CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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. Also use when committing or reviewing a flake.lock or `nix flake update` result, pinning or overriding a flake input, and when reviewing or deploying a NixOS config change (especially to a remote host) before it is applied. Triggers on Nix, NixOS, nixpkgs, home-manager, flake.nix, flake.lock, nix flake update, 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.

Quality

91%

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

81%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 strong advisory skill body: the deployment safety ladder with validation checkpoints and rollback is exemplary, and commands are concrete and executable throughout. The main weakness is token efficiency — two sections re-teach basic Nix syntax Claude already knows, and several sections duplicate material that already lives in dedicated reference files.

Suggestions

Delete or drastically trim the "Common Patterns" section (string interpolation, list/attrset operations) — this is standard Nix syntax Claude already knows, and none of it exists in a reference file where it would justify its tokens.

Compress "Core Principles" to one line each; the declarative-vs-imperative and modularity examples illustrate knowledge Claude already has.

Trim the inline Secrets and Debugging (hash mismatch, infinite recursion) detail to a one-paragraph summary plus the existing pointer to references/Secrets.md, references/Debug.md, and references/Troubleshoot.md, since those files carry the full treatment.

DimensionReasoningScore

Conciseness

High-value non-obvious material is present (the rebuild safety ladder, the "chmod 600 secrets.env is not a fix" treatment, the nix-collect-garbage warning), but the ~40-line "Common Patterns" section teaches basic Nix syntax Claude already knows ("message = \"Hello ${name}\"", "map (x: x * 2) list", "set1 // set2") and "Core Principles" expounds declarative-over-imperative philosophy with trivial examples. That is more than minor over-explanation (anchor 4) but the padding is concentrated in a few sections rather than pervasive (anchor 2), so 3 is the best fit.

3 / 5

Actionability

Fully executable, copy-paste-ready guidance throughout: exact commands ("nix flake update --commit-lock-file", "nix-prefetch-github owner repo --rev <commit>", "nixos-rebuild dry-activate --flake .#<host>"), complete module-option and secrets.nix code, and recovery commands ("switch --rollback", "--switch-generation N"). Examples cover the common cases, matching the 5 anchor; not 4 because the guidance includes failure paths, not just happy-path invocations.

5 / 5

Workflow Clarity

The Safety and Testing section is a textbook 5-rung workflow: a numbered ladder table with "Proves" and "On failure" columns giving explicit feedback loops ("Fix eval errors; re-run 1"), "stop at the first failure", "Confirm each rung actually succeeded before advancing — check the exit status, don't assume", remote-host safety-net commands, rollback procedures, and a security checklist. Clear sequence with explicit validation — the 5 anchor.

5 / 5

Progressive Disclosure

Excellent navigation: a Topic/Trigger/Reference routing table pointing to all 9 reference files (verified to exist, one level deep, with no nested .md references), plus clear per-section pointers ("Read that rather than working from memory", "See references/Secrets.md for the full treatment"). However, the Secrets, Security, and Debugging sections carry substantial inline detail duplicating their dedicated reference files, so the split is "a few key examples inline, bulk in separate file" (anchor 4) rather than a cleanly split overview (anchor 5).

4 / 5

Total

17

/

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.

An exemplary description: dense with concrete capabilities, an explicit and exhaustive trigger list spanning tool/file/command/error vocabulary, and explicit scope boundaries that delegate host-authoring to repo-local skills. Third-person voice throughout, with no fluff despite its length — every clause is either a capability or a trigger.

DimensionReasoningScore

Specificity

Enumerates many concrete actions — "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" plus "committing or reviewing a flake.lock", "pinning or overriding a flake input", and "reviewing or deploying a NixOS config change" — with comprehensive coverage of the skill's task domains, matching the 5 anchor. It is not 4 because there are no consequential coverage gaps: every capability in the body is named as a concrete action.

5 / 5

Completeness

Explicitly answers "what" ("Expert guidance on Nix, NixOS, home-manager, flakes, and Nix packaging... Advisory rather than generative: it explains, reviews, and debugs") and "when" via two "Use when..." clauses plus an enumerated "Triggers on..." list — clearly matching the 5 anchor (both what and when with concrete trigger phrases). It is not 4 because the "when" is not merely present but exhaustively enumerated.

5 / 5

Trigger Term Quality

"Triggers on Nix, NixOS, nixpkgs, home-manager, flake.nix, flake.lock, nix flake update, nixos-rebuild, nix build, nix develop, devShell, derivation, overlay, agenix" plus error phrases ("hash mismatches, infinite recursion, or evaluation failures") — covering tool names, file names, commands, and failure messages users would naturally paste. Only marginal omissions (e.g. `nix shell`) exist, all subsumed by the umbrella term "Nix", so it fits the comprehensive 5 anchor rather than 4.

5 / 5

Distinctiveness Conflict Risk

A clear niche (the Nix ecosystem) with distinct triggers (flake.lock, nixos-rebuild, agenix), and it actively reduces conflict risk: "If the repository provides its own skill for authoring host configurations, prefer that for writing config." Minimal overlap with other skills fits the 5 anchor.

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.

Validation — 15 / 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

Path

plugins/nix-skills/skills/nix-expert/SKILL.md

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.