body-500-lines

Body with exactly 500 lines, at the no-warn boundary.

Quality

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/body-500-lines/SKILL.md

Quality

Content

0%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 pure filler: 500 repetitions of 'Line N does a thing.' with no instructions, code, workflow, structure, or references. It appears to be a size-boundary test fixture rather than a usable skill body, and provides no value to Claude or a user.

Suggestions

Replace the filler lines with a concise, structured body (headed sections, <500 lines) containing the skill's actual instructions.

Include concrete, executable guidance — real commands or code examples covering the common cases — instead of 'does a thing'.

If the skill involves multi-step or batch/destructive operations, add an explicit numbered workflow with validation checkpoints and error-recovery feedback loops; otherwise move any bulk detail into well-signaled reference files under references/.

Dimension	Reasoning	Score
Conciseness	The body is 500 lines of identical filler ('Line 0 does a thing.' through 'Line 499 does a thing.') — every single line is padding that adds nothing Claude doesn't already know. This is maximal verbosity with zero informational content, matching the 'severely verbose; heavily padded' anchor.	1 / 5
Actionability	'does a thing' is the definition of vague direction: no code, no commands, no specific steps, and no examples anywhere in the 500 lines. The content only describes (in the most generic way possible) rather than instructs.	1 / 5
Workflow Clarity	There is no sequence of steps, no headers or structure, and no validation of any kind — the numbered lines are line labels, not actionable workflow steps. Steps are effectively missing and incoherent as a process.	1 / 5
Progressive Disclosure	The body is a monolithic wall of text with no sections, no navigation, and no references; no bundle files (references/, scripts/, assets/) exist. Nothing is split out or organized at any level, matching the worst anchor.	1 / 5
	Total	4 / 20 Passed

Description

17%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 documents a test fixture's file size ('Body with exactly 500 lines, at the no-warn boundary') rather than describing what the skill does or when to use it. It contains no capabilities, no trigger terms, and no use-when guidance, so it would never be surfaced by a real user request.

Suggestions

Rewrite the description to state the skill's actual capabilities in third person with concrete action verbs (e.g., what it processes or produces), replacing the file-metadata statement.

Add an explicit 'Use when...' clause with natural trigger phrases a user would actually say, including synonyms and relevant file extensions.

Remove internal jargon like 'no-warn boundary' that only makes sense to the skill's author, and ensure the description distinguishes the skill from related ones.

Dimension	Reasoning	Score
Specificity	"Body with exactly 500 lines, at the no-warn boundary" describes the file's physical properties rather than any concrete action the skill performs; it names a subject but offers zero capability actions. It is not score 1 because it is not pure abstract filler (it is concrete about the file), and not score 3 because no action verbs or capabilities appear at all.	2 / 5
Completeness	It gives a vague, meta-level 'what' (a 500-line body) with no statement of what the skill does, and there is no 'when' or 'Use when...' clause at all. The missing-use-when rule caps completeness at 3, and this falls below that because the 'what' is not a capability statement.	2 / 5
Trigger Term Quality	The only candidate terms are "body", "lines", and "no-warn boundary" — harness/testing jargon no user would naturally say when needing a skill. There are no natural keywords whatsoever.	1 / 5
Distinctiveness Conflict Risk	It establishes no functional niche or trigger vocabulary; it avoids conflict with other skills only because it would never trigger for anything. Not score 1 since it is not broadly generic like 'helps with code and documents', but it provides no distinguishing capability information.	2 / 5
	Total	7 / 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
skill_md_line_count	SKILL.md is long (504 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: pantheon-org/tekhne
Path: crates/skill-validator-rs/tests/golden-corpus/fixtures/boundary/body-500-lines/SKILL.md
Commit: a1083f4

Reviewed: 1 hour 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.