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

76%

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 ./openclaw/skills/hephaestus-storm/SKILL.md

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.

A well-sequenced, highly actionable orchestration procedure with strong validation checkpoints and feedback loops. Its main weaknesses are buzzword-padded prose that could be tightened and a monolithic single-file layout that inlines content which could be split into reference files.

Suggestions

Trim redundant framing and repeated slogans (e.g. the "stall, run away, or claim false success" line appears in multiple sections) to reduce token overhead.

Move the route-decision branch table and/or loop invariants into a separate reference file referenced one level deep, leaving SKILL.md as a lean overview.

Replace abstract buzzwords ("pipeline fabric", "force-robust") with plain instructional wording that still preserves the concrete commands.

Dimension	Reasoning	Score
Conciseness	The body is mostly instructional and dense, but carries redundant framing ("Unlike a one-shot answer or a generic parallel fan-out"), slogan repetition ("does not stall, run away, or claim false success") and buzzwords ("force-robust", "verifier-first") that could be trimmed, fitting the mostly-efficient-but-could-be-tightened anchor 3.	3 / 5
Actionability	Provides concrete, executable bash snippets (runner resolution loop, auth ensure, the `hep-storm` invocation) and concrete per-branch actions keyed to real route_decision fields, with only minor gaps such as the `<the user's goal>` placeholder and the assumption a runner is installed.	4 / 5
Workflow Clarity	A clearly sequenced §1-§7 procedure with explicit validation checkpoints (verify, bounded repair/retry, final-gate), feedback loops for error recovery, loop invariants, and hard rules including a no-false-pass validation gate for this batch/destructive-style orchestration, matching the anchor 5 example.	5 / 5
Progressive Disclosure	Headers give some structure but the ~175-line body is a monolithic procedure with the route-decision branch table, loop invariants, and hard rules all inlined; no bundle/reference files exist and nothing is split out, fitting the some-structure-but-could-be-better-organized anchor 3 rather than the under-50-line simple-skill exception.	3 / 5
	Total	15 / 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.

A strong, explicit-trigger description that clearly states both what the skill does and when to use it, anchored by a unique slash command. It is held back from the top tier by buzzword-heavy phrasing and a very broad domain list that invites overlap with generic agent skills.

Suggestions

Replace jargon like "force-robustly drive a loop-worthy goal" and "pipeline fabric" with plain phrasing a user would actually say (e.g. "run a multi-step goal to completion with verification").

Narrow or prioritize the "when" domain list so it does not read as overlapping every general-purpose agent task.

Add 1-2 natural synonyms or file/extension-style triggers to broaden keyword coverage beyond the single slash command.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ("routes the goal to real Agentlas specialists, materializes a dependency-ordered pipeline fabric, and runs a verifier-first loop"), but buzzword-heavy phrasing like "force-robustly" and "pipeline fabric" keeps it just below the comprehensive, fully-concrete anchor 5.	4 / 5
Completeness	Clearly answers both what (routes/materializes/runs a verifier-first loop) and when (an explicit "Use when..." clause with concrete trigger phrases), matching the anchor 5 example.	5 / 5
Trigger Term Quality	Explicit slash-command (/hep-storm), @-mention, and a parenthetical of natural goal domains (apps, sites, agents, automations, debugging, research) give good coverage, but the core phrase "force-robustly drive a loop-worthy goal" is not wording users naturally say, so it falls short of comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The /hep-storm and @Hephaestus storm triggers make it mostly distinct, but the broad "when" domain list (apps, sites, agents, automations, debugging, research, reports) overlaps with general-purpose agent skills, so it is not at the minimal-conflict anchor 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: 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.