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

86%

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

Quality

Content

85%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 highly actionable with a clearly sequenced, validation-gated workflow and copy-paste-ready tooling. Its main weakness is progressive disclosure: the monolithic SKILL.md inlines dense contract and receipt detail that would be better placed in reference files.

Suggestions

Extract the §7 receipt field enumeration and the digest-schema constraint rules into a references/ file (e.g. RECEIPTS.md) and link to it one level deep from SKILL.md to reduce inline bulk.

Move the full workforce.* typed-tool call signatures and the digest-schema value rules into a reference file, keeping only the ordered sequence and key boundary rules in SKILL.md.

Trim restated lease/continuity and fail-closed rules that recur across sections 2-4 to tighten the conciseness budget.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (e.g., 'Call these exact typed tools directly... dumping unrelated schemas spends context'), but some boundary and lease/continuity rules are restated across sections and could be trimmed.	4 / 5
Actionability	It provides copy-paste-ready bash for runner resolution, an exact typed-tool call sequence with parameter signatures, and concrete field-level contract values (e.g., decisionAuthor.kind = 'host_llm', bundleDigestSchema digest id).	5 / 5
Workflow Clarity	Steps 1-7 are clearly sequenced with explicit validation checkpoints and fail-closed feedback loops — protocol-version gating, re-plan-on-rejection, and never-report-success-on-fallback rules for the destructive/batch roster operations.	5 / 5
Progressive Disclosure	No bundle files exist and the heavy schema/digest constraints and §7 receipt field enumerations are inlined in a ~330-line SKILL.md; section headers provide some structure, but content that belongs in separate reference files is not split out.	3 / 5
	Total	17 / 20 Passed

Description

87%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 what the skill does and when to use it, with concrete actions and a distinctive OpenClaw-specific niche. The only weakness is keyword coverage that misses a few natural synonyms a user might say.

Dimension	Reasoning	Score
Specificity	The description names concrete actions — 'staff a durable goal', 'chooses the exact roster', 'remains goal-bound until explicit completion' — across Local/Cloud/Hub sources, listing several specific capabilities with only minor gaps in coverage.	4 / 5
Completeness	It explicitly answers both 'what' (staffs a goal-bound roster from Local/Cloud/Hub agents) and 'when' ('Use when the user asks OpenClaw to staff a durable goal') with concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes an explicit 'Use when the user asks OpenClaw to staff a durable goal' trigger with natural phrases and source-type synonyms (Local, Cloud, Hub), but omits common variations like 'assemble a team' or 'hire agents'.	4 / 5
Distinctiveness Conflict Risk	The OpenClaw/Hephaestus, source-scoped, durable-goal framing is a clear niche with distinct triggers and minimal conflict risk against other general skills.	5 / 5
	Total	18 / 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: 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.