retrieval-reflex

When/what to retrieve — open the brain page for a salient entity before answering from memory.

Quality

70%

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 ./recipes/retrieval-reflex/skills/retrieval-reflex/SKILL.md

Quality

Content

78%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 tight, well-structured reflex skill that gives actionable, escalating retrieval guidance and appropriate stop conditions, with only minor padding and a few underspecified steps. It earns full marks on progressive disclosure for a simple skill of its size.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence throughout, with only minor motivational padding (the opening address-book analogy and 'The brain probably has the data') that could be trimmed.	4 / 5
Actionability	Gives concrete commands (get_page <slug>, graph/backlinks) and a clear escalation ladder, with minor gaps such as CLI equivalents living only in a frontmatter comment and 'do a quick resolve' being underspecified.	4 / 5
Workflow Clarity	Sequences retrieval as a 3-level escalation with explicit stop conditions plus a failure-recovery cue; as a non-destructive read it lacks formal validation checkpoints but does not need them.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references, well-organized into focused sections; the only references are clearly-signaled one-level cross-skill pointers ('See also').	5 / 5
	Total	17 / 20 Passed

Description

62%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 crisply conveys both what and when for a narrow retrieval reflex, but relies on internal vocabulary ('salient entity', 'brain page') that users would not naturally say, and does not itself distinguish the skill from the related query skill.

Suggestions

Add one or two natural user-side trigger phrases or synonyms so the description reads in terms a user would actually say.

Include a brief disambiguation from the sibling query/search skill directly in the description text rather than only in comments.

List a second concrete action (e.g., pull linked neighbors/backlinks) to raise specificity from a single action to broader coverage.

Dimension	Reasoning	Score
Specificity	Names the retrieval/brain-page domain with one concrete action ('open the brain page for a salient entity before answering from memory'), but does not enumerate multiple specific actions.	3 / 5
Completeness	Explicitly answers both what ('open the brain page…') and when ('When/what to retrieve… before answering from memory'), though the when-guidance is somewhat abstract rather than concrete trigger phrases.	4 / 5
Trigger Term Quality	Relevant terms (salient entity, brain page, retrieve, memory) are present but read as internal jargon rather than natural phrases a user would say.	3 / 5
Distinctiveness Conflict Risk	Clear niche (retrieve-before-answering reflex for brain pages) with minor overlap risk against the sibling query/search skill, which the description field itself does not disambiguate.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: garrytan/gbrain
Path: recipes/retrieval-reflex/skills/retrieval-reflex/SKILL.md
Commit: 8c70f62

Reviewed: 3 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.