CtrlK
BlogDocsLog inGet started
Tessl Logo

demo

Demo skill that loads.

30

Quality

22%

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 ./plugins/claude-native-toolkit/skills/plugin-reload/examples/loadable-plugin/skills/demo/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

45%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 bare placeholder heading: maximally concise and structurally harmless, but it contains zero actionable guidance or workflow content. It reads as a loading test fixture rather than a usable skill body.

Suggestions

Add a brief instruction or code block describing the skill's single task so a reader (and Claude) knows what to actually do — this is the primary gap driving the actionability score.

If the skill has any multi-step or batch behavior, add a short sequenced workflow with an explicit validation checkpoint, since even simple skills need one unambiguous action described.

Once content grows, keep the SKILL.md body as a concise overview and move detailed material to clearly signaled one-level-deep reference files to preserve the current structural cleanliness.

DimensionReasoningScore

Conciseness

The body is a single two-token heading ("# Demo") with zero padding, no over-explanation, and nothing written that Claude already knows. It matches the lean-and-efficient anchor where every token earns its place; there is simply nothing to trim.

5 / 5

Actionability

The body provides no code, commands, or guidance of any kind — not even a description of what to do. This matches anchor 1 (entirely vague or abstract; no concrete code or commands; only describes rather than instructs); there is not even the minimal high-level hint of anchor 2.

1 / 5

Workflow Clarity

No steps, sequence, or task whatsoever are present. This matches anchor 1 (steps missing or incoherent; no sequence; no validation). The simple-skill exception cannot apply because there is no single unambiguous action to clarify.

1 / 5

Progressive Disclosure

The skill is under 50 lines with no content that needs external references, no inlined material that belongs in separate files, and no nested references; the scoring note allows a 5 for such skills when content is well-organized, and nothing here is misplaced. Anti-drift check: anchor 4's "minor organization gaps" would require actual content to misplace, which does not exist.

5 / 5

Total

12

/

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 a placeholder with no informational value: it names no concrete capabilities, no trigger terms, no use conditions, and no distinguishing niche. It is essentially equivalent to the bad example "Does stuff with files" in specificity, though even shorter.

Suggestions

State 2-4 concrete capabilities in third person (e.g. "Validates skill bundle structure, checks frontmatter fields, and reports missing files").

Add an explicit "Use when..." clause with natural trigger phrases users would actually say (file names, task keywords) to address the missing 'when' that currently caps completeness at the bottom of the scale.

Name the specific domain or artifacts the skill works with so it is distinguishable from other skills and unlikely to trigger for the wrong one.

DimensionReasoningScore

Specificity

"Demo skill that loads." contains no concrete actions or real domain; "loads" is not a capability. This matches the anchor for entirely vague, pure abstract language (e.g. "Helps with documents") and does not rise to anchor 2, which requires naming a real domain with at least generic actions.

1 / 5

Completeness

The "what" ("demo skill") is extremely vague and the "when" is completely absent with no "Use when..." clause or equivalent. Both what and when are missing or extremely vague, matching anchor 1; the missing-trigger cap of 3 is moot since the score is already below it.

1 / 5

Trigger Term Quality

There are no natural keywords a user would say when needing this skill; "Demo skill" and "loads" are entirely generic. This matches the lowest anchor (no natural keywords, only generic language), not anchor 2, which expects at least one or two generic keywords serving as triggers.

1 / 5

Distinctiveness Conflict Risk

"Demo skill that loads." is entirely generic and would conflict with virtually any other demo or placeholder skill. This matches anchor 1 (entirely generic, conflicts with virtually any skill); it lacks even the broad domain specificity of anchor 2.

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
JaviMontano/claude-plugins
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.