CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agentlas-storm

Use when the user types /agentlas-storm, /agentlas storm, /hep-storm, or says @Hephaestus storm <goal> to drive a goal through the force-robust Stormbreaker loop with real Agentlas specialists.

Quality

60%

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-storm/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

33%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 stub the body is admirably lean, but it delegates 100% of its substance to a protocol file that does not exist in the bundle, leaving the reader with no actionable content, no workflow, and a dead link. Either the referenced hephaestus-storm skill must ship alongside this file, or the core loop steps need to be inlined.

Suggestions

Fix the dangling reference: either include hephaestus-storm/SKILL.md in the bundle or inline the essential loop steps (goal intake, execution, verification gate, retry) directly in this body.

Since the loop is "verifier-first" and drives autonomous execution, include at least a minimal step sequence with an explicit validation checkpoint rather than deferring everything to a missing file.

Drop the redundant "Alias for..." line (the heading and description already state the commands) and replace the buzzword tagline with one sentence describing what the loop actually does.

DimensionReasoningScore

Conciseness

The body is short and un-padded — "Drive a goal through the **Stormbreaker Loop** — Hephaestus' force-robust, verifier-first execution loop" plus an alias line and one pointer — with no explanations of concepts Claude already knows. It misses anchor 5 only because the "Alias for `hephaestus-storm` and `/agentlas storm`" line duplicates the command names already in the heading, and the buzzword tagline adds little informational value.

4 / 5

Actionability

The only guidance is "See [hephaestus-storm](hephaestus-storm/SKILL.md) for full execution protocol" — a single high-level pointer with no executable steps, matching anchor 2's "minimal concrete guidance; missing the specific steps". It does not sink to anchor 1's "only describes rather than instructs" because a concrete file pointer is given, but the pointer is broken: no hephaestus-storm/SKILL.md exists in this bundle, so following the instruction yields nothing.

2 / 5

Workflow Clarity

The skill describes a multi-step execution loop ("verifier-first execution loop") yet the body contains no sequence, no steps, and no validation checkpoints whatsoever — the entire protocol is deferred to a missing file. This matches anchor 1 ("steps missing or incoherent; no sequence; no validation for risky operations"); anchor 2 requires at least a rough sequence, which is absent.

1 / 5

Progressive Disclosure

The body has minimal structure (one heading, three lines) and its sole reference — "See [hephaestus-storm](hephaestus-storm/SKILL.md)" — does not resolve: the bundle contains no references/, scripts/, assets/, or hephaestus-storm/ directory, so navigation fails at the first hop. This lands at anchor 2 (minimal structure, references effectively unusable) rather than 3, whose references are at least present and resolvable.

2 / 5

Total

9

/

20

Passed

Description

68%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 excels at trigger clarity — exact command aliases make it highly discoverable and conflict-free — but the capability statement is marketing-flavored jargon ("force-robust Stormbreaker loop with real Agentlas specialists") that tells a reader little about what the skill actually does. Tightening the "what" into one concrete sentence would raise both specificity and completeness.

Suggestions

Replace buzzword phrases like "force-robust Stormbreaker loop with real Agentlas specialists" with a concrete statement of what the loop does (e.g. "iteratively executes a goal, verifying each step against acceptance criteria before proceeding").

Add one or two natural-language trigger phrases beyond the literal slash commands so users who type a plain-English request also match the skill.

State the observable outcome (e.g. "produces a verified result plus an execution log") so the "what" is explicit rather than inferable.

DimensionReasoningScore

Specificity

The only action stated is "drive a goal through the force-robust Stormbreaker loop with real Agentlas specialists" — one generic action wrapped in buzzwords ("force-robust", "Stormbreaker", "real Agentlas specialists") that convey no concrete capability. This matches anchor 2 (domain named, actions minimal/generic) rather than 3, which would require 1-2 genuinely concrete actions; it is above anchor 1 because the domain and trigger surface are specifically named.

2 / 5

Completeness

Both elements are present: the "what" ("drive a goal through the force-robust Stormbreaker loop") and an explicit "Use when..." clause listing concrete triggers. It does not reach anchor 5 because the "what" is buzzword-laden rather than clearly conveying what the skill actually does, but anchor 3 does not fit since the "when" is fully explicit, not missing or weakly implied.

4 / 5

Trigger Term Quality

It enumerates concrete invocation variants — "/agentlas-storm", "/agentlas storm", "/hep-storm", and "@Hephaestus storm <goal>" — giving good synonym coverage of exact commands. It falls short of anchor 5 because there are no natural-language phrasings (e.g. "run the storm loop on <goal>") beyond the literal commands, only touching anchor 4's "good keyword coverage; a few natural terms missing".

4 / 5

Distinctiveness Conflict Risk

The triggers are exact, distinctive command forms (/agentlas-storm, /hep-storm, @Hephaestus storm) tied to a specific named protocol, forming a clear niche with minimal overlap risk against generic skills. This matches anchor 5 (clear niche with distinct triggers); anchor 4's "minor overlap risk" would require some plausible confusion with related skills, which these literal commands avoid.

5 / 5

Total

15

/

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-storm/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.