Tooluck logoTooluck
SKILL.md

nanoresearch-planning

Agent skill fromOpenRaiser/NanoResearch

Produce an experiment blueprint from a research hypothesis

How to install nanoresearch-planning

install nanoresearch-planning
# install the NanoResearch pack with the skills CLI
npx skills add OpenRaiser/NanoResearch

# or add only this skill to Claude Code: copy the folder

skills/nanoresearch-planning/

# into

~/.claude/skills/nanoresearch-planning/ (all projects)

.claude/skills/nanoresearch-planning/ (one project)

skills/nanoresearch-planning/SKILL.md

MITFull file
1# Planning Skill
2
3## Purpose
4Take the selected hypothesis from ideation and produce a detailed experiment blueprint specifying datasets, baselines, evaluation metrics, and ablation groups.
5
6## Tools Required
7None. This skill operates entirely through LLM reasoning over the ideation output.
8
9## Input
10- `ideation_output`: Path to `papers/ideation_output.json` produced by the ideation skill
11
12## Process
131. Parse the selected hypothesis and supporting literature from the ideation output
142. Identify candidate datasets that are publicly available and appropriate for validating the hypothesis
153. Select 2-4 baseline methods from the surveyed literature for comparison
164. Define primary and secondary evaluation metrics aligned with the hypothesis
175. Design ablation groups that isolate each novel component of the proposed approach
186. Estimate computational requirements and timeline for each experiment
197. Compile everything into a structured experiment blueprint
20
21## Output
22Produces `papers/experiment_blueprint.json` containing:
23- Selected hypothesis (carried forward)
24- Dataset specifications (name, source, splits, preprocessing steps)
25- Baseline methods with references
26- Evaluation metrics and success criteria
27- Ablation study design (groups, variables, expected outcomes)
28- Resource estimates and experiment schedule

Excerpt shown under the repository's MIT license.

More skills in NanoResearch

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates