CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-only-skill

An agent-only skill not intended for direct user invocation

26

Quality

16%

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 ./tests/fixtures/sample-plugin/skills/agent-only-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

33%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 a placeholder: it is token-efficient and free of structural/nesting problems, but it offers no actionable guidance or workflow. It conveys essentially nothing for Claude to act on.

Suggestions

Replace the placeholder body with concrete, executable guidance or code for the skill's task.

If the skill involves multi-step or batch operations, add an explicit sequence with validation checkpoints.

Document any references to bundle files clearly so progressive disclosure remains intentional rather than merely absent.

DimensionReasoningScore

Conciseness

The single line "Agent-only skill body." is maximally lean with no padding or over-explanation of known concepts; the lone sentence carries little load, but it never wastes tokens.

4 / 5

Actionability

The body provides no concrete code, commands, or executable guidance — it only describes rather than instructs.

1 / 5

Workflow Clarity

There are no steps, sequence, or validation checkpoints of any kind — the body is a single non-instructional sentence.

1 / 5

Progressive Disclosure

No bundle files exist and the body references none; nothing is inlined that belongs in a separate file and there are no nested references, so the trivial one-line body has no organization problems.

4 / 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 conveys only the skill's invocation mode, not its purpose or triggers, and fails every anchor of specificity, completeness, and distinctiveness. It reads as a placeholder rather than a usable skill description.

Suggestions

State the concrete actions or capabilities the skill performs (e.g., what it does when invoked by an agent).

Add an explicit trigger clause indicating when an agent should select this skill.

Replace the generic framing with domain-specific keywords that distinguish it from other agent-only skills.

DimensionReasoningScore

Specificity

The phrase "An agent-only skill not intended for direct user invocation" names no concrete actions or capabilities — it only describes the skill's invocation mode, never what it does.

1 / 5

Completeness

It offers only a vague notion of "what" (an agent-only skill) and entirely omits "when" Claude should use it — no "Use when…" clause is present.

1 / 5

Trigger Term Quality

There are no natural keywords a user would actually say to trigger this skill; the language is meta (about invocation) rather than domain-oriented.

1 / 5

Distinctiveness Conflict Risk

"An agent-only skill not intended for direct user invocation" is entirely generic and would overlap with virtually any other agent-only skill.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
EveryInc/compound-engineering-plugin
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.