agentlas-upload

Use when the user types /agentlas-upload, /agentlas upload, $hephaestus-upload, or /hep-upload to scan, gate, and publish an agent/team package to Agentlas Cloud (private) or Agentlas Hub (public).

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agentlas-upload/SKILL.md

Quality

Content

58%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.

As an alias skill the body is appropriately lean and well-structured, deferring cleanly to the canonical skill. Its weakness is that the body itself carries no executable steps or validation guidance, leaving actionability and workflow clarity to the referenced file.

Suggestions

Add a one-line summary of the scan/gate/publish sequence and the gate's pass/fail criteria so the body is minimally actionable even if the referenced skill is unavailable.

State the validation checkpoint that constitutes the 'gate' (e.g. what a failed scan prevents) so the publish workflow's safety check is visible in the overview.

Confirm the hephaestus-upload/SKILL.md reference resolves within the plugin bundle; if it is external, note that explicitly so navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	Four lean lines that state purpose, aliases, and a single redirect; every token earns its place and nothing over-explains.	5 / 5
Actionability	The body only redirects to hephaestus-upload/SKILL.md ('See ... for full execution protocol') with no concrete code, commands, or steps present in the body itself.	2 / 5
Workflow Clarity	Scan/gate/publish implies a rough sequence, but no steps are listed and no validation checkpoints appear in the body; for a publish (batch/destructive-leaning) operation this stays well below the cap of 3.	2 / 5
Progressive Disclosure	A clean overview that signals one one-level-deep reference (hephaestus-upload/SKILL.md) for the full protocol; appropriate split with easy navigation and no bundle files to complicate structure.	5 / 5
	Total	14 / 20 Passed

Description

92%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 strong: it pairs an explicit 'Use when' trigger with three concrete actions and named destinations, plus four command aliases for distinctiveness. The only minor gap is the absence of natural-language trigger phrasings beyond the command syntax.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ('scan, gate, and publish') with specific destinations (Agentlas Cloud private / Agentlas Hub public), giving comprehensive coverage of the task.	5 / 5
Completeness	Explicitly answers both 'when' ('Use when the user types ...') and 'what' ('to scan, gate, and publish ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Lists four command-alias variants covering synonyms well, but provides only command tokens and no natural-language phrases a user might say without typing a command.	4 / 5
Distinctiveness Conflict Risk	Highly specific, namespaced command triggers carve out a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: agentlas-ai/Agentlas-OS
Path: .agents/skills/agentlas-upload/SKILL.md
Commit: 7032c0b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.