nanoresearch-planning

Produce an experiment blueprint from a research hypothesis

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-planning/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-organized for a simple instruction-only skill, with a clear seven-step sequence and a specified output. Its main gaps are missing concrete output examples/schema and absent validation checkpoints in the workflow.

Suggestions

Add a concrete example of papers/experiment_blueprint.json (a minimal filled-in schema) so the expected output structure is unambiguous and copy-paste ready.

Insert an explicit validation checkpoint near the end of the process, e.g., a step that verifies the blueprint covers every component of the selected hypothesis before compiling the final output.

Tighten abstract criteria such as 'appropriate for validating the hypothesis' into specific, checkable guidance (e.g., dataset must cover the hypothesis's domain, be publicly available, and have a documented split).

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned (Purpose, Tools, Input, Process, Output) with no padding or explanation of concepts Claude already knows; every section earns its place, matching the lean-and-efficient anchor.	3 / 3
Actionability	Steps give some concrete guidance ("2-4 baseline methods", "primary and secondary evaluation metrics") and a field list for the output, but lack a concrete output JSON example/schema and leave key details unspecified (e.g., what makes a dataset "appropriate"), which is incomplete for a 3.	2 / 3
Workflow Clarity	The seven steps are clearly numbered and logically sequenced, but there are no validation or verification checkpoints (e.g., confirming the blueprint covers all hypothesis components) before emitting the output, so it stops at the sequence-with-validation-gaps anchor.	2 / 3
Progressive Disclosure	This is a sub-50-line single-task skill with no need for external references, and its sections are cleanly organized; per the scoring notes that satisfies progressive disclosure at the top level without bundle files.	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 is concise and names a concrete action and niche, but it omits any explicit "Use when..." trigger guidance and covers only a single action with limited natural-language variations. This places it solidly at the midpoint across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g., 'Use when planning experiments from a research hypothesis, designing ablations, or selecting baselines and datasets.'

List multiple concrete actions the skill performs (e.g., 'Select datasets, choose baselines, define metrics, and design ablation groups') to raise specificity from a single action to a comprehensive set.

Include natural term variations users might say ("experiment design", "research plan", "ablation study") alongside "experiment blueprint" to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names a concrete output action ("Produce an experiment blueprint") and its input ("from a research hypothesis"), but lists only a single action rather than the multiple concrete actions required for a 3.	2 / 3
Completeness	It clearly states what the skill does (produce a blueprint) but provides no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	"experiment blueprint" and "research hypothesis" are relevant domain keywords, but common natural variations (e.g., "experiment design", "research plan") are missing and phrasing is formal rather than conversational.	2 / 3
Distinctiveness Conflict Risk	The research-experiment niche is fairly specific, but with no explicit triggers it could overlap with adjacent nanoresearch skills (e.g., ideation), so it is not a clear, conflict-free 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-planning/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.