hephaestus-build

Use when the user types /prompts:hep-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

96%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an efficient, highly actionable, well-sequenced procedure with strong validation feedback loops. Its main weakness is progressive disclosure: it references docs/ and scripts/ files that are not bundled, and keeps sizable inline detail rather than splitting it out.

Suggestions

Bundle the referenced files (docs/builder-interview-research-gate.md, scripts/verify-team-package.sh, scripts/verify-package.sh, and the docs/*.md outputs) under references/ or scripts/ so the signaled references actually resolve.

Move the long step-4 interview/research bullet list into a dedicated reference doc and link to it one level deep, keeping the SKILL.md procedure as a lean overview.

Add a short navigation/index section listing the support files so the one-level-deep references are clearly signaled.

Dimension	Reasoning	Score
Conciseness	The 14-step procedure is dense and lean, using concrete paths and commands without explaining concepts Claude already knows; nearly every token earns its place.	3 / 3
Actionability	Provides specific executable commands and file targets such as 'scripts/verify-team-package.sh <generated-package-root>' and 'upload <exact-verified-package-root> --visibility private-link', giving copy-paste-ready guidance.	3 / 3
Workflow Clarity	A clear numbered sequence with explicit validation checkpoints and a feedback loop: step 11 fails-the-build behavior ('do not report completion; collapse...') followed by step 12 verification before proceeding.	3 / 3
Progressive Disclosure	The body references docs/ and scripts/ paths (e.g. docs/builder-interview-research-gate.md, scripts/verify-package.sh) but no references/, scripts/, or assets/ bundle files exist, so the signaled references are not backed by an actual bundle and the long step-4 interview/research detail is inline.	2 / 3
	Total	11 / 12 Passed

Description

100%

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 specific, trigger-rich, and explicitly answers both what the skill does and when to use it, with clear distinctiveness. It is a strong, concise description with no significant weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'create a single Agentlas agent', 'create a multi-agent team', and 'package an existing local/external agent into Agentlas architecture', matching the top anchor.	3 / 3
Completeness	An explicit 'Use when...' clause answers when, while the enumerated create/package actions answer what, satisfying both halves.	3 / 3
Trigger Term Quality	Includes natural user-facing triggers like '/prompts:hep-build', 'mentions @Hephaestus for build work', and the create/package phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The dedicated /prompts:hep-build and @Hephaestus triggers plus the Agentlas-specific packaging niche make it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 2 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: 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.