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.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

77%Scale 1-5

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

This is a well-structured advisory skill with excellent workflow clarity (the nixos-rebuild safety ladder is outstanding) and strong progressive disclosure via a clear routing table to reference files. The main weakness is verbosity — several sections cover patterns Claude already knows (basic Nix syntax, string interpolation, list operations) and some core principles are unnecessarily explained. Trimming these known-knowledge sections would significantly improve token efficiency without losing value.

Suggestions

Remove or drastically shorten the 'Common Patterns' section (string interpolation, list/attrset operations) — Claude already knows basic Nix syntax and these consume tokens without adding novel guidance.

Condense 'Core Principles' to a bullet list of just the actionable rules (e.g., 'pin versions, commit flake.lock, avoid --impure') rather than explaining what declarative and reproducibility mean.

DimensionReasoningScore

Conciseness

The skill covers a broad domain and much of the content is useful reference material, but it includes patterns Claude already knows well (string interpolation, list operations, basic Nix syntax) and some sections like 'Core Principles' explain concepts (declarative vs imperative, reproducibility) that are general knowledge for Claude. The file is quite long (~350 lines) and could be tightened significantly.

3 / 5

Actionability

The skill provides concrete, executable code examples throughout — module definitions, flake templates, agenix usage, nixos-rebuild commands, and debugging commands are all copy-paste ready. Minor gaps exist where guidance is more advisory than executable (e.g., 'use binary caches' without showing how to configure them inline), but the routing table directs to reference files for deeper procedures.

4 / 5

Workflow Clarity

The Safety and Testing section is exemplary — it presents a clear 5-rung ladder with explicit validation at each step, failure recovery actions, and a strong warning against skipping rungs. The remote host section adds extra safety considerations. The 'confirm each rung actually succeeded before advancing' instruction and rollback procedures complete a thorough feedback loop for the most critical destructive operation (switch).

5 / 5

Progressive Disclosure

The routing table clearly maps topics to specific reference files with trigger keywords, providing excellent one-level-deep navigation. The main file serves as a genuine overview with inline essentials, while deeper procedures (Package, Secrets, Security, Deploy, Troubleshoot, etc.) are cleanly delegated to reference files. References are well-signaled and contextually placed throughout the document.

5 / 5

Total

17

/

20

Passed

Description

100%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.

This is an excellent skill description that comprehensively covers the Nix ecosystem with specific actions, extensive natural trigger terms, clear 'what' and 'when' guidance, and explicit conflict-avoidance instructions. It uses proper third-person voice throughout and balances thoroughness with clarity. The inclusion of common error types as triggers is a particularly strong touch for discoverability.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and domains: writing/debugging Nix expressions, configuring NixOS/home-manager, authoring derivations, managing flake inputs, encrypting secrets with agenix/sops-nix, hardening NixOS hosts. Also clarifies the mode of operation (advisory: explains, reviews, debugs).

5 / 5

Completeness

Explicitly answers both 'what' (expert guidance on Nix ecosystem, explains/reviews/debugs) and 'when' (detailed 'Use when' clause and 'Triggers on' clause with concrete trigger phrases). Also includes boundary guidance about deferring to repo-specific skills for host configurations.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural trigger terms including tool names (Nix, NixOS, nixpkgs, home-manager, agenix, sops-nix), commands (nixos-rebuild, nix build, nix develop), file names (flake.nix), concepts (derivation, overlay, devShell), and common error types (hash mismatches, infinite recursion, evaluation failures).

5 / 5

Distinctiveness Conflict Risk

Highly distinctive niche targeting the Nix ecosystem specifically. The explicit trigger terms are unique to Nix, and the description even includes conflict-avoidance guidance ('If the repository provides its own skill for authoring host configurations, prefer that'), minimizing overlap risk.

5 / 5

Total

20

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

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

Warning

Total

10

/

11

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.