CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-operations

Agentlas 시스템 운용 절차 — hep-network 편성, cargo/Agent Cloud·marketplace 활용, workforce 로스터 재사용, 메모리 계약. One(개인 에이전트)이 Agentlas를 조작할 때 이 절차를 따른다.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 exceptionally lean, high-signal operational skill with concrete tool calls, parameters, and field-tested pitfalls. Main weaknesses are the dangling INDEX.md reference (the declared authoritative registry is missing from the bundle) and the absence of full call examples and error-recovery loops.

Suggestions

Add the INDEX.md file (or a references/ copy) to the bundle so the declared canonical tool registry is actually reachable from the SKILL.md link.

Include one complete example call payload (e.g., a redacted work-order for workforce.search_candidates) so the recruitment step is copy-paste executable.

Document the '## Memory Events' envelope format and what to do when workforce.validate_selection rejects a selection, closing the actionability and feedback-loop gaps.

DimensionReasoningScore

Conciseness

Every line is operational and non-obvious ('24시간 Hub 리스는 과금 단위지 바인딩 종료가 아니다', '아는 사실 재유도 금지') with zero padding or explanation of concepts Claude already knows. Fully matches the 'lean and efficient; every token earns its place' anchor — nothing to trim.

5 / 5

Actionability

Concrete tool calls with parameters are given throughout — 'workforce.search_candidates (sourceScope=network)', 'workforce.prepare_execution (projectDir 필수)', '"supersedes":"<h:16hex>"', '~/.agentlas/one/' — matching 'mostly executable guidance with minor gaps'. Not 5 because full call payloads, the redacted work-order format, and the Memory Events envelope syntax are referenced but never shown.

4 / 5

Workflow Clarity

The orchestration section is a clearly numbered 1–5 sequence with an explicit validation checkpoint ('workforce.validate_selection') and a preflight step ('agentlas.memory.preflight'), matching anchor 4. Not 5 because error-recovery loops after a failed validation are not spelled out, and later sections are rule lists rather than sequenced workflows.

4 / 5

Progressive Disclosure

Sections are well-organized and the reference is clearly signaled, but the load-bearing pointer '[INDEX.md](INDEX.md)가 정본' targets a file that does not exist in the bundle — the canonical tool registry it designates is unreachable. Falls between anchors 3 and 4; a broken navigation pointer to the document's declared source of truth is more than a minor organization gap.

3 / 5

Total

16

/

20

Passed

Description

78%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 specific, well-scoped description that names concrete capability areas and includes an explicit when-clause tied to a distinctive system name. Keyword coverage is strong within its ecosystem, though it could add natural phrasing variations and more granular trigger conditions.

DimensionReasoningScore

Specificity

Lists several concrete action areas — 'hep-network 편성, cargo/Agent Cloud·marketplace 활용, workforce 로스터 재사용, 메모리 계약' — going beyond naming the domain. Not 5 because '운용 절차' (operation procedures) is broad and several operations (plugin resolution, surface pitfalls) only appear in the body; not 3 since four distinct action areas are explicitly named.

4 / 5

Completeness

Explicitly answers both: 'what' via the four enumerated procedure areas and 'when' via 'One(개인 에이전트)이 Agentlas를 조작할 때 이 절차를 따른다' (follow this procedure when One operates Agentlas). Not 5 because the when-clause is a single broad trigger rather than multiple concrete trigger phrases.

4 / 5

Trigger Term Quality

Good coverage of the ecosystem's canonical terms users would naturally say: 'Agentlas', 'hep-network', 'cargo', 'Agent Cloud', 'marketplace', 'workforce 로스터', '메모리 계약', 'One'. Not 5 because no synonyms or phrasing variations are included (e.g., agent search/recruitment phrasings).

4 / 5

Distinctiveness Conflict Risk

Anchored on proprietary system names ('Agentlas', 'hep-network', 'workforce', 'One') that create a clear niche with distinct triggers and minimal risk of firing for an unrelated skill.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

agentlas-ai/Agentlas-OS

Path

.agents/skills/agentlas-operations/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.