timholy/claude_config

timholy/claude_config

Command

Run inside a package git-repository. The user supplies a link or issue number (referencing the origin repository) when launching; if not provided, ask.

timholy/claude_config

Command

Add Aqua.jl to a Julia package's test dependencies, run quality checks, report findings, and add to the test suite.

timholy/claude_config

Command

Run Julia test coverage analysis, identify gaps, propose new tests, and wait for user approval.

timholy/claude_config

Command

Audit and improve Julia package docs: README completeness, Documenter.jl docs/ structure, jldoctest correctness, and CI deployment.

timholy/claude_config

Command

Audit and improve Julia package docstrings: find missing/outdated docs on exported and public symbols, using Base.Docs.meta for context-efficient gap detection.

timholy/claude_config

Command

Add ExplicitImports.jl to a Julia package, analyze import usage, fix problems, and add to the test suite.

timholy/claude_config

Command

Audit a Julia package's array functions for 1-based indexing assumptions, add OffsetArrays/view tests that enforce the generic-indexing contract, and report fixes.

timholy/claude_config

Command

Update .gitignore for a Julia package to cover coverage files, manifests, and docs build artifacts.

timholy/claude_config

Command

Orchestrate full Julia package freshening: gitignore, deprecations, Aqua, ExplicitImports, struct mutability, design/API/integration reviews, generic indexing, coverage, docstrings, documentation, and formatting.

timholy/claude_config

Command

Format a Julia package with runic, commit as a standalone PR, update .git-blame-ignore-revs, and install the runic post-edit hook.

timholy/claude_config

Command

Perform a whitespace-insensitive search for mutable struct definitions in src/ or ext/.

timholy/claude_config

Command

Use this skill when the user wants to implement the next step of a planned analysis project. Triggers only on an explicit /new-analysis-implement. This skill reads the plan, implements exactly one chunk, updates the plan, and prepares a clean handoff for the next session. Only use this skill when an ANALYSISPLAN.md…

timholy/claude_config

Command

Use this skill when the user wants to start a new analysis project and has an AGENTINSTRUCTIONS or project description to work from. Triggers only on explicit command /new-analysis-plan. This skill produces a persistent plan document that drives the companion /new-analysis-implement skill.

timholy/claude_config

Command

Rewrite a package's prose (docstrings, comments, docs pages, README) so it states what the code is and does now, in plain language, at the length the reader needs.

timholy/claude_config

Command

Profile Julia code to find performance bottlenecks — CPU hot spots, runtime dispatch, GC pressure, allocations, and type instabilities — using a fully headless (no-GUI) workflow.

timholy/claude_config

Command

List the registered versions of a Julia package via Pkg's registry API (not a directory grep).

timholy/claude_config

Command

Review a Julia package's public API for consistency with modern Julia conventions and idioms.

timholy/claude_config

Command

Review a Julia package's design for conceptual coherence: scope, type hierarchy, overlaps, abstraction level, and composability.

timholy/claude_config

Command

Implement the next chunk of a planned design, API, or integration review. Reads DESIGNREVIEWPLAN.md, APIREVIEWPLAN.md, or INTEGRATIONREVIEWPLAN.md, implements one chunk (with a narrow batch exception for decide chunks), updates the plan, and prepares a clean handoff for the next session.

timholy/claude_config

Command

Review a Julia package for dependency-interface compliance, latent bugs, and user friction by reading source, tests, and docs directly.

timholy/claude_config

Command

Update [compat] for a breaking dependency upgrade: verify baseline, bump compat, update, confirm resolver selection, fix breakage.

timholy/claude_config

Command

Use this skill when the user wants a methods write-up of an analysis project — either a consolidated, living account of the whole project or a focused explanation of one stage or result. Triggers only on the explicit command /write-methods. Its primary purpose is human-agent alignment: reconstruct the chain from data…