CtrlK
BlogDocsLog inGet started
Tessl Logo

hephaestus-cloud

Use when the user types /hep-cloud or /agentlas-cloud, or asks to staff from THEIR OWN Agentlas cloud packages only. Cloud is one exact source scope; Network means Local + owner Cloud + public Hub.

60

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/hephaestus-cloud/SKILL.md

The canonical home for this skill is hephaestus-cloud in agentlas-ai/Agentlas-OS

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-sequenced, actionable routing skill with executable bash and a concrete typed-tool call order, supported by explicit validation checkpoints and hard rules. Weaknesses are minor repetition of the source_not_supported warning and redacted placeholder parameters in the MCP call sequence.

Suggestions

Deduplicate the "report source_not_supported; never fall back to legacy cargo search" guidance into the Hard rules section so it is stated once, trimming conciseness waste.

Replace the redacted MCP placeholders (workOrder=..., selection=...) with a minimal concrete example shape or a clear per-field reference so the section-3 sequence is fully actionable.

Add an explicit validate -> fix -> re-validate feedback loop note to section 3 or 4 to push workflow clarity from clear-checkpoints toward full error-recovery guidance.

DimensionReasoningScore

Conciseness

The body is dense and largely assumes Claude's familiarity with Agentlas/Core concepts, but the "report source_not_supported; never fall back to the legacy cargo search path" warning is repeated across sections 1 and 3 and some jargon ("The adapter never owns a second seed format") could be trimmed, so it is mostly efficient with tightening opportunities rather than fully lean.

3 / 5

Actionability

Sections 1 and 2 give fully executable, copy-paste bash scripts (runner resolution, auth ensure) and the install command is concrete; section 3 names the exact typed Workforce tool sequence in order, though parameters use redacted placeholders (workOrder=..., selection=...), leaving a minor gap rather than fully copy-paste MCP calls.

4 / 5

Workflow Clarity

A clearly numbered 0-5 sequence embeds explicit validation checkpoints (validate_selection, validate_execution_receipt) and a Hard rules section; it falls short of 5 because the validate-fix-retry feedback loop is not spelled out as explicitly as the anchor's re-validate-then-proceed pattern.

4 / 5

Progressive Disclosure

A single well-organized SKILL.md with clear numbered section headers and no nested references (no bundle files exist); it is above the 50-line simple-skill exception, so it lands at 4 rather than 5 for structure that is good but does not exercise the one-level-deep reference pattern.

4 / 5

Total

15

/

20

Passed

Description

73%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 focused, trigger-rich description that sharply scopes the skill to owner-cloud staffing and distinguishes it from sibling scopes. The main weakness is that the capability statement is singular and folded into the trigger clause rather than enumerated separately.

DimensionReasoningScore

Specificity

Names the domain ("Agentlas cloud packages") and one concrete action ("staff from THEIR OWN Agentlas cloud packages only") but does not enumerate several distinct capabilities, so it sits at the 1-2-actions anchor rather than the multi-action anchor at 4.

3 / 5

Completeness

Explicit "Use when..." clause gives a clear WHEN with concrete triggers, and the WHAT (staff/route from the owner's own cloud packages) is present but embedded in the trigger clause rather than stated as a standalone capability, so it is not the fully separated what+when of a 5.

4 / 5

Trigger Term Quality

Includes the exact natural slash-command triggers users would type ("/hep-cloud or /agentlas-cloud") plus a plain-language phrasing ("asks to staff from THEIR OWN Agentlas cloud packages"), giving strong keyword coverage; just below 5 because no further synonyms/extensions are enumerated.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers and an explicit contrast against sibling scopes ("Network means Local + owner Cloud + public Hub"), constraining to owner-only cloud, which minimizes conflict with adjacent skills.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentlas-ai/Agentlas-OS
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.