New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Claim-Driven Experiment Planner

by zjYao36 in zjYao36/Auto-Research-Refine

Turns a refined research proposal into a claim-to-evidence-to-run-order roadmap instead of a sprawling benchmark wishlist.

No licenceAuto-check: notesResearch & Science

Install Claim-Driven Experiment Planner

skills CLI
$ npx skills add zjYao36/Auto-Research-Refine --skill experiment-plan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zjYao36/Auto-Research-Refine experiment-plan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zjYao36/Auto-Research-Refine.git skills-src && mkdir -p .claude/skills && cp -r skills-src/experiment-plan .claude/skills/experiment-plan && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
experiment-plan
GitHub stars
128
Used in
6 other repos
Token cost
~2.3k tokens
SKILL.md length
858 words
Files
2
Skills in repo
3
Repo updated
First seen
Licence
None found

At a glance

Turns a refined research proposal into a claim-to-evidence-to-run-order roadmap instead of a sprawling benchmark wishlist.

  • Works in 6 steps: Load the Proposal Context → Freeze the Paper Claims → Build the Experimental Storyline → …
  • Turning a stable method proposal into a concrete experiment plan
  • SKILL.md covers Overview, Constants, Workflow and Key Rules, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill loads the existing proposal context from prior refinement logs when they exist, or derives the same facts from the user's prompt, extracting the problem anchor, the dominant and any supporting contribution, reviewer concerns, and resource constraints before touching experiments.

It freezes a primary claim, an optional supporting claim, and explicit anti-claims to rule out, such as the gain only coming from more parameters, each paired with the minimum evidence that would convince a strong reviewer, capped at two primary claims, five core experimental blocks, and three baseline families by default, with three random seeds when stochastic variance matters.

When your agent uses it

  • Turning a stable method proposal into a concrete experiment plan
  • Deciding what ablations and baselines a paper actually needs
  • Defending that a contribution isn't just decoration

Example prompts

  • “Turn this method proposal into a claim-driven experiment roadmap.”
  • “What ablations do I need to rule out that the gain is just more parameters?”
  • “Plan the run order and compute budget for this paper's experiments.”

Requirements

  • Pre-approved tools (allowed-tools): Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Load the Proposal Context
  2. Freeze the Paper Claims
  3. Build the Experimental Storyline
  4. Specify Each Experiment Block
  5. Turn the Plan Into an Execution Order
  6. Write the Outputs

What it can do on your machine

Read from SKILL.md and the folder at commit a1f1449. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(*)
    • Read
    • Write
    • Edit
    • Grep
    • Glob
    • WebSearch
    • WebFetch
    • Agent

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Claim-Driven Experiment Planner loads about 2.3k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 858 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 858 words (~2,263 tokens).

name
experiment-plan
allowed-tools
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file in experiment-plan of zjYao36/Auto-Research-Refine.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit a1f1449

Used in 6 other repositories

We found 11 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 6 other GitHub owners. This page covers the copy in zjYao36/Auto-Research-Refine, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Claim-Driven Experiment Planner next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Claim-Driven Experiment Planner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claim-Driven Experiment Planner this skillzjYao36/Auto-Research-Refine1286 repos~2.3kAutomated safety check: NotesNone
Metabolic Study Planneraiming-lab/AutoResearchClaw15k—~1.9kAutomated safety check: PassMIT
Scientific BrainstormingOleafly/Oleafly2122 repos~3.5kAutomated safety check: PassMIT
Academic GrillExekiel179/psyclaw103—~2kAutomated safety check: PassMIT
Denariodavila7/claude-code-templates33k8 repos~1.5kAutomated safety check: NotesMIT
Hypothesis Formulationaiming-lab/AutoResearchClaw15k—~628Automated safety check: PassMIT

Similar skills

  • Metabolic Study Planner

    aiming-lab/AutoResearchClaw

    Turns a broad metabolic modelling topic into a concrete, paper-shaped plan with organism, model, perturbations, metrics and figures before any FBA code is written.

    15k GitHub stars~1.9k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Scientific Brainstorming

    Oleafly/Oleafly

    Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs.

    212 GitHub starsUsed in 2 repos~3.5k tokens
    Research & ScienceAuto-check passed

  • Academic Grill

    Exekiel179/psyclaw

    Stress-test an academic research question, proposal, study design, analysis plan, manuscript claim, review protocol, or AI research project through a one-question-at-a-time interview until its…

    103 GitHub stars~2k tokensUpdated yesterday
    Research & ScienceAuto-check passed

  • Denario

    davila7/claude-code-templates

    Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication.

    33k GitHub starsUsed in 8 repos~1.5k tokens
    Research & ScienceAuto-check: notes

  • Hypothesis Formulation

    aiming-lab/AutoResearchClaw

    Guides turning an observation into testable, falsifiable hypotheses with null and alternative statements, competing explanations and predictions tied to experimental design.

    15k GitHub stars~628 tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Hypothesis Generator

    liangdabiao/claude-data-analysis-ultra-main

    Generates testable research hypotheses and experimental designs.

    290 GitHub stars~903 tokensUpdated 5 mo ago
    Research & ScienceAuto-check passed

More from zjYao36/Auto-Research-Refine

  • Research Refine Pipeline

    zjYao36/Auto-Research-Refine

    Chains research-refine and experiment-plan to turn a vague research direction into a focused proposal and a claim-driven experiment roadmap.

    128 GitHub starsUsed in 5 repos~1.4k tokens
    Auto-check: notes

  • Research Refine

    zjYao36/Auto-Research-Refine

    Turns a vague research direction into a focused, problem-anchored method plan through up to five review rounds with a second model.

    128 GitHub starsUsed in 6 repos~6.9k tokens
    Auto-check: notes

Categories

Questions about Claim-Driven Experiment Planner

What does Claim-Driven Experiment Planner do?

Turns a refined research proposal into a claim-to-evidence-to-run-order roadmap instead of a sprawling benchmark wishlist. This skill loads the existing proposal context from prior refinement logs when they exist, or derives the same facts from the user's prompt, extracting the problem anchor, the dominant and any supporting contribution, reviewer concerns, and resource constraints before touching experiments.

When should I use Claim-Driven Experiment Planner?

Claim-Driven Experiment Planner fits situations like: turning a stable method proposal into a concrete experiment plan; deciding what ablations and baselines a paper actually needs; defending that a contribution isn't just decoration.

How do I install Claim-Driven Experiment Planner in Claude Code?

Run `npx skills add zjYao36/Auto-Research-Refine --skill experiment-plan -a claude-code`. Or copy the skill folder (experiment-plan in zjYao36/Auto-Research-Refine) into .claude/skills/experiment-plan in your project. Claude Code loads it when a task matches its description.

How do I install Claim-Driven Experiment Planner in Codex?

Run `npx skills add zjYao36/Auto-Research-Refine --skill experiment-plan -a codex`. Or copy the skill folder (experiment-plan in zjYao36/Auto-Research-Refine) into .agents/skills/experiment-plan in your project. Codex loads it when a task matches its description.

Can I use Claim-Driven Experiment Planner in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zjYao36/Auto-Research-Refine --skill experiment-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/experiment-plan, .gemini/skills/experiment-plan, .github/skills/experiment-plan and .opencode/skills/experiment-plan in your project.

What does Claim-Driven Experiment Planner need to run?

SKILL.md names no scripts, command-line tools or credentials: Claim-Driven Experiment Planner is instructions for the agent only. Its frontmatter pre-approves these tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent.

Does Claim-Driven Experiment Planner access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Claim-Driven Experiment Planner safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Claim-Driven Experiment Planner use?

No licence was found for Claim-Driven Experiment Planner or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Claim-Driven Experiment Planner use?

About 2.3k tokens (SKILL.md is roughly 9.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Claim-Driven Experiment Planner?

Skills that share tags, products or a category with Claim-Driven Experiment Planner: Metabolic Study Planner (aiming-lab/AutoResearchClaw, 15k stars), Scientific Brainstorming (Oleafly/Oleafly, 212 stars), Academic Grill (Exekiel179/psyclaw, 103 stars) and Denario (davila7/claude-code-templates, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claim-Driven Experiment Planner?

zjYao36 (a GitHub user) maintains it in zjYao36/Auto-Research-Refine, which has 128 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on March 16, 2026.

Source: zjYao36/Auto-Research-Refine on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.