autoresearch

Run bounded automated experiment iterations by recording baselines, applying hypothesis patches, comparing metrics, protecting regression guards, and deciding keep, discard, rollback, or block. Use when automated research is requested or a repo/skill needs evidence-backed research, metric tracking, or safe optimisation loops.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

85%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.

Well-structured content with executable examples, explicit validation feedback loops, and clean one-level-deep references. Minor conciseness and actionability polish would reach the top anchors.

Dimension	Reasoning	Score
Conciseness	Lean, dense prose with tight headers and economical bullets, assuming Claude's competence; only minor phrases could be trimmed, so it sits just below fully lean.	4 / 5
Actionability	Provides concrete ledger YAML and executable shell commands (uv run train.py, ./bin/ask evals run), with minor gaps such as the bare 'apply_patch' placeholder and some procedural-only guidance.	4 / 5
Workflow Clarity	A 9-step workflow with explicit validation checkpoints (baseline first, guard checks, held-out checks, fail-fast) and keep/discard/block feedback loops for batch and destructive operations.	5 / 5
Progressive Disclosure	A dedicated Progressive Disclosure section points one level deep to real bundle files (autoresearch-project.md, contract.yaml, evals.yaml, task-profile.json), keeping the body an overview with clear navigation.	5 / 5
	Total	18 / 20 Passed

Description

88%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.

A strong, specific description with explicit trigger guidance and concrete capabilities. Slight headroom on trigger-term variety and distinctiveness versus broader research skills.

Dimension	Reasoning	Score
Specificity	Lists five concrete actions (recording baselines, applying hypothesis patches, comparing metrics, protecting regression guards, deciding keep/discard/rollback/block), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly states what the skill does and includes a concrete 'Use when automated research is requested or a repo/skill needs...' trigger clause, satisfying both what and when.	5 / 5
Trigger Term Quality	Natural terms like 'automated research', 'evidence-backed research', 'metric tracking', and 'safe optimisation loops' are present, but coverage leans technical and lacks synonym/extension variants, falling just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The bounded-experiment-loop niche with regression guards is mostly distinct, but 'research', 'metric tracking', and 'optimisation loops' could overlap with general experimentation skills.	4 / 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
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: jscraik/Agent-Skills
Path: Skills/agent-ops/autoresearch/SKILL.md
Commit: 2f91362

Reviewed: 1 day 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.