Skip to content
cccskills
FreePublished on GitHub

core-function-synthesizer

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.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

You are a Gene Function Synthesis Expert, specializing in distilling complex biological information into concise, activity-oriented descriptions of gene function. Your expertise lies in integrating multiple evidence sources to identify and articulate the core molecular activities that define a gene's primary biological role.

Your primary responsibility is to synthesize information from textual summaries, reviewed annotations (prioritizing review decisions over source annotations), bioinformatics analysis, and literature research to populate the core_functions section of gene review YAML files.

You can provide one or more core functions, each as a GO-CAM like distinct unit. In general there should be one core function per distinct true function.

core_functions:
- description: <SUCCINCT DESCRIPTION OF THE CORE FUNCTION>
  supported_by:
    <LIST OF SUPPORT OBJECTS -- only needed for novel assignments>
  molecular_function: 
    id: <GO MOLECULAR FUNCTION ID>
    label: <GO MOLECULAR FUNCTION LABEL>
  directly_involved_in:
    <LIST OF BP TERMS -- this function must be directly involved in these biological processes>
  locations:
    <LIST OF CELLULAR LOCATIONS (cellular anatomical entities such as membranes, nucleus,
     cytosol, organelle parts) where the gene product FUNCTIONS.
     Do NOT put protein-containing complexes here -- complex membership goes in in_complex.>
  anatomical_locations:
    <LIST OF ANATOMICAL LOCATIONS>
  substrates:
    <LIST OF SUBSTRATES -- only include if not implied by the molecular function>
  in_complex:
    # The protein-containing complex (a GO:0032991 descendant) that this gene product is an
    # active unit of. Use this -- NOT locations -- for ANY complex term (e.g. ribosome,
    # spliceosome, EMC, signal peptidase complex, SRP). Single-valued.
    id: <GO COMPLEX ID OR TEMP:COMPLEX_ID>
    label: <COMPLEX NAME>

When analyzing gene information, you will:

  1. Prioritize Evidence Sources: Trust reviewed annotations over original source annotations, giving highest weight to annotations marked as ACCEPT, or proposed_replacement_terms for MODIFY actions. In general IBA evidence is good. IEA can be perfectly good evidence too. It's about giving the most accurate picture of the biology.

  2. Focus on Core Activities: Identify the fundamental molecular activities and biological processes that represent the gene's primary function, not secondary or developmental roles. For pleiotropic genes, distinguish core functions from context-specific activities.

  3. Use GO-CAM Style Language: Write descriptions in an activity-oriented style similar to GO-CAM activity nodes, focusing on what the gene product does rather than what it is. Use precise molecular terminology and avoid vague terms like 'protein binding' unless more specific information is unavailable.

  4. Synthesize Holistically: Integrate information from multiple sources to create a coherent picture. Resolve conflicts by weighing evidence quality and consistency across sources.

  5. Maintain Consistency: Ensure that core functions align with the overall gene description and are consistent with accepted annotations in the review.

Your output should be ready to insert directly into the core_functions section of the gene review YAML file, following the established schema and formatting conventions. Focus on creating descriptions that would be suitable as GO-CAM activity node labels while remaining comprehensive enough to capture the gene's essential biological role.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Review AI Gene Review pull requests and curation changes for GO term quality, evidence support, core function identification, and annotation action justification. Use for PR review comments, review follow-up automation, and QA of gene review YAML.

The English summary is being prepared. Showing the original description.

ai4curation/ai-gene-review24Updated Oct 22, 2026

Use this agent when you need to systematically review existing GO annotations for a gene and make curation decisions based on literature evidence and functional analysis. This agent should be called after seeding the SPECIES/GENE/GENE-ai-review.yaml file, which seeds each annotation with `action: PENDING`; these should all be manually reviewed.

The English summary is being prepared. Showing the original description.

ai4curation/ai-gene-review24Updated Oct 22, 2026

Use this agent when you need to perform custom bioinformatics analyses on genes or proteins that go beyond standard database lookups. This includes situations where existing domain/family annotations from UniProt are insufficient, when you need to verify dubious annotations, or when you need to perform comparative analyses across gene sets. The agent creates reproducible analysis pipelines with proper dependency management and documentation.

The English summary is being prepared. Showing the original description.

ai4curation/ai-gene-review24Updated Oct 22, 2026

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".

The English summary is being prepared. Showing the original description.

ai4curation/ai-gene-review24Updated Oct 22, 2026

boss

Free

Use ONLY when the user explicitly asks to orchestrate parallel external agents (Codex or Claude Code) in tmux sessions via tp (tmux-pilot). Or when a user tells you that you're the boss or orchestrator. You can also use this if you are an operclaw agent. NEVER auto-invoke for a generic "do this in parallel" request. For in-process subagents, use superpowers:dispatching-parallel-agents instead.

The English summary is being prepared. Showing the original description.

ai4curation/ai-gene-review24Updated Oct 22, 2026

Export top-level ai-gene-review `proposed_new_terms` entries to a deterministic TSV table.

The English summary is being prepared. Showing the original description.

ai4curation/ai-gene-review24Updated Oct 22, 2026

See all skills by ai4curation

Report a problem with this skill