CtrlK
BlogDocsLog inGet started
Tessl Logo

ask-claude

Deprecated compatibility shim for Claude advisor requests

62

Quality

72%

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 ./skills/ask-claude/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%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 an exemplary terse deprecation shim: it states the deprecation, gives exact replacement commands, and explains its continued existence briefly, with no wasted tokens.

DimensionReasoningScore

Conciseness

The body is a lean deprecation notice with no padding or explanation of concepts Claude already knows; the one rationale sentence is brief and relevant, so every token earns its place.

5 / 5

Actionability

It gives concrete, copy-paste-ready alternative commands ('$ask claude <question>' and 'omx ask claude "<question>"') and an explicit directive ('Do not invoke or route this skill'), which is fully executable guidance.

5 / 5

Workflow Clarity

As a single-purpose redirect skill, its single action is unambiguous—do not use this, use the named alternatives—satisfying the simple-skill exception that allows a 5 when the action is clear.

5 / 5

Progressive Disclosure

The skill is well under 50 lines, needs no external references, and is organized with a clear heading and direct statements, meeting the bar for a 5 on small single-purpose skills.

5 / 5

Total

20

/

20

Passed

Description

45%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 third-person and names its narrow niche, but it is abstract (no concrete actions), lacks any 'Use when' trigger guidance, and uses 'Claude advisor requests' rather than the natural 'ask claude' phrasing.

Suggestions

Add an explicit trigger clause such as 'Use when routing legacy ask-claude advisor requests' to satisfy the 'when' requirement and lift completeness above 3.

Replace jargon like 'Claude advisor requests' with the natural user phrase 'ask claude' to improve trigger-term quality.

State the concrete redirect action in the description (e.g., 'Redirects to the $ask claude workflow') so it lists a concrete capability rather than only the abstract 'shim' role.

DimensionReasoningScore

Specificity

The phrase 'compatibility shim for Claude advisor requests' names the domain but offers only an abstract role ('shim') with no concrete actions, matching the 'names the domain but actions are minimal or generic' anchor rather than the vaguer score-1 example.

2 / 5

Completeness

It states a clear 'what' (a deprecated compatibility shim) but provides no 'when' / 'Use when' trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

'Claude advisor requests' includes relevant keywords (Claude, advisor) but omits the natural phrase users would actually say ('ask claude'), so it has some relevant terms while missing common variations.

3 / 5

Distinctiveness Conflict Risk

The description targets a specific niche (Claude advisor requests) but, being a shim, directly overlaps with the canonical $ask claude workflow, so it is only somewhat distinct with real overlap risk.

3 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Yeachan-Heo/oh-my-codex
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.