DRMacIver

This skill should be used when the user asks 'what should I work on', 'what's next', 'pick a task', or when needing to select between multiple available tasks. Provides guidance for prioritizing and selecting tasks.

This skill should be used when creating documentation, writing instructions, capturing reusable procedures, or when the user asks to 'create a how-to' or 'document a procedure'. Provides guidance for creating effective how-to documentation.

This skill should be used when starting complex multi-step work, when breaking down work into smaller pieces, or when needing to track progress on tasks. Provides guidance on creating fine-grained tasks with proper dependencies.

This skill should be used before planning or implementing any non-trivial request. It provides a systematic approach to understanding what the user actually wants, not just what their words literally say. Prevents building technically-correct-but-useless…

This skill should be used when the user asks to implement a new feature, add new functionality, or build something new. Provides a systematic approach to feature implementation that avoids common pitfalls like making false assumptions about APIs or tool…

This skill should be used when the user asks to work on a GitHub issue, fix a bug from an issue, or implement a feature request from GitHub. Provides guidance on properly understanding issues, defining acceptance criteria, and committing work that references…

This skill should be used when the user asks to 'get to 100% coverage', 'improve test coverage', 'cover uncovered code', 'fix coverage gaps', or mentions uncovered lines or coverage percentage. Provides strategies for achieving complete test coverage through…

This skill should be used when the user's request is ambiguous, the scope is unclear, there are multiple valid interpretations, or details need clarification before proceeding. Guides collaborative requirements gathering to understand the problem being solved.

Property-test a storage engine's crash/power-loss recovery by injecting simulated crashes through its storage-backend abstraction: a backend that separates "written" from "fsynced" bytes, plus a full write log that lets you cut the stream anywhere (including…

Build a stateful, model-based property test for a stateful Rust API (a data structure, store, engine, or VM) with hegel — drive a random sequence of operations against both the real system and a simpler reference model, and assert equivalence plus invariants…

Close the last uncovered regions of a dependency under property test by measuring per-file region coverage of the DEPENDENCY (not your crate), reading why each cold region is cold, and writing property-shaped tests — with a real oracle, not mere calls — that…

Property-test a stateful Rust API without a reference model, using hegel: metamorphic relations (two executions whose results must relate in a known way — commuting operations, do/undo identities, batch-equals-loop, reset-equals-fresh) and differential…

Decide whether a bug found in someone else's crate is actually worth reporting, and how strong a finding it is, before writing it up. Use when triaging a candidate bug, selecting which findings to file upstream, or sanity-checking a severity claim. Guards…

Write an upstream bug report or GitHub issue draft for a bug found in someone else's project. Use when drafting bug reports, issue text, or reproductions to send to a crate's or library's maintainers. Produces a short, plainly-written report led by a runnable…

Help write an interestingness test for shrinkray (test-case reducer). Use when the user needs to reduce a test case, write or fix an interestingness test, or is working with test-case reduction.

Diagnose problems with shrinkray test-case reduction — unexpected results, reduction getting stuck, slippage to wrong bugs, or interestingness test issues. Use when reduction output is surprising or reduction is not making progress.

Guide the user through setting up and running test-case reduction with shrinkray. Use when the user has a file that triggers a bug and wants to minimize it.

Write or update the RELEASE.md changelog entry that Shrink Ray requires for any change touching src/ or pyproject.toml. Use when opening or preparing a PR, adding a user-facing feature or fix, or when CI / `just check-release` reports a missing RELEASE.md.

Write correct C++ code using the CaDiCaL 3.0.0 SAT solver API. Triggers on: "cadical", "CaDiCaL", "SAT solver", "CDCL", "DIMACS", "CNF", "ExternalPropagator", "external propagator", "IPASIR", "satisfiability", "solver.add", "solver.solve", "solver.val",…

Find and fix pbtkit shrink bugs by running pbtsmith fuzzing (both crash tests and shrink quality comparison against Hypothesis). Use this skill when the user says "/debug-shrink", asks to find shrink bugs, wants to run pbtsmith, or wants to iterate on shrink…