CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-local

Staff a task only from Agentlas agents registered on this machine.

Quality

72%

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

Quality

Content

76%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.

This is a well-built, maximally lean delegation stub: it unambiguously points to a sibling skill as the sole authority and guards against improvisation. Its main weakness is robustness — the referenced hep-local skill is not present in this environment and the body defines no behavior or error path for that case, capping workflow clarity.

Suggestions

Add a validation step and failure path, e.g. "If ../hep-local/SKILL.md cannot be found, tell the user the agentlas-local skill depends on the hep-local skill and stop" — this both validates the delegation target and prevents improvisation when it is missing.

Consider bundling or inlining a minimal fallback summary of the staffing procedure so the skill retains some function if the sibling skill is absent.

DimensionReasoningScore

Conciseness

The body is ten lean lines with no concept explanations: every element (alias mapping to /skill:hep-local, explicit path resolution, argument forwarding, anti-improvisation guard) earns its place. It assumes Claude's competence and matches the "lean and efficient" anchor; the second paragraph's emphasis is functional (preventing drift), not padding, so it does not drop to 4.

5 / 5

Actionability

The pointer is concrete and executable — an explicit relative path ("../hep-local/SKILL.md relative to this file, under the same kimi/skills/ root") and an explicit rule for forwarding trailing arguments. It is not 5 because there is no guidance for the case where the target file cannot be found, a real gap since the referenced sibling does not exist in this environment.

4 / 5

Workflow Clarity

A clear sequence is present (locate sibling skill, read its SKILL.md, follow it, forward the request) and the "do not improvise a separate workflow and do not summarize from memory" guard is a useful negative checkpoint. However, there is no validation step confirming the delegation target exists before proceeding — and the referenced ../hep-local/SKILL.md is absent here, leaving the skill with no defined behavior or error path. This matches anchor 3 (sequence present, checkpoints missing) rather than 4.

3 / 5

Progressive Disclosure

The delegation reference is well-signaled and exactly one level deep (locate ../hep-local/SKILL.md and follow it), which is good progressive disclosure for a thin dispatcher. It is not 5 because the entire skill is a pointer to a file outside its own bundle with no bundled fallback content, so nothing is self-contained; it is not 3 because the reference is clearly signaled, not buried.

4 / 5

Total

16

/

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 is concise and specific about its niche (locally registered Agentlas agents), but it answers only "what" and omits any "when to use" trigger guidance. It is serviceable but would misfire on discovery since a user has to already know the term "Agentlas" to find it.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to staff, assign, or delegate a task to agents and mentions Agentlas or local/machine-registered agents."

Enumerate one or two more concrete capabilities of the staffing flow (e.g. listing available registered agents, selecting agents for a request) to raise specificity.

Include natural synonyms such as "local agents", "assign agents", or "delegate to agents" so the description matches phrasings users actually type.

DimensionReasoningScore

Specificity

"Staff a task only from Agentlas agents registered on this machine" names the domain (locally registered Agentlas agents) and one concrete action (staff a task), matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not 4 because no additional actions are enumerated, and not 2 because "staff a task" is more concrete than a purely generic action like "Processes PDF files".

3 / 5

Completeness

The description clearly answers "what" (staff a task from local Agentlas agents) but contains no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It is not 2 because the "what" is specific rather than vague, and not 4 because the "when" is entirely missing rather than merely imprecise.

3 / 5

Trigger Term Quality

Terms like "Staff", "task", "Agentlas agents", and "registered on this machine" are relevant and "Agentlas" is a strong distinctive keyword, but common natural variations (e.g. "local agents", "assign agents", "available agents") are absent. This sits at the "some relevant keywords but missing variations" anchor rather than 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

"Agentlas agents registered on this machine" carves a clear niche with a distinctive keyword, but the generic "staff a task" phrasing leaves minor overlap risk with other agent-delegation or team-staffing skills. This matches anchor 4 (mostly distinct, minor overlap risk) rather than 5, which would require distinct trigger phrases.

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-local/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.