nanoresearch-experiment

Generate a Python code skeleton from an experiment blueprint

Quality

55%

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

57%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 well-structured and concise but stays at the level of a process outline: it tells Claude what to produce without executable guidance or any validation step to verify the generated skeleton. Adding concrete code templates and a run/import-check checkpoint would lift actionability and workflow clarity.

Suggestions

Include a minimal executable template (e.g. the run.py entry point or a config-loading snippet) so the guidance is copy-paste ready rather than descriptive.

Add a validation checkpoint after generation, e.g. 'Run `python -c "import experiments"` or a smoke test on run.py with a tiny config to confirm the skeleton is importable and executes.'

Show an example config file structure for an ablation group so the configs step has concrete guidance instead of only naming the deliverable.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or over-explanation of concepts Claude already knows; it stays close to the 'efficient; minor instances that could be trimmed' anchor with essentially nothing to trim.	4 / 5
Actionability	Steps give high-level intent ('Generate training loop with logging, checkpointing, and early stopping', 'Implement model architecture stubs') but no executable code, commands, or concrete implementation specifics, matching the 'high-level hints missing specific steps' anchor.	2 / 5
Workflow Clarity	Eight well-sequenced steps are present, but this batch code-generation workflow has no validation/verification checkpoints (e.g. confirm the skeleton imports/runs), which caps workflow clarity at 3 per the guidelines.	3 / 5
Progressive Disclosure	Under 50 lines, needs no external references, and is cleanly organized into Purpose/Tools/Input/Process/Output sections, satisfying the simple-skill exception for a 5.	5 / 5
	Total	14 / 20 Passed

Description

53%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 names a concrete, niche action but omits any 'when to use' trigger guidance, which caps completeness and limits trigger-term quality. Adding a 'Use when...' clause would meaningfully raise several dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when implementing an experiment from an experiment_blueprint.json, scaffolding research code, or generating train/eval baselines and ablations.'

Broaden natural keywords to include synonyms a user might say (e.g. 'experiment code', 'research skeleton', 'method implementation', 'ablation configs'), not just the artifact name.

List the concrete deliverables in the description itself (data loaders, model stubs, training loop, eval harness, configs) to push specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Python code skeleton') and one concrete action ('Generate'), matching the '1-2 concrete actions but not comprehensive' anchor rather than the multi-action anchors.	3 / 5
Completeness	It clearly states the 'what' ('Generate a Python code skeleton from an experiment blueprint') but has no 'when'/'Use when' trigger guidance, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Relevant terms ('Python code skeleton', 'experiment blueprint') are present but 'blueprint' is a technical artifact name and common user variations/synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	Tied to a specific upstream artifact ('experiment blueprint'), it is mostly distinct with only minor overlap risk; it lacks explicit trigger phrases that would justify a 5.	4 / 5
	Total	13 / 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: OpenRaiser/NanoResearch
Path: skills/nanoresearch-experiment/SKILL.md
Commit: 9d3b440

Reviewed: 11 days 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.