fence-unclosed

Body opens a fenced code block that is never closed.

Quality

29%

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/boundary/fence-unclosed/SKILL.md

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 token-minimal but substantively empty: it contains no instructions, no meaningful commands, and no workflow, and its unclosed code fence would swallow subsequent content in rendering. It functions as a formatting defect fixture rather than usable skill guidance.

Suggestions

Close the bash code fence so the body renders correctly and subsequent content is not swallowed as code.

Replace the placeholder commands (`echo hello`, `exit 0`) with executable guidance that actually performs the skill's task.

Add a short, clearly sequenced set of instructions (even 2–3 numbered steps) so the skill's single action is unambiguous, and rename the generic '# Body' header to describe the actual task.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean with zero over-explanation of concepts Claude already knows, matching 'efficient; minor instances that could be trimmed'. It falls short of anchor 5 because the unclosed fence undermines rendering clarity, so not every token cleanly earns its place.	4 / 5
Actionability	The body contains literal shell commands (`echo hello`, `exit 0`) but they are placeholder no-ops that instruct nothing about any real task, matching 'minimal concrete guidance; missing the specific steps to execute'. It is above anchor 1 because some executable code is present, but below anchor 3 because the guidance is not merely incomplete — it is unrelated to any task.	2 / 5
Workflow Clarity	No steps or sequence of any kind are present — the body is a bare header and an orphaned code block — matching 'steps missing or incoherent; no sequence'. The simple-skill exception does not apply because no unambiguous single action is stated.	1 / 5
Progressive Disclosure	There are no bundle files and nothing that should be split out, but the body's only structure is a generic '# Body' header and a broken fence, so it does not meet 'well-organized sections' required for a 5 under the simple-skill exception. Anchor 3 ('some structure but could be better organized') is the best fit; anchor 4 requires mostly clear organization, which the generic header and malformed fencing do not provide.	3 / 5
	Total	10 / 20 Passed

Description

21%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 reads as a defect report about the SKILL.md file rather than a description of a skill's capabilities. It contains no 'what does this skill do' statement, no 'when to use it' guidance, and no natural trigger terms a user would say.

Suggestions

State the skill's concrete capabilities in third person (e.g., 'Validates and repairs markdown code fences in documents') instead of describing the file's formatting defect.

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say, such as 'Use when fixing broken markdown formatting or unbalanced code fences.'

Include user-facing synonyms and file extensions (e.g., 'markdown, .md, code blocks, fenced blocks') to improve trigger-term coverage and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names a concrete technical condition ("opens a fenced code block that is never closed") but states no action or capability the skill performs, matching the anchor 'names the domain but actions are minimal or generic'. It is not anchor 1 because the language is specific rather than vague, and not anchor 3 because no concrete skill action is listed.	2 / 5
Completeness	There is no 'Use when...' clause or equivalent trigger guidance (capping completeness at 3), and the 'what' describes a file formatting defect rather than what the skill does for the user. This sits between anchor 1 (both missing/vague) and anchor 3 (clear what) — something concrete is stated, but it is not a capability, so 2 fits best.	2 / 5
Trigger Term Quality	"fenced code block" and "never closed" are technical jargon no user would naturally say when they need a skill, matching 'no natural keywords; only technical jargon'. It cannot be anchor 2 because not even one generic user-facing keyword is present.	1 / 5
Distinctiveness Conflict Risk	The terms are narrowly specific, so overlap with other skills' triggers is low, but the description fails to carve out a functional niche that would reliably route the right requests to it. Anchor 3 ('somewhat specific but could still overlap') is the closest fit; anchor 4 requires a mostly distinct capability statement.	3 / 5
	Total	8 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pantheon-org/tekhne
Path: crates/skill-validator-rs/tests/golden-corpus/fixtures/boundary/fence-unclosed/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.