ('gbrain entity "<name>"', 'gbrain search "<core claim>" --limit 5', 'gbrain get <slug>', 'gbrain check-backlinks check'), plus a band table, decision tree, and full output-format example. Not 5 because a few steps remain abstract ('Extract the core claim — 1-2 sentences').	4 / 5
Workflow Clarity	Clear two-gate sequence (Named-Entity Resolution FIRST, Dedup SECOND) with a decision tree and an explicit Verification pass plus a feedback loop ('If check-backlinks check reports gaps ... route back through enrich'). Not 5 because some checkpoints are implied rather than framed as explicit pass/fail gates.	4 / 5
Progressive Disclosure	Single-file skill (no references/scripts/assets bundle present) with well-sectioned content and a delegation table that clearly signals one-level-deep references to sibling skills and conventions. Not 5 because a few inline sections (e.g. the full Contract list) could be trimmed or externalized.	4 / 5
	Total	15 / 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 specific and well-scoped to a clear niche, but lacks an explicit 'Use when...' trigger clause and buries natural user phrasings in the separate triggers field, capping completeness and trigger-term quality. It is strong on what the skill does but weaker on when a user would invoke it.

Suggestions

Add an explicit 'Use when ...' clause to the description naming concrete trigger phrases (e.g. 'Use when moving files into the brain, bulk-importing, or checking whether a page already exists before writing').

Surface 1-2 natural user phrases ('is this already in the brain', 'dedup before saving') directly in the description text rather than only in the triggers field.

Soften jargon like 'registry-first' and 'read-the-top-hit dedup decision tree' with a plain-language gloss so the description reads naturally to a user.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('resolve named entities registry-first', 'run the read-the-top-hit dedup decision tree (clear-dup / plausible-dup / clear)', 'delegates enrichment to the shipped ingestion skills'), with only minor coverage gaps. Not 5 because coverage is not fully comprehensive and some actions are stated abstractly.	4 / 5
Completeness	Has a clear 'what' (pre-write quality gate with named-entity resolution and dedup) but 'when' is only weakly implied via 'Before any new page lands' with no explicit 'Use when...' clause, which per the rubric caps completeness at 3. Not 4 because there is no explicit trigger guidance.	3 / 5
Trigger Term Quality	Includes some relevant natural terms ('content entering the brain', 'raw copies', 'cp/mv into the brain repo', 'dedup') but leans technical ('registry-first', 'named entities') and omits common user phrasings, which live in the triggers field rather than the description. Not 4 because several natural synonyms users would say are missing from the description text itself.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (brain ingest dedup/resolution gate) and explicitly distinguishes itself from sibling skills ('Owns dedup; delegates enrichment'), leaving only minor overlap risk with the ingestion skills it delegates to. Not 5 because it shares trigger territory with those closely related skills.	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: 16 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: plugin-variants/gbrain-coding/skills/brain-ingest-gate/SKILL.md
Commit: 43597b1

Reviewed: 1 day 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.