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.

63

Quality

74%

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 ./.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

75%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-structured, actionable routing skill with concrete shell commands, an explicit MCP tool sequence, and clear error-handling checkpoints. The main improvement space is tightening redundancy between the scope and hard-rules sections and factoring the long runner-resolution script into a bundled script.

Suggestions

Consolidate the repeated source_not_supported / scope-boundary guidance so it lives once (section 0 or section 5) and is referenced rather than restated, improving conciseness.

Move the multi-line runner-resolution bash block into a scripts/ file (e.g., scripts/resolve-runner.sh) and invoke it from the body, which would lift progressive_disclosure and shorten the SKILL.md overview.

Provide a minimal concrete WorkOrder/selection example with realistic (non-redacted) field shapes so the MCP call sequence is fully copy-paste ready at actionability level 5.

DimensionReasoningScore

Conciseness

The body is dense and procedural, assuming Claude's competence without explaining basics, with only minor padding (the scope rule in section 0 overlaps with the hard rules in section 5, and source_not_supported guidance is restated across sections 1 and 3); it is more efficient than the level-3 anchor but not perfectly lean.

4 / 5

Actionability

It provides concrete executable guidance: a copy-paste bash runner-resolution loop, an `auth ensure` command, and a typed MCP tool sequence (`workforce.search_candidates`, `validate_selection`, etc.); it stops short of level 5 only because WorkOrder/selection arguments are redacted placeholders (`workOrder=...`, `selection=...`).

4 / 5

Workflow Clarity

Sections 0-5 form a clear ordered sequence (scope -> resolve runner -> core contract -> sign-in -> staff -> act on result -> hard rules) with explicit error checkpoints ('If no runner exists...', 'If bootstrap is blocked, stop', 'report source_not_supported; never fall back'), meeting the level-4 'clear sequence with most checkpoints' rather than the fully-recoverable level-5.

4 / 5

Progressive Disclosure

The skill is a single self-contained routing document with well-organized numbered sections and no external bundle files (references/scripts/assets absent), so structure is good; because it exceeds ~50 lines and inlines some material that could live in a reference (e.g., the runner-resolution script), it is level 4 rather than the minimal-organization level 5.

4 / 5

Total

16

/

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 tightly scoped, well-triggered routing description that clearly separates the owner-Cloud scope from Hub/Network alternatives. Its main weakness is specificity: it conveys a single staffing/routing action rather than a comprehensive set of concrete capabilities.

Suggestions

Lead with a short 'what' clause (e.g., 'Routes requests to the signed-in user\'s own Agentlas cloud packages') before the 'Use when' trigger list so the capability is stated independently of the trigger.

Add one or two more concrete actions (e.g., 'searches owner-Cloud releases, validates selections, prepares pinned execution') to lift specificity toward comprehensive coverage.

Include a common synonym or two (e.g., 'my cloud packages' / '보관함') so trigger coverage reaches the natural-term breadth of level 5.

DimensionReasoningScore

Specificity

The description names the domain ("Agentlas cloud packages") and one concrete action ("staff from THEIR OWN ... cloud packages only") but does not enumerate multiple distinct capabilities, fitting the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action level 4.

3 / 5

Completeness

It answers both 'when' ("Use when the user types /hep-cloud...") and 'what' (staff/route from the owner's own cloud packages) with concrete triggers, but the 'what' is embedded in the when-clause rather than stated as a standalone capability, so it is not the fully explicit level 5.

4 / 5

Trigger Term Quality

Explicit trigger phrases include the slash commands "/hep-cloud" and "/agentlas-cloud" plus the natural phrase "asks to staff from THEIR OWN Agentlas cloud packages", giving good keyword coverage; it falls just short of level 5 because no synonyms or alternative phrasings are listed.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply defined by product-specific slash commands and an explicit scope boundary ("Cloud is one exact source scope; Network means Local + owner Cloud + public Hub"), giving distinct triggers and minimal conflict risk with sibling 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.