CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-call

Prepare explicitly named Agentlas Hub or Cloud agents.

Quality

68%

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 ./kimi/skills/agentlas-call/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 maximally lean, well-guarded alias skill whose instructions are unambiguous in form, but which delegates 100% of its behavior to a sibling file (../hep-call/SKILL.md) that is not present in the bundle, making it unexecutable as shipped. Its brevity is exemplary; its dependency is unverified and unresolvable.

Suggestions

Ship the referenced ../hep-call/SKILL.md alongside this skill (or inline its essential steps) so the delegation target actually resolves within the bundle.

Add a fallback instruction for when the sibling skill cannot be located (e.g., report the missing dependency to the user rather than improvising).

Consider duplicating the trigger/usage guidance from hep-call into this SKILL.md's frontmatter so the skill is self-describing even before delegation.

DimensionReasoningScore

Conciseness

The 9-line body is lean and every sentence earns its place: it defines the command equivalence ("Identical to /skill:hep-call and /agentlas call <request>"), gives a precise path ("../hep-call/SKILL.md relative to this file"), and adds a meaningful anti-improvisation guardrail. It is not 4 because there is no over-explanation or padding to trim.

5 / 5

Actionability

The delegation instructions are concrete in form (exact relative path, exact command mapping, explicit argument handling), but the sole execution target ../hep-call/SKILL.md is absent from the skill's bundle, so the guidance cannot actually be executed as shipped — 'Some concrete guidance but incomplete... missing key details'. It is not 2 because the steps themselves (locate, read, follow exactly) are specific, not high-level hints, and not 4 because the missing target is the entire substance of the skill, not a minor gap.

3 / 5

Workflow Clarity

As a single-purpose alias skill the single action is unambiguous (locate sibling skill, read it, follow it, pass trailing input as the request), which would merit 5 under the simple-skill exception. It drops to 4 because there is no fallback or checkpoint if the sibling directory cannot be found — a real gap since the referenced path does not resolve in this bundle.

4 / 5

Progressive Disclosure

The external reference is clearly signaled and exactly one level deep ("../hep-call/SKILL.md relative to this file, under the same kimi/skills/ root"), but no bundle files exist and the referenced path does not resolve, leaving the skill with no navigable content of its own. This sits between 'references mostly clear' (4) and the broken-navigation failure mode, so it lands at 3.

3 / 5

Total

15

/

20

Passed

Description

48%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 names a distinct product niche but relies on a single generic verb ("Prepare") and completely lacks trigger guidance for when the skill should be used. It is distinguishable from other skills but under-specified in both capabilities and activation conditions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user explicitly names an Agentlas Hub or Cloud agent to prepare (e.g. /skill:agentlas-call <agent-name> or /agentlas call <request>)'.

Replace or augment the generic verb 'Prepare' with the 2-3 concrete actions involved (e.g., provisioning, configuring credentials, verifying the agent is ready).

Include natural keyword variations users might type, such as 'set up', 'provision', or 'launch' alongside 'prepare'.

DimensionReasoningScore

Specificity

The description names the domain ("Agentlas Hub or Cloud agents") but the sole action verb "Prepare" is generic, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because no concrete actions (e.g., what preparing an agent involves) are enumerated, and not a 1 because the domain and target object are explicitly named.

2 / 5

Completeness

A 'what' is present ("Prepare explicitly named Agentlas Hub or Cloud agents") but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is above 2 because the 'what' names a specific platform and target rather than being vague.

3 / 5

Trigger Term Quality

"Agentlas Hub", "Cloud agents", and "agents" are relevant product keywords a user of that ecosystem would say, but the description offers no synonyms, variations, or natural phrasing beyond the bare product nouns (e.g., "provision", "set up", "deploy"). This fits 'Some relevant keywords but missing common variations or synonyms' rather than 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The product proper nouns ("Agentlas Hub", "Cloud agents") give it a clear niche with minimal conflict against generic skills, fitting 'Mostly distinct; minor overlap risk'. It is not 5 because no trigger phrases distinguish it from closely related sibling commands (the body itself declares it identical to /skill:hep-call), and not 3 because the specificity far exceeds generic domain descriptions.

4 / 5

Total

12

/

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

agentlas-ai/Agentlas-OS

Path

kimi/skills/agentlas-call/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.