CtrlK
BlogDocsLog inGet started
Tessl Logo

nix-expert

Expert guidance on Nix, NixOS, home-manager, flakes, and Nix packaging. Use when writing or debugging Nix expressions, configuring NixOS or home-manager, authoring derivations, managing flake inputs, encrypting secrets with agenix or sops-nix, or hardening a NixOS host. Triggers on Nix, NixOS, nixpkgs, home-manager, flake.nix, nixos-rebuild, nix build, nix develop, devShell, derivation, overlay, agenix, and on Nix errors such as hash mismatches, infinite recursion, or evaluation failures. Advisory rather than generative: it explains, reviews, and debugs. If the repository provides its own skill for authoring host configurations, prefer that for writing config.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured advisory skill body: actionable code and commands throughout, an exemplary validated rebuild ladder for the destructive 'switch' operation, and clean one-level-deep progressive disclosure via a verified reference table. Only minor conciseness trim opportunities in the principles prose.

Suggestions

Tighten the 'Core Principles' section: replace the declarative/imperative and flake-benefit prose with the code contrast alone, since Claude already knows these concepts.

Consider moving the inline 'Flake Management' output-schema skeleton to references/Flakes.md to keep SKILL.md purely an overview, matching the routing model used elsewhere.

DimensionReasoningScore

Conciseness

The body is largely lean and code-driven, but a few prose passages explain concepts Claude already knows — e.g. 'Declarative over imperative' and 'Flakes give hermetic evaluation, a standard output schema, dependency locking, and better caching' — which could be trimmed without losing clarity.

4 / 5

Actionability

Dense with concrete, copy-paste-ready commands and code — 'nix flake lock', 'nixos-rebuild dry-build --flake .#<host>', derivation/module templates, overlay patterns, and the agenix CLI — covering the common cases an operator actually runs.

5 / 5

Workflow Clarity

The 'Safety and Testing' section is a sequenced five-rung ladder with an 'On failure' feedback column, explicit 'stop at the first failure' checkpointing, remote-host guardrails, and rollback procedures — matching the top anchor for validation and error recovery on a destructive operation.

5 / 5

Progressive Disclosure

A routing table links nine task-oriented reference files that all exist on disk, each one level deep and clearly signaled with 'Read only the one you need', keeping SKILL.md an overview while details live in references.

5 / 5

Total

19

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that pairs a precise capability statement with explicit 'Use when' and 'Triggers on' guidance, comprehensive natural keywords, and clear niche boundaries. No verbosity or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the domain — 'writing or debugging Nix expressions', 'authoring derivations', 'managing flake inputs', 'encrypting secrets with agenix or sops-nix', 'hardening a NixOS host' — giving comprehensive coverage rather than vague claims.

5 / 5

Completeness

Explicitly answers both 'what' (expert guidance that 'explains, reviews, and debugs') and 'when' via a concrete 'Use when...' clause plus a 'Triggers on...' enumeration, satisfying the top anchor on both axes.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including ecosystem names, file extensions, and commands ('Nix, NixOS, nixpkgs, home-manager, flake.nix, nixos-rebuild, nix build, nix develop, devShell, derivation, overlay, agenix') plus error phrases users actually hit ('hash mismatches, infinite recursion, or evaluation failures').

5 / 5

Distinctiveness Conflict Risk

Occupies a clear Nix-ecosystem niche with distinct triggers and minimal overlap risk, and even disambiguates by deferring to a repository's own config-generation skill when present.

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (501 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
rikdc/ai-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.