update-package-instructions
Skill10 starsChanged 3 months agoMITView on GitHub
Update existing AI instruction documentation when an R/Bioconductor package changes
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- instructions/claude.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- adr-authorSkill
- analyze-r-packageSkill
- bioc-howtoSkill
- bioc-pkg-devSkill
- bioc-pkg-finderSkill
- bioc-pkg-reviewSkill
- build-check-bioccheckSkill
- check-bioconductor-skillsSkill
- create-package-instructionsSkill
- create-skillSkill
- document-skillSkill
- improve-code-coverageSkill
- migrate-datapkg-to-zenodoSkill
- security-audit-r-packageSkill
- update-r-newsSkill
- validate-skillSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 12
Update existing .github/instructions/ files when an R/Bioconductor package changes, preserving manual customizations.
- Very specific: line 27
Analyze Current State: Run the analyze-r-package skill to produce a current package analysis.
- Very specific: line 28
Identify Changes: Read existing .github/instructions/ .md files.
- Very specific: line 29
Determine Update Scope: Check which template variables have changed by referencing templates/package-instructions/README.md.
- Very specific: line 32
Update Systematically: Update version numbers globally.
≈ “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.
Files
update-package-instructions
Update existing .github/instructions/ files when an R/Bioconductor package changes, preserving manual customizations.
Usage
Invoke this skill when your package has changed and you want to refresh the AI instructions:
- "Update the package instructions"
- "Sync instructions with current package state"
Prerequisites
- Working directory is an R package root.
- Existing instructions exist at
.github/instructions/.
Process
- Analyze Current State: Run the
analyze-r-packageskill to produce a current package analysis. - Identify Changes: Read existing
.github/instructions/.mdfiles. Compare the current package analysis to the documented state to identify changes in metadata (version, dependencies), structure (functions, vignettes, classes), and content (data sources). - Determine Update Scope: Check which template variables have changed by referencing
templates/package-instructions/README.md. If a variable differs, its corresponding file needs an update. - Apply Update Strategy:
- Preserve Custom Content: Retain manually-added domain explanations, examples, and warnings.
- Update Systematically: Update version numbers globally. Add new functions (with
[Description needed]), remove deleted ones, and preserve custom descriptions. - Targeted Edits: Modify only the changed variables, rather than completely replacing files.
- Provide Update Summary: Report the detected changes, updated files, and any items requiring manual review.
Error Handling
- No instructions found: Direct the user to
create-package-instructions. - Conflicts: Prompt for a keep/replace/merge decision if manual changes conflict directly with template updates.
Integration
- Uses:
analyze-r-package - Works with:
create-package-instructions
Related: See create-package-instructions, analyze-r-package.
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
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.