hephaestus-network

Use when the user types $hephaestus-network or /hep-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%

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 lean, highly actionable orchestration protocol with a clearly sequenced workflow, explicit validation/feedback loops, and well-organized single-file structure. It assumes Claude's competence and packs specific tool calls and required receipts without padding.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes domain competence; it never explains basic concepts Claude already knows, and each line carries a specific instruction (exact versions, hashes, digests, receipts) that earns its place.	3 / 3
Actionability	It names exact MCP tools, schemas, parameters, and policy env vars (e.g. 'workforce.validate_selection', 'agentlas.workforce-work-order.v1', 'explicitCompletion=true', 'AGENTLAS_MODEL_ALLOCATION_POLICY_JSON'), giving concrete, executable guidance for an instruction-only protocol skill.	3 / 3
Workflow Clarity	A clear numbered 1–7 sequence includes explicit validation feedback loops ('validate_selection, revise on rejection, then prepare_execution') and an explicit success checklist ('planner parse success without fallback... passing verifier'), matching the level-3 anchor.	3 / 3
Progressive Disclosure	This is a self-contained, sub-50-line single-file skill with no external bundle files and no nested references; it is organized into a numbered workflow plus focused prose, which the rubric notes allow to score 3.	3 / 3
	Total	12 / 12 Passed

Description

75%

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 has an explicit trigger and a clear, distinctive niche, but its action list is high-level and its trigger phrasing is jargon-heavy. It answers both 'what' and 'when' well but could be more concrete and use more natural language.

Suggestions

Add concrete operations to the description (e.g., 'search candidates, validate the selection, bind the plan to the goal, and allocate models') to lift specificity toward a comprehensive action list.

Soften the trigger phrasing with plain-language variants a user might actually say (e.g., 'Use when the user wants to assemble or staff a team of agents for a long-running goal'), reducing reliance on ecosystem jargon.

Optionally name the durable-context guarantee in user-friendly terms ('the roster persists across turns and sessions until the goal is explicitly completed') to reinforce the distinctive behavior.

Dimension	Reasoning	Score
Specificity	It names the domain ('staff a durable goal from Agentlas Hub agents or teams') and a couple of actions ('chooses the exact roster', 'goal-bound until explicit completion'), but these are high-level behaviors rather than a comprehensive list of concrete operations as the level-3 anchor requires.	2 / 3
Completeness	It clearly answers what the skill does (staffs a durable goal; host LLM chooses a goal-bound roster) and provides an explicit 'Use when...' trigger for when to invoke it, satisfying the level-3 anchor for both what and when.	3 / 3
Trigger Term Quality	Relevant keywords are present ('staff', 'goal', 'agents', 'teams'), but the phrasing leans on ecosystem jargon ('OpenClaw', 'Agentlas Hub', 'durable goal') and omits common user-level variations, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The trigger is tightly scoped to OpenClaw/Agentlas Hub goal staffing, a clear niche with distinct triggers that is unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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: .agents/skills/hephaestus-network/SKILL.md
Commit: 2eb39ad

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.