Menü
Manage and drive forward an ongoing project, tracked in projects/ dir
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Curate, review, or repair ai-gene-review ModuleReview YAML documents under modules/, including pathway/module boundary setting, parts and variant modeling, annoton-level molecular functions, representative UniProt/PTN grounding, module deep-research provenance, validation, rendering, and project batch updates.
Work with BioReason-Pro predictions and reasoning traces for protein function. Use when: comparing BioReason outputs against curated reviews, converting web exports to YAML, reviewing reasoning trace quality, or running the SFT/RL comparison. Triggers: "bioreason", "GO-GPT predictions", "reasoning trace review", "bioreason comparison", "SFT vs RL".
Review computational protein or gene function predictions and fill PredictionReview YAML files using the COR/CNN/LSP/UNC/PLI/NPI/REP biological-validity taxonomy. Use for DeepECTF, BioReason/GO-GPT, InterPro2GO, PANTHER/IBA, CLEAN, GloEC, MAPred, ProteinInfer, or other predicted EC/GO annotations.
Use when running or wiring OpenScientist for AI Gene Review gene-function hypotheses, especially blinded comparisons against local bioinformatics analyses.
Evaluate and review GO-CAM (Gene Ontology Causal Activity Model) activities / annotons — molecular-function typing, has-input, causal relations, complexes, evidence — and check their consistency with gene annotation reviews. Use when reviewing cached GO-CAMs under gocams/, filling a GoCamReview YAML (gocams/<id>/<id>-review.yaml), or grounding a module in GO-CAM models.
Use this agent when you need to synthesize and distill the core functions of a gene from multiple information sources (textual summaries, reviewed annotations, bioinformatics analysis) and populate the `core_functions` section of a gene review YAML file. This agent should be called after completing the gene research, annotation review, and bioinformatics analysis phases of a gene review project.
| name | pm |
| description | Manage and drive forward an ongoing project, tracked in projects/ dir |
| argument-hint | [PROJECT_NAME] |
You should find either a file or a folder:
./PROJECT_NAME.md ./PROJECT_NAME/
A project doc typically will contain a list of genes, potentially prioritized. This should be in the form of a checkbox you can check off. The species for the gene (uniprot code or lowercase name like 'mouse') should be clear (if not, ask)
Review the genes in the priority order.
IMPORTANT: you MUST consult the annotation-reviewer.md subagent for this task.
If the user specifies a deep research provider(s), make sure to perform deep research using at least this provider(s), otherwise default to falcon.
E.g. just deep-research-falcon ORGANISM GENE_SYMBOL
You can edit the project doc, but try and make this incremental. After the main description have something like:
<checkboxes etc here; keep this up to date>
<get the date from date>
<todays notes, add here>
ONLY make PRs when asked.
The general procedure is:
just validate-allgh pr createif the user asks, build the static site and stats (just stats, just update-browser-data). Note it can be hard to disentangle derived
files, but you should be OK if there are no other local updates
besides the one for this project.