ipea
- 14 skills
- 0 followers
- 10 hours ago last updated
- ▌ Capture Environment · ipeaSnapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning Dockerfile, and produces a paste-ready "Computational requirements" block. Use when user says "capture the environment", "snapshot my dependencies", "pin the versions", "make a renv.lock / requirements.txt", "make this byte-reproducible", or before releasing a replication package to openICPSR / the AEA Data Editor.
- ▌ Replication Package · ipeaAssemble a submission-ready replication package to the AEA Data and Code Availability Standard (DCAS) / openICPSR / Social Science Reproduction Platform expectations — standard replication README, dataset manifest, computational-requirements capture, a Table/Figure → script:line map, and a confidential-data deposit plan. Use when user says "build the replication package", "prepare the openICPSR deposit", "make the AEA data and code package", "DCAS compliance", "assemble the deposit for the journal", or after a paper is accepted and the journal's data editor needs the package. NOT a numeric verifier — it calls /audit-reproducibility to confirm claims reproduce before packaging.
- ▌ Humanize · ipeaRead-only audit of `.tex`, `.qmd`, or `.md` text for AI-voice tells — boilerplate transitions ("Moreover", "Furthermore", "It is important to note that"), AI-cliché lexicon ("delve", "navigate the complexities", "tapestry", "robust framework"), em-dash overuse, symmetric paragraph shapes, tricolon abuse, hedging stacking, "not only X but also Y" frames, and formulaic openers. Produces a report; does NOT rewrite. Use when user says "humanize", "does this sound like AI?", "check for AI tells", "de-AI this draft", "remove AI voice", "audit my prose for sycophancy", or before journal submission / posting a working paper.
- ▌ Proofread · ipeaRead-only proofreading pass over lecture `.tex` or `.qmd` files. Checks grammar, typos, overflow, terminology consistency, and academic writing quality; produces a report without editing. Use when user says "proofread", "check for typos", "look for grammar issues", "copy-edit this", "any writing errors?", or before a lecture release.
- ▌ Promote Memory · ipea<!-- Pattern adapted with attribution from Chris Blattman's claudeblattman v2.1
- ▌ Commit · ipeaStage, verify, commit, and push geobr changes. Use ONLY on explicit commit intent — user says "commit", "ship it", "push this", "let's commit this", or prefixes with `/commit`. Do NOT auto-invoke on vague end-of-task phrases ("we're done", "wrap up") — those require explicit confirmation first. Runs the touched-package test gate first; never force-pushes, never skips hooks, never auto-merges.
- ▌
- ▌ Review R · ipeaRead-only R code review protocol for `.R` scripts. Checks code quality, error handling, spatial-data correctness, and package conventions; produces a report without editing. Use when user says "review this R script", "check the R code", "audit the analysis code", "code review on the R", or when R code is touched as part of a release. NOT for running the code — pair with `/r-package-check` for the CRAN gate.
- ▌ New Skill · ipeaScaffold a new skill that follows this repo's conventions — interviews for purpose, trigger phrases, and tool needs, then writes `.claude/skills/<name>/SKILL.md` from the skill template with frontmatter and body that pass the integrity gates on first try. Use when user says "write a skill", "scaffold a skill", "create a new skill", "I keep doing X, make it a skill", "new slash command", or "turn this workflow into a skill". NOT for capturing a one-off session discovery — that is `/learn`.
- ▌ Checkpoint · ipeaSave a structured state snapshot the next session can resume from — active plan, decisions and why, file pointers with line numbers, open questions, next 1-3 actions, and what to deliberately forget. Use before a break, a model switch, a collaborator handoff, or when context is approaching auto-compaction. Use when the user says "checkpoint", "save state", "where am I", "compress", "distil this session", "wrap up for handoff", "before we hit auto-compact".
- ▌ Deep Audit · ipeaDeep consistency audit of the geobr repository — configuration, documentation, and the two packages. Launches parallel specialist agents to find factual errors, dead references, drift between the R and Python sides, and claims that no longer match disk. Then fixes what is genuinely broken and loops until clean. Use after broad changes, before a release, or when the user says "audit", "find inconsistencies", "check everything".
- ▌ Parity Check · ipeaCheck R↔Python API parity across geobr's two packages — which read_* functions exist on one side but not the other, and where matched functions disagree on argument names, defaults, or the metadata key they resolve. Use when the user says "check parity", "do R and Python match", "is the python side up to date", "API drift", or after changing a public reader on one side. Read-only; produces a report, never edits.
- ▌ R Package Check · ipeaRun the full R package release gate — regenerate docs, run the test suite, run R CMD check --as-cran, and triage every ERROR / WARNING / NOTE against CRAN policy before a release or submission. Use when the user says "check my R package", "R CMD check", "is this package CRAN-ready", "run devtools::check", "prepare for CRAN submission", or asks about the R side of geobr. Produces a check report + CRAN-submission checklist in `quality_reports/`.
- ▌ Py Package Check · ipeaRun the Python package release gate for geobr — sync the locked environment, run the offline and network test suites, build the distribution, and review the source against the Python conventions. Use when the user says "check the python package", "run pytest", "is the python side ready", "prepare a PyPI release", or points at python-package/. Produces a check report in quality_reports/. Mirrors .github/workflows/Python-CMD-check.yaml so local and CI cannot diverge.