aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa

Name is exactly 64 bytes, the valid upper boundary.

Quality

18%

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/aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/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 a placeholder rather than guidance: maximally terse (strong on conciseness) but containing no actionable instruction, no workflow, and only nominal structure. Claude reading this skill would learn nothing about what to do.

Suggestions

Replace 'Use it.' with the concrete instruction, command, or code the skill exists to deliver.

Rename the '# Body' heading to reflect the actual task, and organize any longer material into clearly signaled sections or one-level-deep reference files.

If the task involves multiple steps, list them in order and add validation checkpoints where operations are risky.

Dimension	Reasoning	Score
Conciseness	The body ('# Body' + 'Use it.') is three words of content with zero padding, no explanation of known concepts, and no wasted tokens — matching anchor 5 ('lean and efficient; every token earns its place' in the token-budget sense). Its lack of substance is scored under actionability, not here.	5 / 5
Actionability	'Use it.' provides no concrete, executable guidance — no code, commands, or steps, and the referent of 'it' is undefined. This matches anchor 1 ('entirely vague or abstract; only describes rather than instructs') and is well below anchor 3's 'some concrete guidance'.	1 / 5
Workflow Clarity	No sequence of steps exists at all, matching anchor 1 ('steps missing or incoherent; no sequence'). Even under the simple-skill exception, a single action must be unambiguous — 'Use it.' names no action, so the exception cannot lift the score.	1 / 5
Progressive Disclosure	The body has minimal structure — a generic '# Body' heading over a single vague sentence — with no bundle files or references to organize. This sits between anchor 2 ('minimal structure') and anchor 4 ('good structure; most content appropriately placed'): there is nothing that should be split out, but the organization that exists is nominal and uninformative.	3 / 5
	Total	10 / 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 not a skill description at all — it is a test note about the `name` field hitting the 64-byte boundary. It conveys zero information about capabilities, triggers, or use cases, scoring the minimum on every dimension.

Suggestions

Replace the meta-commentary with a description of what the skill actually does, e.g. concrete verbs and objects ('Extracts…', 'Validates…').

Add an explicit 'Use when…' clause naming the natural phrases a user would say to trigger the skill.

State the skill's domain clearly so it is distinguishable from other skills and unlikely to be selected for unrelated requests.

Dimension	Reasoning	Score
Specificity	The description 'Name is exactly 64 bytes, the valid upper boundary.' states no capability or action whatsoever — it is meta-commentary about the `name` field's length. This matches anchor 1 ('entirely vague; no concrete actions'), and cannot be 2 since it doesn't even name a domain of operation.	1 / 5
Completeness	Neither 'what does this do' nor 'when should Claude use it' is addressed in any form — the text describes a property of the name field. This matches anchor 1 ('missing both what and when') and is below anchor 3, which requires a clear 'what'.	1 / 5
Trigger Term Quality	No natural trigger keywords appear; phrases like 'Name', '64 bytes', 'upper boundary' are technical meta-language no user would say when needing a skill. Anchor 1 ('no natural keywords') is the closest match, and anchor 2 ('one or two generic keywords') does not apply since even generic domain keywords are absent.	1 / 5
Distinctiveness Conflict Risk	The description contains no domain or capability information, so it provides nothing to distinguish this skill from any other; it is entirely non-descriptive in the same way as anchor 1's generic example. It cannot be 2 because even a broad-but-real domain statement ('helps with document files') is absent.	1 / 5
	Total	4 / 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/aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa/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.