agentlas-graph

Use when the user types /agentlas-graph, /agentlas graph, or /hep-graph to create, list, inspect, or run Agentlas automation graphs.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agentlas-graph/SKILL.md

Quality

Content

61%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 body is an extremely lean alias/pointer skill that delegates the real execution protocol to another skill. It is token-efficient and well-structured as an overview, but offers almost no actionable or workflow detail itself, relying entirely on the referenced skill.

Suggestions

Add a brief inline summary of the core execution step or a one-line command example so the skill is actionable without forcing a full redirect to hephaestus-graph.

Include a short validation/checkpoint note for graph creation and execution, since running DAG automations is a batch operation where missing validation caps workflow clarity.

Confirm the hephaestus-graph/SKILL.md reference resolves within the bundle, or note explicitly that it is a cross-skill dependency, so progressive-disclosure navigation is verifiable.

Dimension	Reasoning	Score
Conciseness	The five-line body is lean and assumes Claude's competence, with no padding or explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	It only names high-level actions ("Create, inspect, schedule, and execute ... graphs") and delegates all execution to hephaestus-graph, providing no concrete steps, code, or commands; matches 'minimal concrete guidance' rather than 1 because it does point to a concrete protocol location.	2 / 5
Workflow Clarity	No multi-step sequence or validation is described in the body, but the single redirect action ("See hephaestus-graph for full execution protocol") is unambiguous; since running DAG graphs is a batch operation with no validation steps present, workflow_clarity is capped at 3.	3 / 5
Progressive Disclosure	The body is a clear overview with a single, well-signaled one-level-deep reference (hephaestus-graph/SKILL.md); not 5 because that reference points outside this skill's bundle (no references/ directory exists) so in-bundle navigation cannot be verified.	4 / 5
	Total	14 / 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 concise, third-person, and clearly states both what the skill does and when to use it, with distinct command-based triggers. Its only weakness is that the action vocabulary is narrow and command-only rather than comprehensive.

Dimension	Reasoning	Score
Specificity	"create, list, inspect, or run Agentlas automation graphs" names the domain plus four concrete actions, matching the 'several specific actions; minor gaps' anchor; not 5 because coverage is narrow rather than comprehensive, not 3 because more than 1-2 actions are listed.	4 / 5
Completeness	It explicitly answers both 'what' (create, list, inspect, or run Agentlas automation graphs) and 'when' ("Use when the user types ...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Trigger phrases "/agentlas-graph, /agentlas graph, or /hep-graph" give good coverage of the natural command invocations a user would type, including synonyms/aliases; not 5 because it is limited to command forms rather than a fuller spread of natural-language phrasings.	4 / 5
Distinctiveness Conflict Risk	"Agentlas automation graphs" paired with three distinct slash-command triggers carves out a clear niche with minimal overlap risk, matching the 'clear niche with distinct triggers' anchor.	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
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: agentlas-ai/Agentlas-OS
Path: .agents/skills/agentlas-graph/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.