CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-hub

Staff a task only from public Agentlas Hub agents.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./kimi/skills/agentlas-hub/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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-guarded alias that delegates its entire behavior to a sibling hep-hub skill via a precisely specified relative path. However, the delegated file is absent from the bundle, so the skill cannot actually execute and offers no fallback, which drags actionability, workflow clarity, and progressive disclosure to the middle anchors.

Suggestions

Ship the hep-hub skill (or inline its essential instructions) alongside this alias so the delegation target `../hep-hub/SKILL.md` actually resolves.

Add an explicit fallback for when the sibling file cannot be found (e.g., report the error to the user instead of improvising a workflow).

Add a quick existence-check step ("verify `../hep-hub/SKILL.md` exists before proceeding") so the delegation is verifiable rather than assumed.

DimensionReasoningScore

Conciseness

The ~90-word body is maximally lean for an alias skill: "Locate the sibling skill directory `hep-hub` ... read its `SKILL.md`, and follow its instructions exactly" plus a two-sentence anti-improvisation guardrail. Every sentence instructs or guards; nothing explains concepts Claude already knows, matching the 'every token earns its place' anchor.

5 / 5

Actionability

The steps are concretely specified ("`../hep-hub/SKILL.md` relative to this file"), but the referenced sibling skill does not exist anywhere in the bundle, so the executable target of the guidance is missing. This lands at 'some concrete guidance but incomplete / missing key details' rather than 4, whose gaps must be minor.

3 / 5

Workflow Clarity

The sequence (locate → read → follow exactly, with the request passed through) is unambiguous in form, but it dead-ends: there is no validation step confirming the sibling exists and no guidance for what to do when `../hep-hub/SKILL.md` is absent. This is a simple single-action skill, yet the missing fallback/checkpoint keeps it at the 'validation gaps' anchor rather than 5.

3 / 5

Progressive Disclosure

Structure is sound in form — a short overview with a single, clearly signaled one-level-deep reference to `hep-hub/SKILL.md` — but the bundle contains no reference/scripts/assets files at all and the one referenced path does not resolve, so navigation leads nowhere. Not score 1-2 (nothing is inlined or nested), but the dangling reference prevents the 'easy navigation' of a 4-5.

3 / 5

Total

14

/

20

Passed

Description

53%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 concrete niche action with a distinctive proper-noun trigger, but provides no 'when to use' guidance and only thin keyword coverage. It is serviceable for users who already name Agentlas Hub, yet incomplete for reliable automatic triggering.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to staff, assign, or find agents on Agentlas Hub."

Include natural keyword variations users might actually say (hire, delegate, browse, assign agents) alongside "staff" to improve trigger matching.

DimensionReasoningScore

Specificity

"Staff a task only from public Agentlas Hub agents" names the domain ("public Agentlas Hub agents") and one concrete action ("staff a task"), matching the '1-2 concrete actions, not comprehensive' anchor. It is above score 2 because 'staff a task' is a real named action rather than a generic verb, but below 4 because only a single action is covered.

3 / 5

Completeness

There is a clear 'what' ("Staff a task only from public Agentlas Hub agents") but no 'when' — no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is above score 2 because the 'what' is concrete, not vague.

3 / 5

Trigger Term Quality

Keywords present are "Staff", "task", "Agentlas Hub", and "agents" — relevant to the niche but missing common variations or synonyms a user might naturally say (e.g. hire, find, delegate, browse agents). This fits 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

"Agentlas Hub" is a distinctive proper noun giving the skill a clear niche with minimal conflict risk against unrelated skills. Only minor overlap risk exists with the closely related sibling skill (hep-hub) that this skill aliases, so it fits 'mostly distinct; minor overlap risk' rather than the fully distinct anchor at 5.

4 / 5

Total

13

/

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-hub/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.