CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa

Name is exactly 64 bytes, the valid upper boundary.

28

Quality

35%

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 ./crates/skill-validator-rs/tests/golden-corpus/fixtures/boundary/aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

37%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 content-free: two words that instruct nothing. While maximally token-efficient, it fails actionability and workflow clarity completely, and its single heading conveys no organization. It needs actual executable guidance for whatever the skill is supposed to do.

Suggestions

Replace "Use it." with concrete, executable guidance — specific commands, code, or unambiguous instructions covering the skill's common cases.

If the task involves multiple steps, lay them out as an explicit numbered sequence with validation checkpoints for risky operations.

Give the section heading a meaningful, task-relevant name (e.g., "## Quick start") and organize any detail content into clearly signaled sections or reference files.

DimensionReasoningScore

Conciseness

The body ("# Body\n\nUse it.") contains zero verbosity, padding, or explanation of things Claude already knows — none of the verbosity-based failure modes at anchors 1–4 apply. The lack of any substance is penalized under actionability and workflow_clarity, not here.

5 / 5

Actionability

"Use it." is entirely vague — no concrete code, commands, or specific steps, and it doesn't even specify what "it" refers to. This matches anchor 1 (entirely vague, no concrete guidance); anchor 2 at least gives high-level hints toward execution.

1 / 5

Workflow Clarity

No steps or sequence of any kind are present — the body is a single instruction-free sentence. The simple-skill exception cannot apply because "Use it." is not an unambiguous single action; it specifies nothing about what to do.

1 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files, but the lone heading "# Body" is uninformative and provides no organizational or navigation value, so the simple-skill path to 5 (well-organized sections) is not met. It has minimal structure without inlined misplaced content, landing at anchor 3 rather than 4, which requires appropriately placed content and clear references.

3 / 5

Total

10

/

20

Passed

Description

0%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 meta-commentary about the frontmatter name length, not a description of the skill. It fails all four dimensions: no capabilities, no triggers, no what/when, and no distinctiveness. A complete rewrite stating concrete actions and "Use when..." triggers is required.

Suggestions

Replace the description with concrete third-person capability statements (e.g., 'Validates X, generates Y') instead of commentary about the name field's byte length.

Add an explicit 'Use when...' clause with natural trigger phrases and synonyms users would actually say when they need this skill.

Include domain-specific keywords and file extensions so the skill is distinguishable from similar skills and triggers reliably.

DimensionReasoningScore

Specificity

The description ("Name is exactly 64 bytes, the valid upper boundary.") states a fact about the frontmatter name field's length rather than naming any capability or action. It matches anchor 1 (no concrete actions, pure abstract language); anchor 2 requires at least naming a domain of operation, which is absent.

1 / 5

Completeness

Neither "what" (no capability is described) nor "when" (no trigger guidance) is present — the sentence describes the name field, not the skill. Anchor 2 requires at least a vague "what"; even that is missing, and the missing 'Use when...' clause cap applies.

1 / 5

Trigger Term Quality

No natural keywords a user would say when needing this skill — only meta-jargon ("Name", "64 bytes", "upper boundary") about a length constraint. This matches anchor 1 (no natural keywords, only technical jargon); anchor 2's generic keywords like "Works with files" at least gesture at a task domain.

1 / 5

Distinctiveness Conflict Risk

The description conveys no functional information, giving no basis to distinguish this skill from any other or to trigger it correctly — entirely generic from a triggering standpoint. Anchor 2's "very broad" skills at least imply a domain; this implies none.

1 / 5

Total

4

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

pantheon-org/tekhne

Path

crates/skill-validator-rs/tests/golden-corpus/fixtures/boundary/aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/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.