CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skills-sdk-valid-fixture

Minimal valid Codex skill source fixture for JSC-391 scaffold tests.

Quality

56%

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 ./Infrastructure/tests/fixtures/skills_sdk/valid_skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

51%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 maximally lean, well-structured declaration that appropriately requires no bundle files, but it is purely descriptive: it provides no guidance, steps, or usage instructions for the fixture's intended consumers. As written, it tells the reader what the fixture is not rather than what to do with it.

Suggestions

Add a short actionable section describing how the fixture is used, e.g. "Load this source as the input to the skills-sdk scaffold path and assert the projection succeeds."

State the invariants the fixture exercises (e.g. expected frontmatter fields, expected projection output) so tests built on it are concrete.

If the disclaimer list (install, eval, signing, sandbox, registry, publish) maps to specific test expectations, link each to the scaffold behavior it guards.

DimensionReasoningScore

Conciseness

The body is three short lines ("This fixture is a canonical skill source sample. It is not a runtime projection and does not claim install, eval, signing, sandbox, registry, or publish readiness.") with zero padding and no explanation of concepts Claude already knows. Every token earns its place, matching the "lean and efficient" anchor exactly.

5 / 5

Actionability

The body contains no code, commands, or instructions of any kind — it purely describes ("is a canonical skill source sample", "does not claim... readiness") rather than instructing, matching anchor 1's "only describes rather than instructs". It is not a 2 because even anchor 2 expects high-level hints toward concrete steps, and nothing here directs any action, not even a hint about how the fixture is meant to be consumed by the scaffold tests.

1 / 5

Workflow Clarity

No steps or sequence are described anywhere in the body. It avoids anchor 1 only because there are no risky operations that lack validation — the skill is static and declarative — but it also fails the simple-skill exception since no single unambiguous action is articulated; the content establishes no workflow at all, which is noticeably below the midpoint.

2 / 5

Progressive Disclosure

This is a sub-50-line skill needing no external references, and the content is appropriately self-contained with a clear title heading and no inlined material that belongs in separate files. Per the rubric's simple-skill guideline this matches the top anchor.

5 / 5

Total

13

/

20

Passed

Description

41%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 identifies its niche concretely but is a pure noun phrase: it lists no capabilities or actions, includes no "Use when" trigger guidance, and relies on internal jargon (JSC-391, scaffold) rather than natural user language. It would rarely be selected by a user's natural request.

Suggestions

Rewrite the description to lead with what the skill does, e.g. "Serves as a minimal valid Codex skill source sample for exercising skills-sdk scaffold logic."

Add an explicit trigger clause, e.g. "Use when running JSC-391 scaffold tests or when a valid skill source fixture is needed."

Replace internal jargon with natural keywords users would say ("skill fixture", "sample SKILL.md", "test scaffold") so it can be matched to real requests.

DimensionReasoningScore

Specificity

"Minimal valid Codex skill source fixture for JSC-391 scaffold tests" names a concrete domain (a skill source fixture for scaffold tests) but contains no action verbs whatsoever — it states what the thing IS, not what it does. This sits between anchor 1 (entirely vague, e.g. "Helps with documents") and anchor 3 (domain plus 1-2 concrete actions); the domain is specific but the action coverage is nil, so 2 fits best.

2 / 5

Completeness

The "what" is reasonably clear (a minimal, valid skill source sample used in scaffold tests), but there is no "Use when..." clause or any equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 4 because the "when" is entirely absent rather than merely under-specified, and not a 2 because the "what" is concrete rather than vague.

3 / 5

Trigger Term Quality

The only keywords are developer jargon — "Codex skill", "source fixture", "scaffold tests", "JSC-391" — with no natural phrases a user would say when needing this skill and no synonyms or file extensions. It edges above anchor 1 because "skill", "fixture", and "test" are at least on-topic keywords, but it clearly does not reach anchor 3's "some relevant keywords" with natural variations.

2 / 5

Distinctiveness Conflict Risk

The explicit ticket reference ("JSC-391") and the narrow fixture framing give it a clear niche with minimal conflict risk against general-purpose skills. It falls short of anchor 5 because the description provides no distinct triggers and could overlap with other test-fixture skills that share the "valid skill source sample" framing.

4 / 5

Total

11

/

20

Passed

Validation

100%

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

jscraik/Agent-Skills

Path

Infrastructure/tests/fixtures/skills_sdk/valid_skill/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.