planning-with-files
Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or…
Author, review, or diagnose Nix expressions, modules, packages, and flakes, including builds, closures, and evaluation performance.
$ npx -y skills add khaneliman/khanelinix --skill nix-toolkit --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nix-toolkitContext preview
The summary Claude sees to decide when to auto-load this skill.
Author, review, or diagnose Nix expressions, modules, packages, and flakes, including builds, closures, and evaluation performance.
name: nix-toolkit description: Author, review, or diagnose Nix expressions, modules, packages, and flakes, including builds, closures, and evaluation performance.
Use this toolkit for Nix authoring and operational work. The caller retains lifecycle ownership; a diagnosis alone does not authorize code changes.
1. Read repository contributor docs and scoped guidance. They override this toolkit's authoring defaults. 2. Select the branch that matches the requested result. Load only that reference and the detail it selects. When diagnosis leads to an authorized fix, load authoring guidance before editing. 3. Run the focused check that proves the result. Report the target, exact command, observed result, and any unverified behavior.
Authoring references own Nix construction and semantic choices. Evaluation performance owns profiling, measurement, and optimization acceptance. Review guidance owns finding thresholds and suggestions; load it only for review work.
| Requested result | Read | | --------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------- | | Create or refactor expressions, NixOS, nix-darwin or Home Manager modules, overlays, packages, or flake outputs | [Authoring](references/authoring.md) | | Review Nix changes, decide whether to request changes, or write suggestions | [Review guidance](references/review.md) | | Compare package outputs, prove a dependency removal changes nothing, or check rebuild reproducibility | [Package diffing](references/package-diffing.md) | | Diagnose a failed build | [Build debugging](references/build-debugging.md) | | Find why an option resolves to that value, conflicts, or recurses infinitely | [Option forensics](references/option-forensics.md) | | Choose or verify a module test tier | [Module testing](references/module-testing.md) | | Explain or reduce closure contents | [Closure analysis](references/closure-analysis.md) | | Trace a dependency or its owning option | [Dependency forensics](references/dependency-forensics.md) | | Update flake inputs or maintain lock files | [Flake maintenance](references/flake-maintenance.md) | | Maintain nixpkgs updates, plugins, or review publication | [Nixpkgs maintenance](references/nixpkgs-maintenance.md) | | Measure evaluation cost or validate an optimization | [Evaluation performance](references/eval-performance.md) | | Remove import-from-derivation | [IFD remediation](references/ifd-remediation.md) | | Verify activation or loaded runtime state | [Activation verification](references/activation-verification.md) |
For first-pass reports or repeatable measurements, read [Scripts](references/scripts.md) and use the matching bundled helper. Read [Operating rules](references/operating-rules.md) for operational reporting, privilege-wrapper failures, or toolkit maintenance.
Run packages directly with: Or install from the packages output. For example:
Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or…
Audit coding-agent sessions and mine cross-harness history for recurring corrections, skill-routing gaps, and harness faults. Use…
Design and audit agent instructions, skills, plugins, subagents, prompts, hooks, and provider configuration. Use for AI-tool…
Sketch interfaces, state, and module structure before code. Use for explicit design-led implementation or as a caller-owned…
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena,…
Bevy workflows for ECS, migrations, first-party UI/input/rendering/assets/shaders, plugin selection, scenes, scheduling, hot…