hearth

Generating and auditing personal dev environment configs (zsh/tmux/neovim/ghostty) and automating the macOS desktop via AppleScript/JXA (Finder, Mail, Safari). Use for dotfiles or Apple Events.

Quality

88%

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

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, actionable skill body with explicit workflows, validation feedback loops, and a clean reference map. The only weakness is minor verbosity from a duplicated metadata comment block and light overlap between adjacent sections.

Dimension	Reasoning	Score
Conciseness	The body is dense, table-driven, and assumes Claude's competence with no concept-padding, but the duplicated HTML-comment capability block and some overlap across Trigger Guidance, Supported Tools, and Reference Map could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready verification commands (zsh -n, time zsh -i -c exit, zprof), concrete startup/bootstrap targets, permission values (600/644), and specific anti-patterns with quantified reasons.	5 / 5
Workflow Clarity	Defines an explicit SCAN→PLAN→CRAFT→APPLY→VERIFY sequence with a dedicated VERIFY validation phase, before/after benchmarking feedback loops with escalation thresholds, and Always/Ask-First/Never checklists for destructive operations.	5 / 5
Progressive Disclosure	Maintains a clear overview with well-signaled one-level-deep references, a per-recipe "Read First" column, and a Reference Map table stating when to consult each file, yielding easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

83%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 specific, well-targeted description that names concrete actions and tools across two distinct domains and includes an explicit trigger clause. The "Use for" guidance is somewhat terse and could enumerate more trigger synonyms to reach the top anchor.

Suggestions

Expand the "Use for" clause to list a few more concrete triggers (e.g., shell/terminal/editor setup, config auditing, macOS app automation) so the "when" matches the breadth of the "what".

Add natural synonyms or file extensions (e.g., .zshrc, config files, dotfile management) to broaden trigger-term coverage.

Confirm third-person voice is preserved throughout; the current phrasing is already correctly third person.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Generating and auditing", "automating the macOS desktop") across a comprehensive set of named tools (zsh/tmux/neovim/ghostty, AppleScript/JXA, Finder/Mail/Safari), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Clearly answers "what" and includes an explicit "Use for" trigger clause, but the "when" covers only two umbrella terms (dotfiles, Apple Events) rather than the full tool range, so it could be more specific.	4 / 5
Trigger Term Quality	Includes many natural terms users say (dotfiles, zsh, tmux, neovim, ghostty, AppleScript/JXA, Apple Events, Finder/Mail/Safari), but the "Use for" clause is terse and omits synonyms and file extensions, leaving it just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (personal dev-environment configs plus macOS AppleScript/JXA automation) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 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: simota/agent-skills
Path: .archive/hearth/SKILL.md
Commit: f425adc

Reviewed: 5 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.