CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

publish

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

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/publish/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 strong, executable reference for a deterministic CLI: copy-paste commands for every workflow, concrete failure handling with specific error codes, and a defined output format. The only weaknesses are minor: a thrice-repeated encryption-default rule, an off-task philosophy link, and the absence of an output-verification step.

DimensionReasoningScore

Conciseness

The body is dominated by tight command examples and tables, but the encryption default is stated three times ("Default is always encrypted unless the user explicitly requests", "Default to password-protected unless the user explicitly says", "Publishing without encryption. ... Default to password-protected") and the intro links off-task to a "Thin Harness, Fat Skills" architecture-philosophy post. These are minor trimmable instances rather than the broader padding of the anchor below.

4 / 5

Actionability

Every workflow is backed by copy-paste-ready commands ("gbrain publish brain/companies/acme.md --password 'secret123' --out /tmp/acme-share.html", "gbrain files signed-url shares/acme/acme.html") plus a concrete output template and specific error responses ("run gbrain doctor --json"). The examples cover the common cases (basic, password, title, output path, upload, signed URL) exactly as the top anchor requires.

5 / 5

Workflow Clarity

Options A-D give clear sequences for each sharing path, and "When it fails" supplies error-recovery feedback ("resolve the real slug first; never publish a guessed page"; handle "bucket_not_found" via "gbrain doctor --json"). It falls short of the top anchor only because there is no explicit verification checkpoint on the published output (e.g., confirming the file is encrypted) before reporting.

4 / 5

Progressive Disclosure

A well-organized single-file guide with clearly labeled sections and no bundle files to split; the single external reference is clearly signaled. It misses the top anchor because that reference ("../conventions/agent-operator-protocol.md") points outside the skill bundle where it may not resolve, and inline material like the crypto parameter list is borderline separable.

4 / 5

Total

17

/

20

Passed

Description

57%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 concise, in third person, and clearly distinct thanks to its brain-specific domain language. Its main weakness is discoverability: it states a single concrete capability with no trigger guidance in the description itself, relying on a separate triggers field for the "when".

Suggestions

Append an explicit trigger clause to the description, e.g., "Use when the user asks to share, publish, or create a link to a brain page."

Fold the natural phrases from the triggers field ("publish", "create shareable link") into the description itself so retrieval does not depend on a separate field.

Replace "beautiful" with a concrete capability such as "self-contained HTML with private metadata stripped" to strengthen specificity.

DimensionReasoningScore

Specificity

The description names the domain ("brain pages") and the output ("password-protected HTML") with essentially one concrete action ("Share"), while "beautiful" is fluffy filler. This matches the anchor for a domain plus 1-2 concrete actions rather than the anchor above, which lists several specific actions.

3 / 5

Completeness

The "what" is clear ("Share brain pages as beautiful password-protected HTML with zero LLM calls") but the description contains no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It is not the score below because the "what" is concrete, not vague.

3 / 5

Trigger Term Quality

"Share" is a natural keyword a user would say, but the other common phrases ("publish", "shareable link", "export") exist only in the separate triggers field, not in the description itself. This lands on the anchor for some relevant keywords with missing common variations rather than the good-coverage anchor above.

3 / 5

Distinctiveness Conflict Risk

"Brain pages" combined with password-protected HTML publishing carves out a clear niche with distinct terminology, making accidental triggering of unrelated skills unlikely. This fits the top anchor for a clear niche with minimal conflict risk rather than the anchor below, which admits minor overlap with closely related skills.

5 / 5

Total

14

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 2 suspicious

Warning

Total

14

/

16

Passed

Repository

garrytan/gbrain

Path

skills/publish/SKILL.md

Reviewed

Table of Contents

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.