crlf-lines

Use when testing Windows CRLF line endings.

Quality

43%

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 ./test/fixtures/skills/crlf-lines/SKILL.md

Quality

Content

47%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 concise and appropriately self-contained for a simple skill, but it lacks executable guidance and validation checkpoints: the steps are vague and the sole code example is a non-functional placeholder. Providing specific commands and a verify step would substantially improve actionability and workflow clarity.

Suggestions

Replace 'Run tests on Windows' and 'echo crlf' with concrete, executable commands that actually exercise CRLF handling (e.g. a real test invocation or a grep/sed check for '\r\n').

Add an explicit validation/verification step with a feedback loop, e.g. 'Verify output preserves CRLF; if LF appears, re-run with the CRLF-preserving flag.'

Tie the prose directives ('MUST handle CRLF', 'MUST NOT assume LF only') directly to the numbered steps so the workflow reads as one coherent sequence.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation and assumes competence, but 'Ensure parsing works' is slightly redundant with the MUST directives and the 'echo crlf' block is trimmable filler, fitting the 'efficient; minor instances that could be trimmed' anchor.	4 / 5
Actionability	Steps like 'Run tests on Windows' and 'Verify frontmatter parsing' are high-level hints missing the specific commands to execute, and the only code block ('echo crlf') is non-functional, matching the 'minimal concrete guidance; missing specific steps' anchor.	2 / 5
Workflow Clarity	A rough two-step sequence is present but the steps are poorly defined and validation is absent, matching the 'rough sequence present but many gaps; validation absent' anchor rather than the checkpoint-bearing anchors above.	2 / 5
Progressive Disclosure	The skill is short and self-contained with no external references needed, which is appropriate; organization is reasonable under a single header but the loose mix of list, prose directive, and code block could be tighter, fitting the 'good structure; minor organization gaps' anchor.	4 / 5
	Total	12 / 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 provides a clear trigger ('Use when testing Windows CRLF line endings') and a distinct niche, but it lacks an explicit statement of what the skill actually does and relies on a single generic action verb. Adding a concrete 'what' clause and a few synonym triggers would materially raise completeness and specificity.

Suggestions

Add an explicit 'what' clause before the trigger, e.g. 'Detects and normalizes Windows CRLF line endings. Use when testing...'.

Include natural synonym triggers users might say, such as 'carriage return', '\r\n', or 'line breaks'.

Replace the generic verb 'testing' with a concrete capability verb (e.g. 'detects', 'normalizes', 'verifies handling of').

Dimension	Reasoning	Score
Specificity	The phrase 'testing Windows CRLF line endings' names the domain but offers only one generic action ('testing'), matching the anchor for minimal/generic actions rather than the 1-2 concrete actions required for a 3.	2 / 5
Completeness	The description is solely a 'when' clause ('Use when testing Windows CRLF line endings') with no separate 'what' statement, matching the anchor where only 'when' is present without a clear 'what'.	2 / 5
Trigger Term Quality	It includes relevant core keywords ('Windows', 'CRLF', 'line endings') but omits common variations users might say such as 'carriage return', '\r\n', or 'line breaks', fitting the 'some relevant keywords but missing synonyms' anchor.	3 / 5
Distinctiveness Conflict Risk	'Windows CRLF line endings' is a clear, narrow niche with minimal conflict risk, though the generic verb 'testing' leaves minor overlap with general test-running skills, fitting the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	11 / 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: saif-shines/doraval
Path: test/fixtures/skills/crlf-lines/SKILL.md
Commit: 0fa2092

Reviewed: 1 day 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.