CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

foo

Second foo skill.

27

Quality

34%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/coding-agent/test/fixtures/skills-collision/tilde-second/foo/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

33%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 body is effectively empty — a single title line with no instructions, examples, workflow, or structure. While it wastes no tokens, it provides Claude nothing to act on. The skill needs an explicit statement of what to do, even if only a single unambiguous action or a short code example.

Suggestions

Add actual instructional content under the heading — at minimum a concrete statement of the single action the skill performs, or executable code/commands for the common cases.

If the skill is a multi-step process, list the steps in order with explicit validation checkpoints; if it is a single-purpose simple skill, state that one action unambiguously so workflow clarity can apply.

Replace the placeholder title ('Foo (Second)') with a title that reflects the skill's real purpose, and organize any longer material into clearly signaled sections or one-level-deep reference files.

DimensionReasoningScore

Conciseness

The body is a single heading ('# Foo (Second)') with zero padding, over-explanation, or unnecessary tokens. It is vacuously lean — every token present is a conventional document title; the absence of any content is penalized under actionability and workflow clarity, not here.

5 / 5

Actionability

The body contains no code, commands, or instructions of any kind — only a title. This matches the anchor 'Entirely vague or abstract; no concrete code or commands; only describes rather than instructs' (in fact it does not even describe), and cannot be a 2 because there is no high-level hint of any kind.

1 / 5

Workflow Clarity

No steps, sequence, or validation checkpoints exist anywhere in the body. This clearly matches anchor 1 ('Steps missing or incoherent; no sequence; no validation for risky operations'); the simple-skill exception does not apply because no single action is ever stated.

1 / 5

Progressive Disclosure

Minimal structure: one lone heading with no sections, no content, and no references. It sits between anchors 1 and 2 — not a 1 because there is no monolithic wall of text or nested references to navigate, but not a 3 because there are no organized sections or clearly signaled structure at all.

2 / 5

Total

9

/

20

Passed

Description

3%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 a placeholder ('Second foo skill.') that conveys no capability, no trigger conditions, and no way to distinguish the skill from its sibling. It would almost never be selected for the right task and would conflict with the first foo skill. It needs a full rewrite stating what the skill does and when to use it.

Suggestions

Replace the placeholder with concrete action verbs describing what the skill actually does, e.g. 'Parses foo configurations and generates foo output' — this is the single highest-impact fix for specificity and completeness.

Add an explicit trigger clause with natural user phrasing, e.g. 'Use when the user mentions foo files, foo configuration, or .foo extensions' — its absence currently caps completeness at 3 and trigger term quality is at the floor.

State what differentiates this skill from the first foo skill (the 'Second' implies a sibling) so the two do not collide on the same triggers.

DimensionReasoningScore

Specificity

The description 'Second foo skill.' names no concrete actions — 'foo' is placeholder language naming no real domain or capability. This is a clear match to anchor 1 ('Entirely vague; no concrete actions; pure abstract language'); it cannot be a 2 because anchor 2 requires naming an actual domain, which this does not do.

1 / 5

Completeness

The 'what' is extremely vague ('foo skill' describes no capability) and the 'when' is entirely absent, matching anchor 1 ('Missing both what and when, or both are extremely vague'). The missing 'Use when' clause also caps completeness at 3 per the guidelines, but the natural level is lower; it is not a 2 because anchor 2 requires a 'what' that at least vaguely describes some activity.

1 / 5

Trigger Term Quality

The description contains no natural keywords a user would say, no synonyms, and no file extensions — nothing that would cause the skill to surface. This matches anchor 1 ('No natural keywords; only technical jargon or entirely generic language'); there are not even one or two generic keywords as anchor 2 requires.

1 / 5

Distinctiveness Conflict Risk

'Second foo skill.' is scoped to 'foo' rather than being entirely generic, but the word 'Second' explicitly signals a sibling foo skill it will collide with, and no distinguishing capability is stated. It falls between anchors 1 and 2 — noticeably above entirely-generic (not a 1) but with guaranteed high overlap risk and nothing specific to distinguish it (not a 3).

2 / 5

Total

5

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

description_field

'description' is very short (17 chars), consider making it more detailed

Warning

Total

15

/

16

Passed

Repository

can1357/oh-my-pi

Path

packages/coding-agent/test/fixtures/skills-collision/tilde-second/foo/SKILL.md

Reviewed

Table of Contents

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.