CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-network

Staff a task from registered Local, owner Cloud, and public Hub agents.

Quality

78%

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-network/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An extremely lean, well-guarded alias skill that delegates its entire behavior to a sibling skill via an exact path, explicit argument semantics, and anti-drift guards against improvising or hallucinating the target's content. The only limitation is that every executable detail lives in the external hep-network file, which is not part of this skill's bundle, so nothing can be verified or executed from this file alone.

DimensionReasoningScore

Conciseness

The ~90-word body is pure dispatch instruction with zero explanation of concepts Claude already knows: "Identical to `/skill:hep-network`", "Locate the sibling skill directory `hep-network` (i.e. `../hep-network/SKILL.md` relative to this file...)". Every sentence earns its place — path resolution, argument semantics, or a distinct failure-mode guard — so it matches the 'lean and efficient; every token earns its place' anchor rather than the level-4 anchor (the second paragraph guards two distinct failure modes rather than over-explaining).

5 / 5

Actionability

Concrete, executable dispatch guidance: an exact relative path ("`../hep-network/SKILL.md` relative to this file, under the same `kimi/skills/` root"), an explicit command mapping ("treating everything typed after `/skill:agentlas-network` as that command's request"), and a named source of authority. Not 5 because all executable substance lives in an external file outside this skill's bundle and no fallback is given if the sibling is missing; not 3 because nothing is vague or pseudocode — the dispatch action itself is fully specified.

4 / 5

Workflow Clarity

This is a simple single-purpose skill (alias dispatch) and the single action is unambiguous: "Locate the sibling skill directory `hep-network` ... read its `SKILL.md`, and follow its instructions exactly". Per the rubric's simple-skill exception, a single unambiguous action scores 5; the guards "Do not improvise a separate workflow and do not summarize `hep-network/SKILL.md` from memory" act as checkpoints against the only realistic failure mode. No destructive or batch operations, so no cap applies.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent), and the skill is under 50 lines with a single purpose, so the simple-skill exception applies. Its one external reference (`../hep-network/SKILL.md`) is one level deep and clearly signaled with precise resolution instructions, matching the 'well-signaled one-level-deep references' anchor. Not 4: there are no organization gaps and nothing that should be inlined; the pointer is unambiguous, and aliasing to a sibling skill is the appropriate structure for this purpose.

5 / 5

Total

19

/

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 states a clear, concrete 'what' with distinctive ecosystem terminology, but it completely lacks any 'when to use' trigger guidance and misses the natural synonyms (delegate, assign) users would most likely say. It uses appropriate third-person voice and avoids fluff, but reads more like an internal capability label than a trigger-optimized description.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to staff, delegate, or assign a task to available agents, or mentions the agent network, Local/Cloud/Hub agents."

Include natural user phrasings and synonyms — "delegate", "assign", "find agents" — alongside "staff", since 'staff a task' is unlikely to match how users actually phrase the request.

Briefly enumerate what staffing involves (e.g., selecting, invoking, and collecting results from agents) so the 'what' goes beyond a single action verb.

DimensionReasoningScore

Specificity

"Staff a task from registered Local, owner Cloud, and public Hub agents" names the domain and one concrete action with the three agent sources enumerated, matching the level-3 anchor ('names domain and 1-2 concrete actions, but not comprehensive'). Not 4: only a single action verb ('staff') is offered rather than several specific actions; not 2: it is far more concrete than 'Processes PDF files', identifying distinct agent tiers.

3 / 5

Completeness

The 'what' is clear (staff a task from Local/Cloud/Hub agents) but the 'when' is entirely absent — there is no "Use when..." clause or equivalent trigger guidance, which the judging guidelines explicitly cap at 3. Not 4: nothing implies when Claude should reach for this skill over any other.

3 / 5

Trigger Term Quality

Relevant keywords are present ("staff", "task", "agents", "Local", "Cloud", "Hub") but common variations users would naturally say — "delegate", "assign", "find/select agents" — are missing, matching the level-3 anchor. Not 4: 'staff a task' is unlikely phrasing for most users, so natural-term coverage is incomplete; not 2: the terms are domain-relevant rather than generic.

3 / 5

Distinctiveness Conflict Risk

The niche ecosystem terminology ("registered Local, owner Cloud, and public Hub agents") is unlikely to collide with unrelated skills, matching 'mostly distinct; minor overlap risk with closely related skills'. Not 5: it shares its underlying behavior with the hep-network alias and 'agents' is a crowded trigger space; not 3: the Local/Cloud/Hub framing is distinctive enough to avoid broad overlap.

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-network/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.