CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

my-skill

When to load this skill. Agents read this line to decide whether to load it, so be specific.

Quality

32%

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 ./docs/authoring/templates/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 body is an unfilled template: one heading and one placeholder sentence. Its only virtue is that it wastes almost no tokens and has no structural problems; it contains no instructions, commands, examples, or workflow an agent could act on. Every substantive dimension (actionability, workflow clarity) is at the floor.

Suggestions

Replace "Put the instructions the agent needs here" with the actual instructions — concrete, executable commands or code covering the skill's common cases.

If the skill involves a multi-step process, lay it out as an explicit numbered sequence with validation checkpoints, especially for batch or destructive operations (which would otherwise cap workflow clarity at 3).

Fill in the heading and overview so the body states what the skill does and when to apply it; if detailed material exists, move it into references/ files and link them one level deep from SKILL.md.

DimensionReasoningScore

Conciseness

The 3-line body ("# My skill" / "What the skill does. Put the instructions the agent needs here.") has no verbosity, padding, or explanations of concepts Claude already knows. It is not a 5 because anchor 5 requires "every token earns its place" — the two placeholder sentences are authoring instructions that deliver nothing to the agent, i.e., a minor instance of content that could be trimmed; it is not a 3 because there is no unnecessary explanation, only placeholder text.

4 / 5

Actionability

"What the skill does. Put the instructions the agent needs here." provides no concrete code, commands, or steps — it is placeholder that only gestures at where instructions would go. This matches anchor 1 ("Entirely vague or abstract; no concrete code or commands; only describes rather than instructs"); even anchor 2's high-level hints about what to do are absent.

1 / 5

Workflow Clarity

No steps or sequence of any kind exist in the body — there is no workflow to evaluate. The simple-skill exception (a single unambiguous action can score 5) does not apply because no action is described at all, so anchor 1 ("Steps missing or incoherent; no sequence") is the best fit.

1 / 5

Progressive Disclosure

The body is 3 lines with no bundle files (references/, scripts/, assets/ are absent) and no file references, so it has zero structural defects — nothing inlined that belongs in a separate file, no buried or nested references. It is not 5 because anchor 5 (and the simple-skill exception, which requires the content to be clear and well-organized) presupposes a clear overview, and a placeholder sentence is not one; it is not 3 because the defects in that anchor (unclearly signaled references, inline content that should be separate) are all absent.

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 field contains the unfilled template's authoring instructions rather than an actual skill description: it explains what the description field is for instead of stating any capability, domain, or trigger. Every dimension scores at the floor because there is no skill content to evaluate.

Suggestions

Replace the placeholder with concrete third-person actions naming the skill's domain and capabilities (e.g., "Extracts X from Y files, merges Z, ..."), modeled on the rubric's good examples.

Add an explicit "Use when..." trigger clause containing the natural words, synonyms, and file extensions a user would actually say when they need this skill.

Delete the meta-text about the field itself ("Agents read this line to decide whether to load it, so be specific.") — it describes the description field, not the skill, and consumes the entire description budget.

DimensionReasoningScore

Specificity

The description text — "When to load this skill. Agents read this line to decide whether to load it, so be specific." — is meta-guidance about the description field itself; it names no domain and no concrete actions, matching the anchor "Entirely vague; no concrete actions; pure abstract language" (example: "Helps with documents"). It cannot be a 2 because that anchor requires naming a domain, which this never does.

1 / 5

Completeness

Neither "what does this do" nor "when should it be used" is answered — the text explains how the field is consumed ("Agents read this line to decide whether to load it") rather than what the skill does or when to trigger it. Anchor 1 ("Missing both what and when") applies directly; the 'Use when...' cap at 3 is irrelevant since the score is already at the floor.

1 / 5

Trigger Term Quality

There are no natural keywords or phrases a user would say when needing this skill — the text is template scaffolding, not trigger language. This matches anchor 1 ("No natural keywords; only technical jargon or entirely generic language"); anchor 2 would require at least one or two generic domain keywords, and none are present.

1 / 5

Distinctiveness Conflict Risk

The description is entirely generic placeholder text with no niche, domain, or distinguishing triggers, so it provides no basis for distinguishing this skill from any other — anchor 1 ("Entirely generic; would conflict with virtually any skill"). Anchor 2 would require at least broad domain overlap language such as "Helps with document files," which is absent.

1 / 5

Total

4

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

vanillagreencom/kendex

Path

docs/authoring/templates/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.