hephaestus-build

Use when the user types /prompts:hep-build or /agentlas-build, mentions @Hephaestus for build work, asks to create a single Agentlas agent, create a multi-agent team, or package an existing local/external agent into Agentlas architecture.

Quality

82%

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

77%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 and exceptionally well-sequenced with validation gates, but it is dense for a single SKILL.md with no supporting reference files, leaving progressive disclosure and conciseness as the weakest dimensions.

Suggestions

Extract the engine/runner resolution shell block and the detailed Builder Interview question list into reference files (e.g. references/engine-resolution.md, references/builder-interview.md) and link to them, improving both progressive disclosure and conciseness.

Trim repeated policy restatements (e.g. multiple 'Never overwrite an existing child' / 'Never default to ., the cwd' lines) into a single consolidated constraints note.

Add a short '## Quick reference' overview near the top summarizing the 14 steps so the core flow is scannable before the detail.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and procedural, but it embeds a long engine-resolution shell block plus several verbose policy re-statements (e.g. repeated 'Never overwrite/never default' caveats) that could be tightened without losing clarity.	3 / 5
Actionability	Provides copy-paste-ready shell snippets (engine/runner resolution, `contract resolve-target`, `contract scaffold`, `contract complete`, `contract verify`) with exact flags and explicit blocker handling covering the common build flow.	5 / 5
Workflow Clarity	A clearly numbered 14-step procedure with explicit validation gates (non-zero/error receipts are blockers, verify exit must be zero, team verify gate) and feedback loops (collapse to single-agent or add HQ contracts on failure), satisfying the batch/destructive feedback-loop requirement.	5 / 5
Progressive Disclosure	No references/, scripts/, or assets/ bundle exists, and the body inlines substantial policy and a large shell block that would benefit from being split out; structure is a single Procedure/Output section rather than overview-plus-references.	3 / 5
	Total	16 / 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 a strong, trigger-rich statement that answers both what and when and is well-differentiated. Its only weak spot is that the trigger terms are product-specific commands rather than fully natural language, slightly limiting the natural keyword breadth.

Suggestions

Add a few plain-language trigger synonyms (e.g. 'build an agent', 'assemble an agent team') alongside the slash commands so users without the exact command syntax can still surface the skill.

Consider tightening the parenthetical list of actions so the most common entry point (single-agent creation) leads the enumeration.

Dimension	Reasoning	Score
Specificity	Lists multiple specific actions ('create a single Agentlas agent', 'create a multi-agent team', 'package an existing local/external agent into Agentlas architecture') covering the build surface comprehensively, with only minor gaps in coverage breadth.	4 / 5
Completeness	Explicitly answers both 'what' (create/package Agentlas agents and teams) and 'when' (the 'Use when...' clause enumerating trigger conditions), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes concrete natural triggers ('/prompts:hep-build or /agentlas-build', 'mentions @Hephaestus for build work') that a user would actually say, though coverage leans on product-specific invocations and omits some common-skill synonyms.	4 / 5
Distinctiveness Conflict Risk	The @Hephaestus mention and /prompts:hep-build / /agentlas-build slash triggers carve a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: agentlas-ai/Agentlas-OS
Path: codex/plugins/agentlas-core-engine-meta-agent/skills/hephaestus-build/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.