run

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation. Use when the user runs /hub:run or asks to execute a full AgentHub competition end-to-end.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

83%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 a tightly written, well-structured workflow with executable commands and a critical-rules safety section. Minor gaps are the lack of a validate-retry feedback loop on merge and a couple of steps described rather than scripted.

Suggestions

Add an explicit validate-then-retry feedback loop around the merge step (e.g. verify the branch builds/tests before merging, and on failure prompt to re-evaluate), since merging is a destructive batch-style operation.

Turn the 'Run /hub:spawn' and Step 5 evaluation steps into concrete command invocations (with the session-id and flag substitutions) matching the Step 1 example, so every step is copy-paste ready.

Confirm the referenced ../agenthub/references/agent-templates.md path resolves from the skill bundle, or relocate it into references/ so the progressive-disclosure navigation stays one level deep and verifiable.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout: parameter table, numbered steps, and inline code blocks with no padding or re-explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	Provides concrete, executable commands (e.g. the hub_init.py invocation) and parameter values, but a few steps like 'Run /hub:spawn' and the LLM-judge path are described rather than given as copy-paste commands.	4 / 5
Workflow Clarity	A clearly sequenced 6-step lifecycle with a stop-on-failure rule and explicit user-confirmation checkpoint before the destructive merge, though there is no explicit validate-then-retry feedback loop for the merge step.	4 / 5
Progressive Disclosure	Well-organized single-file skill with clear section headers and one-level-deep references (../agenthub/references/agent-templates.md), but the referenced path sits outside the bundle so its existence cannot be confirmed here.	4 / 5
	Total	17 / 20 Passed

Description

91%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 and explicit about both capability and trigger, with a clear distinct niche tied to the /hub:run command. It avoids verbosity and over-claims while covering the full chained lifecycle.

Dimension	Reasoning	Score
Specificity	Lists the full chained lifecycle as concrete actions: 'init → baseline → spawn → eval → merge in a single invocation', which is comprehensive coverage of the specific capabilities.	5 / 5
Completeness	Explicitly answers both what ('chains init → baseline → spawn → eval → merge') and when ('Use when the user runs /hub:run or asks to execute a full AgentHub competition end-to-end') with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Includes natural triggers like '/hub:run' and 'execute a full AgentHub competition end-to-end', but lacks synonyms or the .command extension-style variations a user might say.	4 / 5
Distinctiveness Conflict Risk	Scoped to a single lifecycle command '/hub:run' with a distinct end-to-end trigger, so it is unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: engineering/agenthub/skills/run/SKILL.md
Commit: 19392f7

Reviewed: ~7 hours 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.