CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-build

Build, repair, or package Agentlas agents and teams with Hephaestus.

Quality

82%

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 clean, minimal delegation stub: it unambiguously redirects to hep-build with an exact path, argument mapping, and anti-improvisation guardrails. The only weaknesses are slight triple-restatement of the delegation rule and no fallback if the sibling skill is missing.

DimensionReasoningScore

Conciseness

The body is ~9 lines with no explanation of concepts Claude already knows, but the delegation instruction is stated three ways ("Identical to /skill:hep-build", "follow its instructions exactly", "that file is the sole authority"), which is a minor instance of repetition that could be trimmed. This fits anchor 4 ('efficient; minor instances that could be trimmed') better than 5 ('every token earns its place').

4 / 5

Actionability

Concrete, executable delegation: exact path "../hep-build/SKILL.md", resolution rule ("relative to this file, under the same kimi/skills/ root"), and argument mapping ("treating everything typed after /skill:agentlas-build as that command's request"). Not 5 because there is no handling for the referenced file being absent and no examples of common requests — execution depends entirely on an external file.

4 / 5

Workflow Clarity

This is a simple single-task skill and its single action is unambiguous: locate the sibling hep-build directory, read its SKILL.md, follow it exactly, and pass the trailing text as the request — with explicit guardrails ("Do not improvise a separate workflow and do not summarize... from memory"). Per the simple-skill guidance this scores 5; no destructive or batch operations are involved, so no validation cap applies.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent), and the under-50-line body consists of a clear overview plus a single, well-signaled, one-level-deep reference with precise navigation instructions ("../hep-build/SKILL.md relative to this file"). This matches anchor 5 ('clear overview with well-signaled one-level-deep references; easy navigation') rather than 4, since there are no organization gaps.

5 / 5

Total

18

/

20

Passed

Description

70%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, concrete, third-person description with a clear niche and distinct ecosystem-specific trigger terms. Its main weakness is the absence of any 'when to use' guidance, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to build, fix, or package Agentlas agents or teams, or mentions Hephaestus."

Broaden trigger vocabulary with natural synonyms users might say, such as "create", "fix", or "bundle" alongside build/repair/package.

Clarify what the skill produces (e.g., agent/team artifacts or packages) to close the minor coverage gap in specificity.

DimensionReasoningScore

Specificity

"Build, repair, or package" lists three concrete verbs applied to a named domain ("Agentlas agents and teams") via a named tool ("with Hephaestus"), matching the 'several specific actions; minor gaps in coverage' anchor. It falls short of 5 because coverage is not comprehensive — no indication of what building/packaging actually produces — and exceeds 3, which expects only 1-2 concrete actions.

4 / 5

Completeness

The 'what' is clear ("Build, repair, or package Agentlas agents and teams with Hephaestus") but there is no 'Use when...' clause or equivalent trigger guidance, so completeness is capped at 3 per the judging guidelines. It is not 2 because the 'what' is concrete, not vague.

3 / 5

Trigger Term Quality

Natural terms a user would say are present ("build", "repair", "package", "agents", "teams", "Hephaestus", "Agentlas"), giving good keyword coverage. Not 5 because common synonyms and variations (e.g., "fix", "create", "bundle", file extensions) are missing; better than 3 because coverage goes beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

Distinct proper nouns ("Agentlas", "Hephaestus") plus specific actions create a clear niche — a user asking to build or repair an Agentlas agent would unambiguously land here. Even though this skill is an alias of hep-build, the two are behaviorally identical, so misrouting carries minimal practical conflict risk; this fits the 'clear niche with distinct triggers; minimal conflict risk' anchor better than the 4 anchor's 'minor overlap risk'.

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

agentlas-ai/Agentlas-OS

Path

kimi/skills/agentlas-build/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.