Add an agent skill for using the package (closes #69) - #91
Merged
Conversation
Adds skills/lagotrials/SKILL.md, an agent skill in the AWS agent-toolkit format (name/description/version frontmatter plus a structured body) that teaches AI coding agents how to use LAGOtrials: the core lago_optimization() workflow, goal modes, cost-function format and visualize_cost(), outcome-model options, confidence sets, the critical link/NA/rank-deficiency behaviors, troubleshooting, and the result object. skills/README.md explains the format and how to install a skill into an agent (e.g. .claude/skills/). skills/ is excluded from the R build via .Rbuildignore, so nothing ships to CRAN. Every claim was verified against the package source: the recommended intervention's interval is documented as est_outcome_ci (not rec_int_ci, which is only a get_confidence_set() field), and the all-NA up-front refusal is scoped to intervention components and additional covariates.
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this changes
Adds an agent skill for using the package, resolving #69 (modeled on AWS's
agent-toolkit skills).
skills/lagotrials/SKILL.md— an agent skill in the AWS format(
name/description/versionfrontmatter + a structured body) that teachesAI coding agents how to use LAGOtrials: the core
lago_optimization()workflow, goal modes (outcome/power/both), the
cost_list_of_vectorsformatand
visualize_cost(), outcome-model options (family/link, fixed effects,covariates, interactions), confidence sets, the critical link/NA/rank-deficiency
behaviors, troubleshooting, and the result object.
skills/README.md— explains the format and how to install a skill into anagent (e.g.
.claude/skills/).skills/is excluded from the R build via.Rbuildignore, so nothing shipsto CRAN.
Closes #69.
Related issue
Closes #69
Checklist
tests/testthat/— n/a, documentation/skill only, no package codedevtools::document()— n/a, no roxygen changesdevtools::check()passes locally — n/a forskills/(build-ignored); confirmed excluded from the tarballNEWS.mdupdated — n/a, not a shipped-package change (agent tooling, build-ignored)