publish

Share brain pages as beautiful password-protected HTML with zero LLM calls

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

76%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 content is highly actionable with copy-paste commands and clear workflows, but lacks an explicit validation checkpoint before publishing private content, which caps workflow clarity. It is otherwise concise and well-structured.

Suggestions

Add an explicit verification step before sharing, e.g. after publishing, confirm the HTML contains no frontmatter/citations/timeline and that encryption is enabled when required, before delivering the link.

De-duplicate the 'open / no password / public' exception language (it appears in Contract, Default, and Anti-Patterns) into a single defined location to tighten conciseness.

Consolidate the workflow_clarity cap by adding a short validate -> fix -> retry loop referencing the 'What Gets Stripped' table as the acceptance checklist.

Dimension	Reasoning	Score
Conciseness	The body is efficient and mostly lean, but the 'open / no password / public' phrasing and 'beautiful' descriptor recur across the Contract, Default, and Anti-Patterns sections, giving minor over-explanation that could be trimmed — fitting score 4 rather than 5.	4 / 5
Actionability	Copy-paste-ready `gbrain publish ...` commands with flags populate the Quick Reference and four sharing workflows, and the expected Output Format is fully specified, covering the common cases as the score-5 anchor requires.	5 / 5
Workflow Clarity	Workflows A–D are clearly sequenced, but publishing private brain content is an outward-facing/destructive operation with no explicit verify-the-output-contains-no-private-data checkpoint, so per the destructive-operations cap workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	No bundle files exist, so the single self-contained SKILL.md with clear section headers (Contract, Quick Reference, Workflows, Anti-Patterns) is well organized with only minor structure gaps, matching score 4.	4 / 5
	Total	16 / 20 Passed

Description

53%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 clearly states what the skill does but omits any explicit 'when to use' trigger guidance, capping completeness and trigger quality at the midpoint. It is reasonably distinct from sibling skills.

Suggestions

Add an explicit 'Use when ...' clause with natural trigger phrases (e.g. 'Use when the user asks to share, publish, or send a brain page to someone outside the brain').

Include natural synonyms users actually say ('share', 'publish', 'send', 'export', 'create a link') rather than only 'share' and the technical 'password-protected HTML'.

Optionally list a couple more concrete actions (strip private metadata, auto-generate passwords) to lift specificity from 3 to 4.

Dimension	Reasoning	Score
Specificity	Names the domain ('brain pages') and two concrete actions ('Share ... as ... HTML', 'password-protected'), but does not enumerate several specific actions, matching the score-3 anchor.	3 / 5
Completeness	The 'what' is clear (share brain pages as password-protected HTML) but there is no 'Use when...' or explicit trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Contains 'share' and 'HTML' but lacks common natural variations/synonyms a user would say (e.g. 'publish', 'send', 'export'), fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The niche (publishing brain pages to self-contained encrypted HTML with zero LLM calls) is mostly distinct with only minor overlap risk against generic HTML/share skills, matching the score-4 anchor.	4 / 5
	Total	13 / 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 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/publish/SKILL.md
Commit: 055ac6c

Reviewed: about 2 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.