ar-resume

Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:ar-resume or asks to pick up a previously started autoresearch experiment.

Quality

85%

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

82%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 concise, well-structured, and gives mostly executable bash guidance with a clear sequenced workflow. The main gaps are parameterized (non-copy-paste) commands, absent validation checkpoints, and a referenced setup script that is not bundled.

Suggestions

Add an explicit validation checkpoint after 'git checkout' and after reading results.tsv (e.g., if the branch or file is missing, fall back to setup_experiment.py) to support error recovery and raise workflow clarity.

Replace parameterized placeholders with concrete examples or note how {skill_path}, {domain}, and {name} are resolved, so commands are closer to copy-paste ready.

Either bundle the referenced scripts/setup_experiment.py or rephrase the Step 1 command so the body does not point to a non-existent bundle file.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized into Usage and a 4-step 'What It Does' with tight bash/example blocks; it assumes Claude's competence and avoids explaining what experiments or git are, matching the score-5 'lean and efficient' anchor.	5 / 5
Actionability	Quotes concrete executable commands ('python {skill_path}/scripts/setup_experiment.py --list', 'git checkout autoresearch/{domain}/{name}', 'cat .autoresearch/{domain}/{name}/results.tsv', 'git log --oneline -20'); not 5 because placeholders ({skill_path}, {domain}/{name}) prevent direct copy-paste and the /ar:run and /ar:loop handoffs are described rather than given as commands.	4 / 5
Workflow Clarity	A clear numbered 4-step sequence (list → load context → report state → ask next action) matches the score-4 anchor 'clear sequence with most checkpoints present'; not 5 because there are no explicit validation/error-recovery checkpoints (e.g., what to do if the branch or results.tsv is missing).	4 / 5
Progressive Disclosure	Content is a single well-organized self-contained file with clear sections and only one-level sibling-skill references (/ar:run, /ar:loop); not 5 because the body references {skill_path}/scripts/setup_experiment.py yet no scripts/ bundle directory exists, leaving a dangling reference.	4 / 5
	Total	17 / 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 strong: it states concrete actions, an explicit 'Use when...' trigger, and a distinct niche tied to a specific command. Minor weakness is slightly limited trigger-synonym breadth and one generic verb ('continue iterating').

Dimension	Reasoning	Score
Specificity	Quotes 'Checkout the experiment branch, read results history, continue iterating' — three concrete actions named, matching the score-4 anchor 'Lists several specific actions; minor gaps'; not 5 because 'continue iterating' is generic and coverage of sub-actions is incomplete.	4 / 5
Completeness	Explicitly answers both what ('Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating.') and when ('Use when the user runs /ar:ar-resume or asks to pick up a previously started autoresearch experiment.') with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Quotes 'Use when the user runs /ar:ar-resume or asks to pick up a previously started autoresearch experiment' — good natural trigger coverage (resume, pick up, previously started); not 5 because synonym/file-extension breadth is limited for this niche.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific slash command /ar:ar-resume and a narrow autoresearch-experiment niche, giving a clear trigger with minimal conflict risk, matching the score-5 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
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/ar-resume/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.