nanoresearch-experiment

Generate a Python code skeleton from an experiment blueprint

Quality

61%

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 ./skills/nanoresearch-experiment/SKILL.md

Quality

Content

72%

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 and well-structured with a clear sequenced process and concrete output spec, but it lacks executable examples and a verification step for the batch code-generation workflow. Adding a sample artifact and a validate/run checkpoint would raise the weaker dimensions.

Suggestions

Add a brief concrete example of an expected output artifact, such as a sample ablation config YAML or a model-stub code snippet, to improve actionability.

Insert an explicit validation/verification step in the process, e.g. 'Run the generated run.py with a sample config to confirm the skeleton executes end-to-end'.

Include a checkpoint after code generation to lint or smoke-test the produced files before declaring the task complete.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient with no padding or explanation of concepts Claude already knows; every section (Purpose, Tools, Input, Process, Output) earns its place, matching the level-3 anchor.	3 / 3
Actionability	The 8-step process and exact output file/directory listing are concrete and specific, but there are no executable examples or sample artifacts (e.g., a config YAML or model stub), so key details are missing per the level-2 anchor.	2 / 3
Workflow Clarity	Steps are clearly sequenced as an 8-item numbered list, but generating a full project tree is a batch operation with no validation/verification checkpoint (e.g., confirming the generated code runs), which per the guidelines caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The body is under 50 lines with clear, well-organized sections and is self-contained with no need for external references, satisfying the simple-skill exception that lets progressive disclosure score 3.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 states a concrete single action and domain but lacks explicit trigger guidance and term variation coverage, leaving it at the midpoint across all dimensions. Adding a 'Use when...' clause and listing the concrete sub-actions would lift it toward level 3.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when turning an experiment blueprint into a runnable Python training/evaluation scaffold'.

Enumerate the concrete actions in the description (data loaders, model stubs, training loop, evaluation harness, ablation configs) to raise specificity.

Include natural keyword variations users might say ('experiment scaffold', 'training code skeleton', 'ML boilerplate') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('experiment blueprint') and one concrete action ('Generate a Python code skeleton'), but lists only a single action rather than multiple specific concrete actions, so it does not reach the level-3 anchor.	2 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	'Python code skeleton' and 'experiment blueprint' are relevant terms, but coverage of natural variations a user might say is missing, matching the level-2 anchor rather than the broad term coverage of level 3.	2 / 3
Distinctiveness Conflict Risk	The experiment-scaffolding niche is somewhat specific, but without explicit triggers it could still overlap with general Python code-generation skills, matching the level-2 anchor rather than the clear, distinct-niche level 3.	2 / 3
	Total	8 / 12 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: OpenRaiser/NanoResearch
Path: skills/nanoresearch-experiment/SKILL.md
Commit: 7144364

Reviewed: about 14 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.