Name: flox-builds
Rating: 68 (1 reviews)
Author: flox

flox-builds

Building and packaging applications with Flox. Use for manifest builds, Nix expression builds, sandbox modes, multi-stage builds, and packaging assets.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%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 highly actionable, well-organized guide rich in executable examples, but it is a long monolithic file with no progressive disclosure to separate files and some internal repetition that inflates the token budget.

Suggestions

Deduplicate repeated content — the manifest build syntax, the 'Build hooks don't run' caveat, and the core 'flox build' command list each appear more than once; consolidate to one canonical instance.

Split the large language-specific examples and Nix expression patterns into reference files under ./references/ and link to them one level deep, so SKILL.md stays an overview.

Add explicit validation checkpoints (e.g. 'verify ./result-<name> exists and runs before publishing') to the build→publish workflow rather than relying on informal debugging steps.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete examples and little basic-concept padding, but contains real redundancy: manifest build syntax, 'Build hooks don't run', and 'flox build' command listings each appear multiple times, and the deprecated notice plus related-skills add tokens that don't aid execution.	3 / 5
Actionability	Numerous copy-paste-ready TOML, Bash, and Nix snippets cover the common cases (Python/Node/Rust apps, vendored Go, runtime trimming, asset packaging), giving fully executable guidance.	5 / 5
Workflow Clarity	The dev→publish→runtime workflow and debugging steps are clearly sequenced with informal verification (flox build -v, ls result, ./result/bin), but there are no explicit validate-then-proceed checkpoints; not a destructive/batch cap case.	4 / 5
Progressive Disclosure	No bundle files exist and the ~470-line SKILL.md is a single monolithic document; though well-sectioned, content that could live in separate files (language examples, Nix patterns) is inlined and there are no one-level-deep references.	3 / 5
	Total	15 / 20 Passed

Description

92%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 with an explicit 'Use for' trigger clause and a comprehensive list of concrete build/packaging capabilities. Minor room for additional synonyms, but it clearly answers what and when.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Building and packaging applications', 'manifest builds, Nix expression builds, sandbox modes, multi-stage builds, and packaging assets' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers 'what' (building and packaging applications with Flox) and 'when' (Use for...) with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('manifest builds', 'Nix expression builds', 'sandbox modes', 'multi-stage builds', 'packaging assets') but lacks synonyms or file/manifest extensions that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Clear Flox-specific niche with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: flox/flox-agentic
Path: flox-plugin/skills/flox-builds/SKILL.md
Commit: aaa5f1a

Reviewed: 15 days ago

Table of Contents

Discovery Implementation Validation

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.