CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

kennel-handbook

Front-desk handbook for the Maple Street kennel, with its reference files.

Quality

51%

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 ./e2e/fixtures/agent-mcp/agent/skills/kennel-handbook/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 maximally lean but nearly empty of guidance: it states how files are served without ever instructing Claude what to do with them. With no actions, no workflow, and only directory-level pointers to the bundle, the skill leaves its entire purpose implicit.

Suggestions

Add at least a minimal instruction, e.g. 'Answer front-desk questions by consulting the files in `references/` before responding,' so the body instructs rather than merely describes.

Enumerate the bundle files with one-line descriptions (e.g. what latin1.md and logo.png are for) so the pointers are clearly signaled and navigable.

If any task has multiple steps (e.g. looking up a procedure then applying an exception), list them in sequence — even two or three numbered steps would give the skill an executable workflow.

DimensionReasoningScore

Conciseness

The body is two lines with zero padding, no over-explanation, and no concepts Claude already knows — every token is doing work. This matches anchor 5 (lean and efficient, every token earns its place).

5 / 5

Actionability

The only body content — "The files under `references/` and `assets/` are served byte for byte" — is a factual statement, not instruction: no code, commands, or steps for what to do with the handbook. This matches anchor 1 (only describes rather than instructs), and there is not even a high-level hint that would justify 2.

1 / 5

Workflow Clarity

No sequence, steps, or single unambiguous action is defined anywhere in the body; the simple-skill exception cannot apply because no action at all is stated. This matches anchor 1 (steps missing or incoherent, no sequence).

1 / 5

Progressive Disclosure

The bundle files exist (references/empty.md, references/latin1.md, assets/logo.png) and the body does point at the right directories, but it never names or describes any individual file, so discovery and navigation are weak — references present but not clearly signaled. This matches anchor 3, below anchor 4 (references mostly clear) because a reader cannot tell what is in each file.

3 / 5

Total

10

/

20

Passed

Description

40%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 short and names a highly distinct niche, but it describes a document rather than any capability, omits all action verbs, and provides no 'Use when' trigger guidance. It functions closer to a title than a skill description, leaving both what the skill does and when to use it undefined.

Suggestions

State concrete actions the skill enables, e.g. 'Look up check-in procedures, feeding schedules, and medication policies for the Maple Street kennel' instead of naming only a document.

Add an explicit trigger clause, e.g. 'Use when the user asks about Maple Street kennel operations, boarding procedures, or front-desk policies.'

Replace the filler 'with its reference files' with what those reference files contain so users (and Claude) can match queries against the actual content.

DimensionReasoningScore

Specificity

The description names a concrete domain ("Front-desk handbook for the Maple Street kennel") but lists no actions or capabilities whatsoever — "with its reference files" is filler, not an action. It sits at anchor 2 (names the domain, minimal actions), not 1 (the domain is concrete, not pure abstraction) and not 3 (no concrete actions are stated).

2 / 5

Completeness

The 'what' is vague — it names a document type rather than any capability the skill provides — and the 'when' is completely absent (no "Use when..." clause, which caps completeness at 3 regardless). This matches anchor 2 (vague what, no when) and is below anchor 3, which requires a clear 'what'.

2 / 5

Trigger Term Quality

Some natural domain keywords are present ("kennel", "front-desk", "handbook") but common task-level phrases a user would actually say (check-in, feeding, medication, boarding) and their synonyms are entirely missing. This matches anchor 3 (some relevant keywords, missing common variations), and falls short of 4 (no good keyword coverage).

3 / 5

Distinctiveness Conflict Risk

The niche ("Maple Street kennel" front desk) is highly specific and would rarely conflict with other skills, but no explicit distinct trigger phrases exist to lock in distinctiveness. This places it at anchor 4 (mostly distinct, minor overlap risk) rather than anchor 5, which requires clear distinct triggers.

4 / 5

Total

11

/

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

vercel/eve

Path

e2e/fixtures/agent-mcp/agent/skills/kennel-handbook/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.