CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

74%

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 ./codex/plugins/agentlas-core-engine-meta-agent/skills/agentlas-upload/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

51%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.

The body is maximally lean and well-organized as a redirect stub, but it delegates 100% of its execution protocol to a file (hephaestus-upload/SKILL.md) that is absent from the skill bundle, leaving the skill with no usable instructions, no workflow sequence, and no validation guidance for the scan/gate/publish process it names.

Suggestions

Bundle the delegation target (hephaestus-upload/SKILL.md) or inline the essential steps of the execution protocol — the skill's only directive currently points to a file that does not exist in the bundle, making it unusable as written.

Add a minimal scan → gate → publish sequence with an explicit validation checkpoint before the publish step (e.g., 'only publish when the security scan passes'), since publishing to a public hub is a hard-to-reverse operation.

If this is intentionally an alias-only skill, state how to resolve the target (e.g., the canonical skill's install path or repository location) so the redirect can actually be followed.

DimensionReasoningScore

Conciseness

The body is six lines with zero padding: a heading, a one-line purpose statement ("Package security scan and distribution gate for Agentlas agents and teams"), an alias note, and a single reference link. Every token earns its place and nothing explains concepts Claude already knows, matching anchor 5. Not 4, because there is literally nothing left to trim.

5 / 5

Actionability

The only executable guidance is "See [hephaestus-upload](hephaestus-upload/SKILL.md) for full execution protocol" — and that file is not present in the skill bundle, so the directive cannot actually be followed. "Package security scan and distribution gate" describes rather than instructs, matching anchor 2 (minimal concrete guidance, missing the specific steps). Not 1 because the pointer is a concrete, specific direction rather than pure abstraction; not 3 because no partially executable steps exist in the body at all.

2 / 5

Workflow Clarity

The scan → gate → publish workflow is only named, never sequenced: no steps, no checkpoints, and no validation before publish even though publishing to a public hub is a hard-to-reverse operation that the rubric flags as requiring a feedback loop. The simple-skill exception does not apply because the single action (read the referenced protocol) cannot be completed — the target file is missing from the bundle. Score 2 (rough intent but many gaps, validation absent); not 3 because even anchor 3 expects a listed sequence, and none is present.

2 / 5

Progressive Disclosure

Structurally the body is well-organized with one clearly signaled, one-level-deep reference ("See [hephaestus-upload](hephaestus-upload/SKILL.md)"), but scored against the actual bundle structure the reference is dangling: no hephaestus-upload/ directory, and no references/, scripts/, or assets/ exist. Navigation fails at the first hop, which caps this at 3. Not 4/5 because the sole reference does not resolve; not 2 because nothing that belongs in a separate file is inlined and the reference is prominently, clearly signaled.

3 / 5

Total

12

/

20

Passed

Description

87%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 strong description: it pairs an explicit 'Use when' trigger clause listing four concrete command variants with a clear statement of what the skill does (scan, gate, publish) and where it publishes to. The only softness is that "gate" and the scan's criteria are not elaborated and no natural-language trigger phrases accompany the command aliases.

DimensionReasoningScore

Specificity

The description lists three concrete actions ("scan, gate, and publish an agent/team package") with two named destinations ("Agentlas Cloud (private) or Agentlas Hub (public)"), but "gate" is left unexplained and what the scan checks for is unstated, leaving minor gaps in coverage. This matches anchor 4 (several specific actions, minor gaps) rather than 5, and clearly exceeds anchor 3's 1-2 concrete actions.

4 / 5

Completeness

It explicitly answers both questions: the what ("scan, gate, and publish an agent/team package to Agentlas Cloud (private) or Agentlas Hub (public)") and the when ("Use when the user types /agentlas-upload, /agentlas upload, $hephaestus-upload, or /hep-upload") with concrete trigger phrases. This matches anchor 5's structure exactly; anchor 4 would require a weaker or less explicit 'when' clause.

5 / 5

Trigger Term Quality

Four command variants ("/agentlas-upload, /agentlas upload, $hephaestus-upload, or /hep-upload") cover exactly how a user invokes this skill, giving good keyword coverage with synonyms. It falls short of anchor 5 because natural-language phrases a user might say (e.g., "publish my agent", "upload to Agentlas Hub") are missing, but exceeds anchor 3's single generic keyword.

4 / 5

Distinctiveness Conflict Risk

Product-specific names ("Agentlas Cloud", "Agentlas Hub", "$hephaestus-upload") and unique command strings give this a clear niche with minimal conflict risk against any other skill, matching anchor 5. No other skill would plausibly trigger on these exact command invocations.

5 / 5

Total

18

/

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

codex/plugins/agentlas-core-engine-meta-agent/skills/agentlas-upload/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.