CtrlK
BlogDocsLog inGet started
Tessl Logo

ask

Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly

60

Quality

70%

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/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable body with executable commands and a clear required execution path, weakened only by some redundant justification in the routing section and an implied rather than explicitly sequenced verify-then-run workflow. Tightening the rationale and numbering the verify→route→confirm steps would lift it.

Suggestions

Trim the redundant rationale in 'Routing' — state the prohibition once and let the required command stand.

Make the workflow explicit: number it as 1) verify the provider CLI with `--version`, 2) run `omc ask ...`, 3) confirm the artifact at `.omc/artifacts/ask/...`.

Add a one-line note on what to do when a provider CLI is missing or unauthenticated.

DimensionReasoningScore

Conciseness

Mostly lean and concrete (examples, version checks, artifact path), but the 'no raw CLI assembly' prohibition is stated and then re-justified ('The omc ask wrapper handles... Manually assembling... will produce incorrect or outdated invocations'), and the Antigravity/Windows platform note runs long enough that it could be tightened.

2 / 3

Actionability

Provides fully executable, copy-paste-ready guidance: slash-command examples, the required `omc ask {{ARGUMENTS}}` invocation, per-provider `--version` verification commands, and the concrete artifact output path.

3 / 3

Workflow Clarity

The required path (always `omc ask`) and an availability-verification step are present, but verification is a flat list of commands rather than a sequenced flow, and there is no checkpoint confirming the artifact was written or any error-recovery guidance.

2 / 3

Progressive Disclosure

No bundle files exist and none are needed; the ~60-line body is organized into clearly labeled sections (Usage, Routing, Requirements, Artifacts) with no nested references, which is appropriate for a self-contained skill.

3 / 3

Total

10

/

12

Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, third-person description that names concrete actions and a distinct niche, but it is jargon-forward and lacks an explicit 'Use when...' trigger clause. Adding natural trigger phrasing would raise the trigger-term and completeness scores.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when you want to ask Claude, Codex, Gemini, Antigravity, Grok, or Cursor a question from inside Claude Code.'

Soften jargon ('process-first advisor routing', 'artifact capture') toward natural phrasing users would actually say.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'advisor routing' for six specific provider CLIs via `omc ask`, 'artifact capture', and 'no raw CLI assembly' — rather than vague abstractions.

3 / 3

Completeness

The 'what' is explicit (routes a prompt through provider CLIs, captures an artifact, avoids raw assembly) but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

The six provider names (Claude, Codex, Gemini, etc.) are natural terms a user would say, but the surrounding phrasing ('process-first advisor routing', 'artifact capture', 'no raw CLI assembly') leans on technical jargon over common natural variations like 'ask codex' or 'route a question to gemini'.

2 / 3

Distinctiveness Conflict Risk

It carves a clear niche — routing prompts through the named provider CLIs via the `omc ask` wrapper — that is unlikely to trigger for unrelated skills.

3 / 3

Total

10

/

12

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-claudecode
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.