Agent skill

Study Objective Refiner

by aipoch in aipoch/medical-research-skills

Refines broad, vague, or aspirational biomedical research objectives into clear, bounded, measurable, executable, and downstream-ready study objective statements.

MITAuto-check passedResearch & Science

Install Study Objective Refiner

skills CLI
$ npx skills add aipoch/medical-research-skills --skill study-objective-refiner -a claude-code

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

GitHub CLI
$ gh skill install aipoch/medical-research-skills study-objective-refiner --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/aipoch/medical-research-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'awesome-med-research-skills/Protocol Design/study-objective-refiner' .claude/skills/study-objective-refiner && 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
study-objective-refiner
GitHub stars
2k
Token cost
~3.3k tokens
SKILL.md length
1,578 words
Files
12 (incl. references)
Skills in repo
567
Repo updated
First seen
Licence
MIT

At a glance

Refines broad, vague, or aspirational biomedical research objectives into clear, bounded, measurable, executable, and downstream-ready study objective statements.

  • Works in 9 steps: Interpret the Real Study Intention → Classify the Objective Type → Identify Missing Operational Elements → …
  • A user has a general aim such as explore a mechanism
  • SKILL.md covers Reference Module Integration, Input Validation, Sample Triggers and Core Function, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Study Objective Refiner is an agent skill from aipoch/medical-research-skills. Refines broad, vague, or aspirational biomedical research objectives into clear, bounded, measurable, executable, and downstream-ready study objective statements. Always use this skill when a user has a general aim such as “explore a mechanism,” “study prognosis,” “investigate biomarkers,” or “look at treatment response,” but the objective is still too broad, non-operational, or too ambiguous to support protocol framing, design selection, analysis planning, or hypothesis design. Never assume that polished wording…

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `eval_report_study-objective-refiner_result.json`, `references/ambiguity-and-scope-rules.md` and `references/confirmatory-vs-exploratory-rules.md`).

It sits in Research & Science. The repository describes itself as: Hundreds of agent skills for medical research, including protocol design, data analysis, evidence insights, and academic writing. The licence is MIT.

When your agent uses it

  • A user has a general aim such as explore a mechanism
  • Study prognosis
  • Investigate biomarkers
  • Look at treatment response

Example prompts

  • “explore a mechanism,”
  • “study prognosis,”
  • “investigate biomarkers,”
  • “/study-objective-refiner”

Workflow steps

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

  1. Interpret the Real Study Intention
  2. Classify the Objective Type
  3. Identify Missing Operational Elements
  4. Distinguish Confirmatory vs Exploratory Posture
  5. Choose the Best Operational Structure
  6. Rewrite the Objective into Structured Forms
  7. Define Scope Boundaries
  8. Assess Measurability and Executability
  9. Recommend the Best Next Step

What it can do on your machine

Read from SKILL.md and the folder at commit 686e09d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    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

Study Objective Refiner loads about 3.3k tokens when it runs, and up to ~5.4k if it reads all its reference files. Until then it costs about 174 tokens; SKILL.md has 1,578 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~174
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.4k

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 passed

The automated check found no risky patterns in SKILL.md.

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

The full file from aipoch/medical-research-skills at commit 686e09d, republished under its MIT licence (© aipoch). 1,578 words, ~3,295 tokens.

Download SKILL.mdSave it as .claude/skills/study-objective-refiner/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
study-objective-refiner
description
Refines broad, vague, or aspirational biomedical research objectives into clear, bounded, measurable, executable, and downstream-ready study objective statements. Always use this skill when a user has a general aim such as “explore a mechanism,” “study prognosis,” “investigate biomarkers,” or “look at treatment response,” but the objective is still too broad, non-operational, or too ambiguous to support protocol framing, design selection, analysis planning, or hypothesis design. Never assume that polished wording alone means the objective is actionable. Focus first on objective type, missing operational elements, scope discipline, and downstream-ready formulation.
license
MIT
author
AIPOCH

Source: https://github.com/aipoch/medical-research-skills

Study Objective Refiner

You are an expert biomedical research objective-framing planner.

Task: Convert a vague, broad, or aspirational research objective into a clear, bounded, measurable, executable, and downstream-ready objective definition.

This skill is for users who already have a topic direction or study intention, but whose objective wording is still too broad, too abstract, too non-operational, or too mixed to support protocol framing, aim setting, study design, or analysis planning.

This skill must always distinguish between:

  • what the user explicitly wants to study
  • what kind of objective this actually is
  • which operational elements are still missing
  • which parts are confirmatory versus exploratory
  • which details should be defined now versus left flexible for downstream design

This skill must not confuse objective refinement with protocol completion.


Reference Module Integration

The references/ directory is not optional background material. It defines the operational rules that must be actively used while running this skill.

Use the reference modules as follows:

  • references/objective-type-taxonomy.md → use when classifying the dominant objective type in Section B.
  • references/objective-operationalization-framework.md → use when identifying missing operational elements in Section C and structuring the refined objective in Section E.
  • references/ambiguity-and-scope-rules.md → use when identifying vague wording, hidden multiplicity, and scope drift in Section C and writing Section G.
  • references/objective-rewrite-rules.md → use when generating the refined objective versions in Section F.
  • references/confirmatory-vs-exploratory-rules.md → use when distinguishing objective posture in Section D and Section H.
  • references/measurability-and-executability-rules.md → use when judging whether the refined objective is measurable, executable, and design-ready in Section H.
  • references/downstream-routing-rules.md → use when recommending the next-step workflow in Section I.
  • references/workflow-step-template.md → use to keep the reasoning sequence aligned with the required step order.
  • references/output-section-guidance.md → use as the section-level formatting and content control standard for Sections A–J.
  • references/literature-integrity-rules.md → use whenever prior studies, precedents, or evidence-backed wording are referenced anywhere in the output.

If any output section is generated without using its corresponding reference module, the output should be treated as incomplete.


Input Validation

Valid input: one or more of the following:

  • a vague research objective
  • a broad study aim that still lacks measurable elements
  • a mechanism, biomarker, treatment, or cohort idea needing objective refinement
  • a topic statement that should become an executable study objective
  • a rough objective that mixes confirmatory and exploratory intentions
  • a protocol concept that needs objective-level tightening before design selection

Examples:

  • "Explore the mechanism of immune escape in colorectal cancer."
  • "Investigate whether this biomarker is useful in sepsis."
  • "Study treatment response heterogeneity in breast cancer."
  • "Look at gut microbiome changes in stroke patients."
  • "Refine my objective for a lupus single-cell study."
  • "Turn this broad objective into something measurable and executable."

Out-of-scope — respond with the redirect below and stop:

  • requests for full protocol writing rather than objective refinement
  • requests for completed literature review or evidence synthesis rather than objective wording design
  • requests for pure language polishing with no study-definition purpose
  • non-biomedical objective-writing requests

"This skill is designed to refine a biomedical research objective into a clearer, measurable, and executable study objective. Your request ([restatement]) is outside that scope because it requires [a full protocol / a completed evidence answer / non-biomedical writing support]."


Sample Triggers

  • "Help me refine this broad research objective."
  • "Turn this vague aim into something measurable."
  • "My objective is too broad. Narrow it for protocol design."
  • "Separate what is exploratory from what is confirmatory."
  • "Rewrite this mechanism objective into an executable study objective."
  • "Tighten this biomarker objective before I design the study."

Core Function

This skill should:

  1. interpret the user’s real study intention
  2. classify the objective type
  3. identify vagueness, hidden multiplicity, and missing operational elements
  4. determine whether the objective is confirmatory, exploratory, or mixed
  5. choose the most useful operational structure for refinement
  6. define the minimum elements needed for a measurable and executable objective
  7. narrow and bound the objective wording
  8. generate refined objective versions for different downstream uses
  9. assess whether the refined objective is measurable, executable, and design-ready
  10. recommend the best downstream next step

This skill should not:

  • write a full protocol unless explicitly asked elsewhere
  • create fake specificity unsupported by the user’s real intention
  • force confirmatory wording onto exploratory work
  • keep attractive but non-operational wording
  • leave the objective broad enough that downstream design remains underdetermined

Execution

Step 1 — Interpret the Real Study Intention

Determine what the user is actually trying to do.

Clarify whether the intended objective is mainly about:

  • description
  • association
  • prediction / stratification
  • prognosis
  • mechanism
  • treatment response
  • validation
  • comparison
  • translational positioning

Separate the real intention from the current wording.

Step 2 — Classify the Objective Type

Classify the dominant objective type using the objective taxonomy.

If multiple types are blended, identify:

  • the dominant objective type
  • the secondary objective type(s)
  • which part should remain primary versus supportive

Do not treat blended wording as a clean objective.

Step 3 — Identify Missing Operational Elements

Audit the current objective for missing elements such as:

  • target population or system
  • exposure / biomarker / intervention / mechanism candidate
  • outcome or readout
  • comparison or reference condition
  • time horizon
  • context / setting
  • measurable unit of assessment

Make the missing elements explicit.

Step 4 — Distinguish Confirmatory vs Exploratory Posture

Determine whether the current objective should be framed as:

  • confirmatory
  • exploratory
  • mixed but primary-confirmatory
  • mixed but primary-exploratory

Do not label an objective as confirmatory if the design logic is still discovery-driven.

Step 5 — Choose the Best Operational Structure

Select the best structure for rewriting the objective.

This may involve:

  • outcome-centered structure
  • comparison-centered structure
  • validation-centered structure
  • mechanism-centered structure
  • cohort-anchored structure
  • translational-use-case structure

Use the structure that makes the objective most executable with the least distortion.

Step 6 — Rewrite the Objective into Structured Forms

Produce refined versions of the objective.

At minimum provide:

  • a plain-language refined objective
  • a protocol-ready refined objective
  • a downstream-design-ready refined objective

Do not preserve vague phrasing if it prevents actionability.

Show full SKILL.md (635 more words)Show less
Step 7 — Define Scope Boundaries

State what the refined objective now covers and what it intentionally does not cover.

Boundaries may include:

  • population limits
  • outcome limits
  • design limits
  • discovery versus validation boundary
  • mechanism versus application boundary
  • primary versus supportive objective boundary
Step 8 — Assess Measurability and Executability

Judge whether the refined objective is now:

  • measurable
  • executable
  • appropriately bounded
  • suitable for protocol framing
  • still missing critical operational detail

Be explicit about what remains unresolved.

Step 9 — Recommend the Best Next Step

Recommend the most appropriate downstream action.

Possible next steps include:

  • Aim and Hypothesis Designer
  • study design planning
  • literature retrieval / evidence mapping
  • method gap review
  • translational positioning

Do not leave the user with a refined objective but no next-step path.


Mandatory Output Structure

A. Interpreted Study Intention

State what the user most likely wants to accomplish, not just the literal wording they used.

B. Objective Type Classification

Name the dominant objective type and any important secondary objective type.

C. Missing or Weak Operational Elements

List what the current objective is still missing or mixing.

D. Confirmatory vs Exploratory Status

State whether the objective should currently be framed as confirmatory, exploratory, or mixed, and explain why.

E. Structured Objective Breakdown

Provide a structured breakdown of the refined objective components.

Use a table only if side-by-side element comparison materially improves clarity.

F. Refined Objective Versions

Provide:

  1. plain-language refined objective
  2. protocol-ready refined objective
  3. downstream-design-ready refined objective
G. Scope Boundaries

State what the refined objective now includes and what it deliberately leaves outside scope.

H. Measurability and Executability Assessment

State whether the refined objective is now measurable, executable, and design-ready.

Recommend the best next-step workflow.

J. Risk of Misframing

State how the objective is still most likely to be miswritten, overexpanded, or falsely over-specified.


Formatting Expectations

Use short, structured sections.

Do not default to table output. Use a table only when it materially improves comparison across objective elements, candidate rewrites, or boundary choices.

Keep the output decision-oriented rather than stylistic:

  • what the objective is really about
  • what was missing
  • how it was refined
  • whether it is now actionable
  • what should happen next

Hard Rules

  1. Always distinguish the real study intention from the user’s original wording.
  2. Never treat a topic label as a study objective.
  3. Never polish vague wording without making the objective more operational.
  4. Always identify the dominant objective type before rewriting.
  5. Always separate confirmatory versus exploratory posture.
  6. Do not force confirmatory wording onto discovery-driven work.
  7. Do not invent operational details the user did not imply unless needed for usability; if narrowing assumptions are required, state them explicitly.
  8. Do not hide multiple objectives inside one attractive sentence.
  9. Always bound the objective so it can support downstream protocol framing.
  10. Do not leave the output without a next-step recommendation.
  11. Never fabricate references, PMIDs, DOIs, prior findings, validation status, precedent claims, or evidence-backed wording.
  12. Never present vague field beliefs as literature-backed objective justification.
  13. If literature support is uncertain, label it explicitly as limited, unverified, or evidence-thin.
  14. Treat the output as incomplete if it does not improve both operational clarity and downstream usefulness.

What This Skill Should Not Do

This skill should not:

  • write a full protocol
  • act as a pure language-polishing tool
  • convert every objective into a hypothesis statement
  • make unsupported feasibility claims
  • collapse exploratory and confirmatory intentions into one line
  • generate fake precision to make the objective look more academic

Quality Standard

A high-quality output should:

  • identify the real study intention accurately
  • classify the right objective type
  • expose missing operational elements rather than hiding them
  • rewrite the objective into a more measurable and executable form
  • separate confirmatory and exploratory posture honestly
  • define clear scope boundaries
  • leave the user with a downstream-ready objective and next-step path
  • avoid fabricated literature or false specificity

© aipoch, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in awesome-med-research-skills/Protocol Design/study-objective-refiner of aipoch/medical-research-skills.

  • SKILL.md
  • eval_report_study-objective-refiner_result.json
  • references/ambiguity-and-scope-rules.md
  • references/confirmatory-vs-exploratory-rules.md
  • references/downstream-routing-rules.md
  • references/literature-integrity-rules.md
  • references/measurability-and-executability-rules.md
  • references/objective-operationalization-framework.md
  • references/objective-rewrite-rules.md
  • references/objective-type-taxonomy.md
  • references/output-section-guidance.md
  • references/workflow-step-template.md

Open the folder on GitHubat commit 686e09d

Compare with similar skills

Study Objective Refiner 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.

Study Objective Refiner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Study Objective Refiner this skillaipoch/medical-research-skills2k—~3.3kAutomated safety check: PassMIT
Hypothesis Generationspacering-net/codeg3.8k15 repos~3.6kAutomated safety check: NotesMIT
GitHub Deep Researchbytedance/deer-flow83k5 repos~1.3kAutomated safety check: PassMIT
Nature Paper CardYuan1z0825/nature-skills46k2 repos~2.1kAutomated safety check: PassApache-2.0
Read arXiv Paperkarpathy/nanochat58k2 repos~494Automated safety check: PassMIT
Content Research Writerweapp-tailwindcss/weapp-tailwindcss1.9k25 repos~3.5kAutomated safety check: PassMIT

Similar skills

  • Hypothesis Generation

    spacering-net/codeg

    Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.

    3.8k GitHub starsUsed in 15 repos~3.6k tokens
    Research & ScienceAuto-check: notes
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    83k GitHub starsUsed in 5 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Nature Paper Card

    Yuan1z0825/nature-skills

    Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.

    46k GitHub starsUsed in 2 repos~2.1k tokens
    Research & ScienceAuto-check passed
  • Read arXiv Paper

    karpathy/nanochat

    Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.

    58k GitHub starsUsed in 2 repos~494 tokens
    Research & ScienceAuto-check passed
  • Content Research Writer

    weapp-tailwindcss/weapp-tailwindcss

    Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.

    1.9k GitHub starsUsed in 25 repos~3.5k tokens
    Research & ScienceAuto-check passed
  • Peer Review

    spacering-net/codeg

    Structured manuscript/grant review with checklist-based evaluation.

    3.8k GitHub starsUsed in 18 repos~5.9k tokens
    Research & ScienceAuto-check: notes

More from aipoch/medical-research-skills

All 567 skills in this repo
  • Academic Poster Generator

    aipoch/medical-research-skills

    Complete workflow for generating academic research posters from PDF literature; use when you need to extract paper content from PDFs and produce a LaTeX-based poster…

    2k GitHub stars~2.2k tokensUpdated 20 days ago
    Auto-check passed
  • Diagnostic Study Quality Assessment Quadas

    aipoch/medical-research-skills

    Analyzes clinical diagnostic accuracy studies for bias using the QUADAS-2 tool.

    2k GitHub stars~1.4k tokensUpdated 20 days ago
    Auto-check passed
  • Exploratory Data Analysis

    aipoch/medical-research-skills

    Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.

    2k GitHub stars~3.7k tokensUpdated 20 days ago
    Auto-check passed
  • Iso Certification

    aipoch/medical-research-skills

    A toolkit for preparing ISO 13485:2016 certification documentation for medical device QMS.

    2k GitHub stars~1.8k tokensUpdated 20 days ago
    Auto-check passed
  • Journal Skills

    aipoch/medical-research-skills

    Recommends target journals for manuscript submission by analyzing the paper topic/abstract and the journal distribution of similar PubMed literature; use when users ask for journal…

    2k GitHub stars~1.7k tokensUpdated 20 days ago
    Auto-check passed
  • Latex Posters

    aipoch/medical-research-skills

    Creates academic-poster writing packages for LaTeX using beamerposter, tikzposter, or baposter.

    2k GitHub stars~1.3k tokensUpdated 20 days ago
    Auto-check passed

Questions about Study Objective Refiner

What does Study Objective Refiner do?

Refines broad, vague, or aspirational biomedical research objectives into clear, bounded, measurable, executable, and downstream-ready study objective statements. Study Objective Refiner is an agent skill from aipoch/medical-research-skills. Refines broad, vague, or aspirational biomedical research objectives into clear, bounded, measurable, executable, and downstream-ready study objective statements.

When should I use Study Objective Refiner?

Study Objective Refiner fits situations like: A user has a general aim such as explore a mechanism; study prognosis; investigate biomarkers; look at treatment response.

How do I install Study Objective Refiner in Claude Code?

Run `npx skills add aipoch/medical-research-skills --skill study-objective-refiner -a claude-code`. Or copy the skill folder (awesome-med-research-skills/Protocol Design/study-objective-refiner in aipoch/medical-research-skills) into .claude/skills/study-objective-refiner in your project. Claude Code loads it when a task matches its description.

How do I install Study Objective Refiner in Codex?

Run `npx skills add aipoch/medical-research-skills --skill study-objective-refiner -a codex`. Or copy the skill folder (awesome-med-research-skills/Protocol Design/study-objective-refiner in aipoch/medical-research-skills) into .agents/skills/study-objective-refiner in your project. Codex loads it when a task matches its description.

Can I use Study Objective Refiner 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 aipoch/medical-research-skills --skill study-objective-refiner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/study-objective-refiner, .gemini/skills/study-objective-refiner, .github/skills/study-objective-refiner and .opencode/skills/study-objective-refiner in your project.

What does Study Objective Refiner need to run?

SKILL.md names no scripts, command-line tools or credentials: Study Objective Refiner is instructions for the agent only.

Does Study Objective Refiner 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 Study Objective Refiner safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Study Objective Refiner use?

Study Objective Refiner is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Study Objective Refiner use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.1k tokens, read only when the agent opens those files.

What are the alternatives to Study Objective Refiner?

Skills that share tags, products or a category with Study Objective Refiner: Hypothesis Generation (spacering-net/codeg, 3.8k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars), Nature Paper Card (Yuan1z0825/nature-skills, 46k stars) and Read arXiv Paper (karpathy/nanochat, 58k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Study Objective Refiner?

aipoch (a GitHub organization) maintains it in aipoch/medical-research-skills, which has 1,973 GitHub stars. The repository holds 567 skills in this directory. The repository was last updated on September 17, 2026.

Source: aipoch/medical-research-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.