agentleFS
Sign inStart free
BioconductorBioconductor/ai-agent-skills/skills/create-package-instructions/SKILL.md

create-package-instructions

Skill10 starsChanged 3 months agoMITView on GitHub

Create complete AI instruction documentation for an R/Bioconductor package in .github/instructions/

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 1 is distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create complete AI instruction documentation for an R/Bioconductor package in .github/instructions/.

    line 12
  2. Very specific:

    Create Directory: Ensure .github/instructions/ exists.

    line 34
  3. Very specific:

    Ensure .github/instructions/ is NOT ignored in .gitignore.

    line 37
  4. Very specific:

    Add ^\.github/instructions$ to .Rbuildignore.

    line 38
  5. Very specific:

    Instructions exist: Ask user to overwrite or use update-package-instructions.

    line 44
  6. Distinctive:

    Template not found: Verify templates directory exists.

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

create-package-instructions

Create complete AI instruction documentation for an R/Bioconductor package in .github/instructions/.

Usage

Invoke this skill when you want to generate AI-friendly documentation for an R package:

  • "Create instructions for this package"
  • "Create .github/instructions for this R package"

Prerequisites

  • Working directory is an R package root (contains DESCRIPTION file).

Process

  1. Run Package Analysis: Invoke analyze-r-package to understand the package structure.
  2. Determine Required Instruction Files: Based on the analysis, select the appropriate templates from templates/package-instructions/:
    • 00-overview.md.template (Always)
    • 10-data-access.md.template (If Type: Remote or Hybrid)
    • 20-development.md.template (Always)
    • 30-testing-and-docs.md.template (Always)
    • 40-vignettes.md.template (If Vignettes > 0)
    • INDEX.md.template (Always)
  3. Create Directory: Ensure .github/instructions/ exists.
  4. Create Files from Templates: Perform variable substitution for each {{VARIABLE_NAME}} using the analysis output (refer to templates/package-instructions/README.md for mappings). Write the results to .github/instructions/.
  5. Update Package Config:
    • Ensure .github/instructions/ is NOT ignored in .gitignore.
    • Add ^\.github/instructions$ to .Rbuildignore.
  6. Provide Summary: Inform the user about the files created, documented functions, and next steps.

Error Handling

  • Analysis fails: Propagate error, provide guidance.
  • Instructions exist: Ask user to overwrite or use update-package-instructions.
  • Template not found: Verify templates directory exists.

Integration

  • Uses: analyze-r-package
  • Works with: update-package-instructions

Related: See analyze-r-package, update-package-instructions.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free