agentskills-oversized

Body deliberately exceeds the Level 2 line/token budget to exercise the progressive-disclosure warning.

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 ./test/fixtures/skills/agentskills-oversized/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 body is intentionally pure padding — hundreds of identical lines designed to exceed a size budget — with no actionable content, no real workflow, and no progressive disclosure. It fails every content dimension by construction.

Suggestions

Replace the padding with a concise overview that assumes Claude's competence; keep the body well under the line/token budget.

Provide concrete, executable guidance or examples for the skill's actual purpose instead of placeholder steps.

If detail is needed, split it into one-level-deep reference files (e.g. references/ADVANCED.md) and link them from a short SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	The body is 520 identical padded lines ("Step number N in a long list that pushes this file past the 500-line budget") adding no information, the severely-verbose/padded anchor.	1 / 5
Actionability	There is no concrete code, command, or instruction anywhere — only repeated placeholder sentences, matching the entirely-abstract/no-concrete-guidance anchor.	1 / 5
Workflow Clarity	Although numbered 1–520, the steps are vacuous repetition with no real task sequence and no validation checkpoints, fitting the incoherent/no-meaningful-sequence anchor better than the 'rough sequence' anchor.	1 / 5
Progressive Disclosure	Beyond a single heading, the file is a monolithic wall of padding with no structure, no sectioning of real content, and no references to separate files, matching the monolithic-wall-of-text 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 describes the file's own deliberate bloat rather than a user-facing capability, so it lacks concrete actions, natural trigger terms, and explicit 'when to use' guidance. It is third-person (no pronoun penalty) but reads as meta-commentary, not a skill pitch.

Suggestions

Rewrite the description as a concrete capability with specific actions a user would invoke (e.g. what the skill does for the user), not a statement about file size.

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say.

Include natural synonyms or file-type keywords relevant to the skill's actual purpose to improve trigger term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	Quotes "deliberately exceeds the Level 2 line/token budget" and "progressive-disclosure warning" name a meta domain but list no concrete capability actions, matching the anchor that names a domain with minimal/generic actions.	2 / 5
Completeness	There is a vague 'what' (the body is deliberately oversized) but no 'Use when...' trigger guidance, so it falls at the 'vague what, no when' anchor rather than a clear what.	2 / 5
Trigger Term Quality	The text offers only meta language ("progressive-disclosure warning", "line/token budget") that no user would naturally say when they need a skill; there are no natural trigger keywords.	1 / 5
Distinctiveness Conflict Risk	The description is about file-size behavior rather than a user capability, leaving it broad and overlapping with any skill-authoring concern rather than carving a distinct niche.	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 (528 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: saif-shines/doraval
Path: test/fixtures/skills/agentskills-oversized/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.