Name: hephaestus-storm
Rating: 66.4 (1 reviews)
Author: agentlas-ai

hephaestus-storm

Use when the user types /hep-storm or /agentlas-storm, says @Hephaestus storm <goal>, or asks to drive a goal to verified completion through a force-robust Stormbreaker loop. Stormbreaker routes the goal to real Agentlas specialists, materializes a dependency-ordered pipeline fabric, and runs each work packet as a verifier-first hardened loop that does not stall, run away, or claim false success. Use it for loop-worthy work — apps, sites, agents, automations, debugging, multi-step research, data/report generation. Trivial questions are answered directly, not stormed.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

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

Quality

Content

70%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 a well-sequenced, verifier-first workflow with strong validation feedback loops and concrete executable commands. It loses points on conciseness (padding and restated invariants) and on progressive disclosure (monolithic single-file layout with no supporting reference files).

Suggestions

Move the §5 loop protocol detail and §7 hard rules into a reference file (e.g. references/loop-protocol.md) and keep SKILL.md as an overview, improving progressive disclosure.

Trim the marketing comparison in the intro, the Korean update-fallback line, and the §6 invariants that restate §5 rules to tighten conciseness.

Replace '<the user\'s goal>' placeholders with a worked example goal so the core commands are copy-paste executable without substitution.

Dimension	Reasoning	Score
Conciseness	Mostly procedural and command-driven, but includes unnecessary padding: a Korean update-fallback note, a marketing comparison ('Unlike a one-shot answer or a generic parallel fan-out...'), and §6 'Loop invariants' restating rules already established in §5.	3 / 5
Actionability	Provides concrete, copy-paste-ready shell (runner resolution loop, `auth ensure`, `hep-storm`, `hep-call`) and explicit branch actions per route_decision, with minor gaps from placeholders like '<the user\'s goal>' and dependence on an external binary that may not be installed.	4 / 5
Workflow Clarity	Clear numbered sequence (§1 resolve → §2 sign-in → §3 route/materialize → §4 branch → §5 loop) with explicit validation checkpoints: a verify step, bounded repair/retry with stall detection, and a final-gate that gates success on evidence — a full feedback loop.	5 / 5
Progressive Disclosure	No bundle files exist and the entire ~175-line protocol is inlined in one file with clear section headers; the detailed loop protocol and hard rules could live in separate reference files, so structure is present but content that should be split is inline.	3 / 5
	Total	15 / 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.

The description is explicit, well-triggered, and clearly distinguishable, answering both what and when with concrete invocation phrases. Its main weakness is heavy proprietary jargon ('force-robust', 'verifier-first hardened loop', 'pipeline fabric') that pads length and slightly mutes concrete-capability clarity.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'routes the goal to real Agentlas specialists', 'materializes a dependency-ordered pipeline fabric', 'runs each work packet as a verifier-first hardened loop' — but they are wrapped in proprietary jargon that slightly obscures the actual capabilities, leaving minor gaps versus a fully comprehensive concrete-action list.	4 / 5
Completeness	Explicitly answers both 'what' (routes to specialists, materializes fabric, runs hardened loops, refuses success without evidence) and 'when' (opens with 'Use when the user types...' and closes with 'Use it for loop-worthy work'), with concrete trigger phrases throughout.	5 / 5
Trigger Term Quality	Strong trigger coverage with literal commands ('/hep-storm', '/agentlas-storm', '@Hephaestus storm <goal>') plus natural categories ('apps, sites, agents, automations, debugging, multi-step research, data/report generation'), though a few natural phrasings users might say are absent.	4 / 5
Distinctiveness Conflict Risk	Highly distinctive slash-command and @-invocation triggers tie it to a clear niche (the Stormbreaker/Agentlas loop), making accidental triggering by other skills very unlikely.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: agentlas-ai/Agentlas-OS
Path: .agents/skills/hephaestus-storm/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.