CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-mate-qoder

Run the Qoder CLI non-interactively with structured output. Use when the user asks to delegate a coding task to Qoder.

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A lean, highly actionable body that covers availability checking, execution, output validation, authentication, and permission boundaries with a copy-paste-ready command and explicit error handling. The only weaknesses are minor redundancy and an unspecified permission-mode mechanism in the edit-permission branch.

DimensionReasoningScore

Conciseness

The body is efficient and dense with non-obvious facts ("Code Mate installs the CN executable `qoderclicn`, not `qoder`"; "a zero exit alone is not success"), but minor redundancy remains, such as "Pass the prompt as one quoted argument" restating the visible `-p "<prompt>"` flag. This fits the efficient-with-minor-trims anchor at 4 rather than the every-token-earns-its-place anchor at 5.

4 / 5

Actionability

The skill provides a copy-paste-ready command (`qoderclicn -p "<prompt>" -o json --no-session-persistence`), a concrete availability check (`command -v qoderclicn`), and explicit output validation via `is_error`. It falls short of 5 because the permission branch ("the command select the narrowest non-default permission mode") gives no concrete flag or mechanism for doing so.

4 / 5

Workflow Clarity

The sequence is clear (set working directory and timeout, check availability, run one stateless task) with explicit validation ("check `is_error`"; "accept the result only when `is_error` is false") and explicit failure branches for every failure mode (missing binary, missing auth/trust/provider config). This is a simple single-task skill with no destructive or batch operation, so the full validation coverage matches the top anchor.

5 / 5

Progressive Disclosure

The skill is under 50 lines, performs a single task, needs no external references, and is organized into two clear sections ("Run" and "Authentication And Permissions"). Per the simple-skill guideline, well-organized sections alone warrant the top score.

5 / 5

Total

18

/

20

Passed

Description

73%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.

A concise, third-person description with an explicit "Use when" trigger and a clearly distinct niche. Its main weaknesses are limited specificity of capabilities and a single trigger phrasing, which leave the what/when coverage good but not comprehensive.

Suggestions

List 1-2 more concrete capabilities in the "what" clause (e.g., "review code, implement fixes, or analyze a repository") to raise specificity beyond a single action.

Broaden the "when" clause with natural phrasing variations such as "hand off a task to Qoder" or "ask Qoder to..." to improve trigger term coverage and completeness.

State the concrete task types supported (e.g., code review, bug fixes, refactoring) so the trigger guidance is more specific about which coding tasks qualify.

DimensionReasoningScore

Specificity

"Run the Qoder CLI non-interactively with structured output" names the domain and 1-2 concrete actions but does not enumerate several specific capabilities, matching the anchor for naming the domain with limited actions. It falls short of 4 because there is no multi-action coverage (e.g., what kinds of coding tasks it performs).

3 / 5

Completeness

It explicitly answers both "what" ("Run the Qoder CLI non-interactively with structured output") and "when" ("Use when the user asks to delegate a coding task to Qoder"). It stops short of 5 because the trigger is a single phrasing and the "what" does not elaborate the concrete task types covered.

4 / 5

Trigger Term Quality

Natural terms like "Qoder", "CLI", and "delegate a coding task to Qoder" give good keyword coverage for a user needing this skill. It is not 5 because common phrasing variations (e.g., "hand off to Qoder", "ask Qoder") are absent, and not 3 because the keywords are specific rather than generic.

4 / 5

Distinctiveness Conflict Risk

It names a specific tool ("Qoder") with a clear niche trigger ("delegate a coding task to Qoder"), making conflict with other skills minimal. This clearly matches the anchor for a clear niche with distinct triggers rather than the minor-overlap anchor at 4.

5 / 5

Total

16

/

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

CherryHQ/cherry-studio

Path

resources/code-cli-skills/code-mate-qoder/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.