Name: hephaestus-storm
Rating: 69.6 (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

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

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

Quality

Content

81%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 content is a well-sequenced, executable protocol with strong validation gates and concrete shell commands throughout. Its main room for improvement is trimming repeated jargon and possibly externalizing some inline detail.

Suggestions

Consolidate the repeated 'force-robust / verifier-first / does not stall, run away, or claim false success' phrasing so it appears once rather than being restated across the intro, §5, and §6.

Consider moving the full runner-resolution shell block and the route-decision branch table into a referenced reference file so SKILL.md reads as a lean overview.

Replace the '<the user's goal>' placeholder in the §3 example with a concrete illustrative goal so the command is fully copy-paste-ready.

Dimension	Reasoning	Score
Conciseness	The body is action-oriented and avoids explaining basics Claude already knows, but recurring phrases like 'force-robust', 'verifier-first', and the restated loop invariants in §6 add some padding that could be trimmed.	4 / 5
Actionability	It provides concrete, mostly copy-paste-ready shell snippets (runner resolution, 'auth ensure', 'hep-storm ... --research-evidence', 'hep-call ... --project .') and a concrete branch table, with only minor placeholder gaps like '<the user's goal>'.	4 / 5
Workflow Clarity	A clear numbered sequence (§1–§7) with explicit validation checkpoints — scope-lock, issue contract, verify, bounded repair/retry, final-gate — and feedback loops for a destructive/batch-class operation, satisfying the validation requirement rather than capping at 3.	5 / 5
Progressive Disclosure	Single self-contained file with well-organized numbered sections and no bundle files to reference; no nested links, though some inline detail (e.g. the full runner-resolution script and branch table) could be split out for an even cleaner overview.	4 / 5
	Total	17 / 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 explicitly answers both what the skill does and when to use it, with concrete trigger phrases and a clear scope boundary against trivial questions. Its only weakness is jargon-laden action phrasing that could read as marketing rather than plain capability.

Dimension	Reasoning	Score
Specificity	Concrete actions are stated — 'routes the goal to real Agentlas specialists, materializes a dependency-ordered pipeline fabric, and runs each work packet as a verifier-first hardened loop' — listing several specific operations, though they are wrapped in product jargon rather than plain verbs.	4 / 5
Completeness	Both what and when are explicit: 'Use when the user types /hep-storm...', 'Use it for loop-worthy work — ... Trivial questions are answered directly, not stormed' cleanly state capability and trigger conditions with concrete phrases.	5 / 5
Trigger Term Quality	Strong natural trigger coverage with '/hep-storm or /agentlas-storm', '@Hephaestus storm <goal>', and a useful scope list ('apps, sites, agents, automations, debugging, multi-step research, data/report generation'), but a few common phrasings a user might say are absent.	4 / 5
Distinctiveness Conflict Risk	Distinctive slash-command and mention triggers plus a narrow 'verified completion through a Stormbreaker loop' niche make this unlikely to fire for unrelated skills.	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: a7988bb

Reviewed: 4 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.