hephaestus-network

Use when the user asks OpenClaw to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM chooses the exact roster, which remains goal-bound until explicit completion.

Quality

64%

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-network/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.

The content is a well-sequenced, highly actionable workflow with strong validation checkpoints, but it is verbose with repeated prohibitions and inlines reference-grade detail that would benefit from progressive disclosure into separate files.

Suggestions

Move the dense digest/schema/policy rules (e.g., the bundleDigestSchema and execution-receipt field lists) into a references/ file and link to it from the body, keeping SKILL.md as an overview.

Consolidate the scattered 'Do not / Never / must not' prohibitions into a single concise 'Boundaries' section to reduce repetition and token cost.

Prune edge-case enumerations that do not change the core workflow (e.g., redundant lease and standby clarifications) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is dense and domain-specific (MCP contracts, digest schemas, release pinning) rather than explaining basics Claude already knows, but it is heavily padded with repeated negative rules ('Do not...', 'Never...', 'must not') and edge-case enumerations that could be tightened.	3 / 5
Actionability	It provides concrete executable guidance: a copy-paste bash runner-resolution script and an exact ordered MCP tool-call sequence with named parameters, though several call signatures use '...' placeholders that are justified rather than fully literal.	4 / 5
Workflow Clarity	The numbered sections 1-7 form a clear sequence with explicit validation checkpoints (validate_selection, validate_execution_receipt, 'fail closed', 'Re-plan on rejection') and feedback loops for error recovery, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	The body is a single ~360-line file with good section headers but no references to separate files, and large blocks of digest/schema rules that could live in references are inlined; no bundle files exist to offload detail.	3 / 5
	Total	15 / 20 Passed

Description

58%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 highly distinctive and clearly answers what and when, but its trigger phrasing is jargon-heavy and unlikely to match natural user language. Tightening the trigger terms and adding concrete action verbs would raise specificity and trigger quality.

Suggestions

Add natural-language trigger phrases a user would actually say (e.g., 'Use when the user wants to assemble a team of agents for a long-running task, recruit workers for a goal, or staff a multi-agent project').

Replace jargon like 'staff a durable goal' with at least one plain-English synonym alongside the project term to broaden trigger coverage.

Spell out one or two more concrete operations (e.g., 'recruit, validate, and bind agents to a goal') to lift specificity above a single abstract action.

Dimension	Reasoning	Score
Specificity	Phrases like 'staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams' and 'chooses the exact roster, which remains goal-bound until explicit completion' name the domain and a couple of concrete actions, but the actions are framed in project-specific jargon rather than multiple clearly concrete operations.	3 / 5
Completeness	It explicitly answers both 'what' (staffs a roster from Local/Cloud/Hub that stays goal-bound) and 'when' (the 'Use when...' clause), but the 'when' lacks synonyms or alternative trigger phrasings.	4 / 5
Trigger Term Quality	The trigger 'Use when the user asks OpenClaw to staff a durable goal' relies on technical jargon ('OpenClaw', 'staff a durable goal') that a user would rarely say naturally; it is missing the common phrasings a user would actually utter.	2 / 5
Distinctiveness Conflict Risk	The OpenClaw / Local-Cloud-Hub staffing niche and the 'goal-bound until explicit completion' framing are highly distinctive with minimal overlap risk against generic skills.	5 / 5
	Total	14 / 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-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.