hephaestus-storm

Use when the user types /hep-storm, mentions @Hephaestus storm, or asks to force-robustly drive a loop-worthy goal (apps, sites, agents, automations, debugging, multi-step research, data/report generation) to a verified finish. Stormbreaker routes the goal to real Agentlas specialists, materializes a dependency-ordered pipeline fabric, and runs a verifier-first loop that does not stall, run away, or claim false success. 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

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

73%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-structured, actionable workflow with strong validation and feedback loops, scoring high on actionability and workflow clarity. Its weaknesses are mild jargon padding and some redundancy that hurt conciseness, and the lack of any bundle-file split for a 175-line skill caps progressive disclosure at 4.

Suggestions

Trim redundant restatement between §5 (act/verify/bounded repair/final-gate) and §6 (loop invariants) so each point appears once.

Replace proprietary jargon ('pipeline fabric', 'force-robust') with plain terms unless the term is load-bearing for the protocol.

Consider extracting the route-decision branch table (§4) into a reference file to shorten the main body and lift progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence without explaining basics, but recurring jargon ('force-robust', 'verifier-first execution loop', 'dependency-ordered pipeline fabric') and redundancy between §5 steps and §6 invariants could be tightened.	3 / 5
Actionability	Provides concrete, mostly executable shell commands (runner resolution loop, 'auth ensure', 'hep-storm ... --research-evidence', 'hep-call ... --project .') with only minor gaps such as the '<the user's goal>' placeholder and the unspecified AGENTLAS_HOST_RUNTIME default.	4 / 5
Workflow Clarity	A clearly sequenced §1–§7 workflow with explicit validation checkpoints (verify, bounded repair/retry with stall detection and iteration ceilings, final-gate) and feedback loops for error recovery; the batch/destructive-operation cap does not apply because validation is present and prominent.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references and all content at one level; at ~175 lines with no bundle files, a small amount of inline material (route-decision branches, loop invariants) could arguably be split out, which keeps it just below 5.	4 / 5
	Total	16 / 20 Passed

Description

83%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 explicitly covers both what the skill does and when to invoke it, with concrete trigger phrases and a scope exclusion. Its main weakness is buzzword padding ('force-robustly', 'loop-worthy', 'pipeline fabric') that slightly undermines specificity and naturalness of the trigger terms.

Suggestions

Replace buzzword phrasing like 'force-robustly drive a loop-worthy goal' with plain language a user would actually type (e.g., 'drive a multi-step goal to a verified finish').

Tighten the domain list so the trigger does not overlap with generic coding/automation skills; lead with the distinctive '/hep-storm' and '@Hephaestus storm' signals.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('routes the goal to real Agentlas specialists, materializes a dependency-ordered pipeline fabric, and runs a verifier-first loop that does not stall, run away, or claim false success') with only minor coverage gaps, though some phrasing ('force-robustly', 'loop-worthy') leans on buzzwords.	4 / 5
Completeness	Explicitly answers both what (routes/materializes/runs a verifier-first loop) and when ('Use when the user types /hep-storm, mentions @Hephaestus storm, or asks to...'), with concrete trigger phrases and a scope exclusion ('Trivial questions are answered directly, not stormed').	5 / 5
Trigger Term Quality	Good keyword coverage with explicit triggers ('/hep-storm', '@Hephaestus storm') plus natural domain terms (apps, sites, agents, automations, debugging, multi-step research, data/report generation); 'force-robustly drive a loop-worthy goal' is not phrasing a user would naturally say, costing the top score.	4 / 5
Distinctiveness Conflict Risk	The '/hep-storm' and '@Hephaestus storm' triggers give it a clear niche with minimal conflict risk, but the broad domain list (apps, sites, agents, automations, debugging, research) overlaps with general coding/automation skills, preventing a 5.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: agentlas-ai/Agentlas-OS
Path: openclaw/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.