Menu
Use when the user wants to set up SDRF skills dependencies, install parse_sdrf and techsdrf, or configure the environment for the first time.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Independently falsify and review a created, modified, or proposed SDRF against its specification, ontology terms, source evidence, repository files, and experimental design. Use after SDRF annotation or repair, before contribution or completion, when a review gate reports a pending artifact, or whenever an isolated reviewer must distrust the producer's self-assessment and issue a hash-bound verdict.
Create or improve an SDRF through a producer-reviewer workflow with deterministic validation, an evidence manifest, fresh-context adversarial review, repair, and mandatory re-review. Use when an SDRF must be independently verified before completion or contribution, when the user requests adversarial review, or when automated review hooks require a passing hash-bound receipt.
Use when the user wants SDRF annotation to run as an autonomous retained-improvement loop over one dataset, a manifest, or a dataset class such as all PRIDE cell line or crosslinking datasets.
Use when the user has a completed SDRF annotation for a ProteomeXchange dataset and wants to contribute it back to the community via a PR to sdrf-annotated-datasets.
Use when the user wants a comprehensive quality review of an SDRF file, a PR review of an SDRF submission, or a quality score assessment.
Use before sdrf:autoresearch when the user needs to screen or shortlist proteomics studies from PRIDE, MassIVE, ProteomeXchange accessions, or a manifest using detailed user-defined inclusion/exclusion criteria; extract study-level metadata from repository records and publications; and write an evidence-backed TSV for downstream annotation, review, or meta-analysis.
| name | sdrf:setup |
| description | Use when the user wants to set up SDRF skills dependencies, install parse_sdrf and techsdrf, or configure the environment for the first time. |
| user-invocable | true |
| argument-hint | [optional: conda | pip | check] |
You are guiding the user through installing SDRF skills dependencies. Follow these steps.
In Cursor: The user invokes this by asking "install SDRF dependencies" or similar (no /sdrf:setup slash command). Ensure environment.yml and requirements.txt exist at the workspace root; if not, suggest cloning the full sdrf-skills repo or copying those files.
Check which package managers are available (run these in the terminal or ask the user):
command -v conda && conda --version
command -v mamba && mamba --version
command -v uv && uv --version
command -v pip && pip --version
Based on what's available, output the exact commands the user should run.
# From the sdrf-skills project directory:
conda env create -f environment.yml
conda activate sdrf-skills
If using mamba (faster):
mamba env create -f environment.yml
conda activate sdrf-skills
# From the sdrf-skills project directory:
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
pip install -r requirements.txt
Note: With pip, thermorawfileparser is not available (not on PyPI). For Thermo .raw files, use conda.
uv venv .venv
source .venv/bin/activate
uv pip install -r requirements.txt
After the user runs the commands, ask them to verify:
parse_sdrf --version
techsdrf --version
If both succeed, setup is complete.
If the user cloned without submodules or wants the latest spec:
git submodule update --init --recursive
# To pull latest:
git submodule update --remote --recursive
For full SDRF annotation (PRIDE, OLS, PubMed), the user needs MCP servers configured. Tell them to check their host's MCP configuration:
For Europe PMC full text, prefer the local normalizer over raw XML inspection:
python scripts/europepmc_fulltext.py PMC_ID --format text
This keeps methods/results/discussion easier for LLMs to interpret and preserves
canonical links plus detected accessions in JSON mode.
Provide a clear summary:
When the user invokes /sdrf:setup check, run the verification step and report status: