warnings-only-skill

A skill that produces warnings but no errors.

Quality

22%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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/testdata/warnings-only-skill/SKILL.md

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 token-efficient and appropriately sized for a single-file skill, but it contains no actionable guidance — the entire instruction is "Follow the instructions to get started" with no actual instructions. It is a structural shell with well-organized sections and nothing inside them.

Suggestions

Replace "Follow the instructions to get started" with the actual instructions: concrete commands, code, or specific step-by-step guidance the skill exists to provide.

Define what the skill's single task actually is so the workflow is unambiguous rather than referencing undefined "instructions".

Clarify whether the extras/ note is user-relevant guidance or test scaffolding commentary; if it is not part of the skill's function, remove it from the body.

Dimension	Reasoning	Score
Conciseness	The body is roughly six lines with zero padding and no explanation of concepts Claude already knows; every sentence is short and direct. Matches anchor 5 ("Lean and efficient; every token earns its place") for token efficiency, even though what it says is vague.	5 / 5
Actionability	"Follow the instructions to get started" is entirely vague — no code, commands, or specific steps anywhere; the body describes rather than instructs. Exactly matches anchor 1.	1 / 5
Workflow Clarity	No steps or sequence are present at all. The simple-skill exception cannot apply because there is no unambiguous single action to perform — the only instruction is an undefined reference to "the instructions".	1 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and no reference paths are mentioned that would need verifying (the extras/ note is informational, not a link). Per the rubric guideline, well-organized sections in a short single-file skill score 5.	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 meta-statement about the skill's validation profile rather than a description of what it does or when to use it. It fails all four dimensions at the lowest anchor: no concrete actions, no trigger terms, no what/when coverage, and total overlap risk with other skills.

Suggestions

State concrete third-person capabilities (e.g., what the skill actually does) instead of describing its validation behavior as "produces warnings but no errors".

Add an explicit trigger clause such as "Use when..." listing natural phrases a user would say when they need this skill.

Include domain-specific keywords or file extensions so the skill is distinguishable from others and surfaces for the right requests.

Dimension	Reasoning	Score
Specificity	"A skill that produces warnings but no errors" names no concrete action or capability — it is pure abstract language about behavior. It does not even reach anchor 2, which requires naming a domain with minimal actions.	1 / 5
Completeness	Neither "what" (no capability described) nor "when" (no trigger guidance whatsoever) is answered; the description characterizes validation behavior rather than function. Far below the anchor-3 cap for a missing "Use when" clause.	1 / 5
Trigger Term Quality	"warnings" and "errors" are entirely generic terms; no natural keyword or phrase a user would say when needing this skill is present. Matches anchor 1 ("only technical jargon or entirely generic language").	1 / 5
Distinctiveness Conflict Risk	The description is entirely generic and would overlap with virtually any other skill; nothing distinguishes it. Matches anchor 1 ("would conflict with virtually any skill").	1 / 5
	Total	4 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: pantheon-org/tekhne
Path: crates/skill-validator-rs/tests/golden-corpus/fixtures/testdata/warnings-only-skill/SKILL.md
Commit: a1083f4

Reviewed: 2 hours ago

Table of Contents

Discovery Implementation Validation

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.