Name: hephaestus-network
Rating: 60 (1 reviews)
Author: agentlas-ai

hephaestus-network

Use when the user types $hephaestus-network, /hep-network, or /agentlas-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

68%

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-network/SKILL.md

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

Quality

Content

63%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 precise, actionable MCP-orchestration protocol with a well-sequenced workflow and explicit validation checkpoints. Its weaknesses are verbosity from repeated negation rules and a monolithic structure that inlines detail a multi-file bundle could offload.

Suggestions

Consolidate the scattered 'Do not'/'Never' prohibitions into a single 'Boundaries' section to cut repetition and tokens.

Move the detailed receipt field lists (section 7) and the execution-plan digest rules (section 3) into a references/ file linked one level deep, keeping SKILL.md as an overview.

Fill in the ellipsis parameters in the Required MCP sequence block or link to a parameter reference so the calls are copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no basic-concept padding), but it is noticeably long with repeated negation rules ('Do not echo', 'Never fabricate', 'must not') that could be consolidated.	3 / 5
Actionability	It gives a concrete MCP tool sequence with named tools and parameters (workforce.preflight_work_order(taskBrief=..., roles=..., edges=...)) plus an executable runner-resolution bash snippet; minor gaps remain where parameters are ellipses.	4 / 5
Workflow Clarity	A clear numbered 1-7 sequence (analysis, retrieve, validate/pin, bind goal, resolve model, execute, receipts) with explicit validation gates (validate_selection, validate_execution_receipt) and feedback loops ('Re-plan on rejection', 'fail closed on mismatch'); the sheer density creates minor linear-following gaps.	4 / 5
Progressive Disclosure	Section headers provide reasonable in-file structure, but with no bundle files (references/scripts/assets absent) the ~360-line protocol detail, field lists, and receipt schemas are all inlined rather than split into one-level-deep references.	3 / 5
	Total	14 / 20 Passed

Description

73%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 a strong, third-person trigger-rich statement with an explicit 'Use when...' clause and niche command tokens that sharply limit conflict risk. Its main weakness is that the core capability is described in domain jargon rather than crisp concrete actions.

Suggestions

Replace abstract phrasing like 'staff a durable goal' with 1-2 concrete verbs a user would recognize (e.g. 'recruit, bind, and run a team of agents for a long-running task').

Add a plain-language synonym or two for users who describe the need without the command token (e.g. 'assemble an agent team', 'assign agents to a project').

Dimension	Reasoning	Score
Specificity	It names the domain ('staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams') and a concrete action (staffing/goal-binding), but the core action stays abstract rather than enumerating multiple specific operations.	3 / 5
Completeness	Both 'what' (staff a durable roster from Local/Cloud/Hub) and 'when' (explicit 'Use when...' with concrete triggers) are present, but the 'what' leans on jargon ('durable goal', 'goal-bound') that could be more explicit.	4 / 5
Trigger Term Quality	It lists explicit trigger tokens ('$hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus') plus a natural phrasing ('asks Agentlas to staff a durable goal'), giving good coverage though a few casual synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Highly niche command tokens and the @Hephaestus mention make it clearly distinguishable with minimal overlap risk against other skills.	5 / 5
	Total	16 / 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-network/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.