setup

Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator. Use when the user runs /ar:setup or asks to start optimizing a file with the autoresearch loop.

Quality

81%

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

75%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 well-structured and actionable, with concrete script commands, a clear interactive sequence, and a reporting section. It is held back from 5s by template placeholders in commands, a few trimmable phrases, and an inline evaluators table that could live in a reference file.

Suggestions

Move the Built-in Evaluators table into a references file (e.g. evaluators.md) and link to it, keeping SKILL.md as a leaner overview.

Add an explicit validation checkpoint in the interactive flow confirming the eval command produced a baseline metric before declaring setup complete.

Replace template placeholders ({skill_path}, {domain}, {eval_cmd}) with a concrete worked example so the primary command is copy-paste-runnable as-is.

Dimension	Reasoning	Score
Conciseness	The body is lean with tables and code blocks and avoids explaining concepts Claude already knows; only minor phrasing in the interactive-mode steps could be trimmed, keeping it just below a 5.	4 / 5
Actionability	Concrete, copy-pasteable invocations like "python {skill_path}/scripts/setup_experiment.py --domain {domain} ..." and explicit per-parameter prompts provide mostly executable guidance, with template placeholders ({skill_path}, {domain}) needing substitution as a minor gap.	4 / 5
Workflow Clarity	The interactive flow is a clear numbered sequence (steps 1-8) with a target-file "Verify it exists" checkpoint and an after-setup baseline/eval-result report; setup is non-destructive so the validation cap does not apply, leaving only minor checkpoint gaps.	4 / 5
Progressive Disclosure	No bundle files are present, but the body is a well-organized self-contained overview (Usage, What It Does, Built-in Evaluators, After Setup) with a one-level-deep reference to the setup script; the inline eight-row evaluators table is the main content that could be split out, holding it at 4.	4 / 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 concise and complete, clearly stating both the capability and a concrete trigger clause. It enumerates specific collected parameters and uses a distinct command/loop trigger, with only minor room to broaden natural synonyms.

Dimension	Reasoning	Score
Specificity	"Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator" enumerates several concrete collection actions with comprehensive parameter coverage, just shy of the multi-action breadth of a 5.	4 / 5
Completeness	It explicitly states what it does ("Set up a new autoresearch experiment... Collects domain, target file, eval command, metric, direction, and evaluator") and when to use it ("Use when the user runs /ar:setup or asks to start optimizing a file"), matching the anchor for both what and when with concrete triggers.	5 / 5
Trigger Term Quality	Natural trigger phrases like "/ar:setup", "start optimizing a file", and "autoresearch loop" give good keyword coverage, though a few common synonyms or variations are absent.	4 / 5
Distinctiveness Conflict Risk	The autoresearch experiment-setup niche with dedicated triggers ("/ar:setup", "autoresearch loop") is clearly distinct with minimal conflict 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
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/autoresearch-agent/skills/setup/SKILL.md
Commit: 19392f7

Reviewed: ~6 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.