Name: arn-code-swift
Rating: 68.8 (1 reviews)
Author: AppsVortex

arn-code-swift

This skill should be used when the user says "swift", "arness code swift", "quick change", "small change", "just do this", "quick feature", "quick implementation", "swift fix", "implement this quickly", "add this quickly", "simple change", "just implement this", "arn-code-swift", "swift mode", "quick task", or wants a lightweight, pattern-aware implementation for a small feature or enhancement (1-8 files) without going through the full Arness pipeline. Bridges the gap between raw Claude Code and the full feature-spec/plan pipeline. Includes architectural assessment, targeted testing, and pattern compliance review.

Quality

85%

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

77%Weight 40%Scale 1-3

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

The skill body is highly actionable with a clear, checkpointed workflow and genuine one-level references. Its main weakness is conciseness: substantial verbatim duplication of the preference/simplification blocks across the simple and moderate paths, and inline detail that could be extracted to references.

Suggestions

De-duplicate the simplification preference-check, gate, and follow-up block (currently repeated verbatim in Step 4A 4b and Step 4B 5b) into a single shared reference such as references/simplification-preference.md that both paths call.

Extract the sketch-aware promotion logic and the SWIFT_REPORT/CHANGE_RECORD field schemas into reference files, leaving the body as a lean overview that points to them.

Condense the repeated two-tier preference lookup chain into one defined procedure referenced by each preference check instead of restating all three steps each time.

Dimension	Reasoning	Score
Conciseness	The body is operationally dense rather than fluffy, but at ~600 lines it duplicates large blocks verbatim (the entire simplification preference-check/gate/follow-up is repeated in both Step 4A and Step 4B, and the two-tier preference lookup chain recurs several times), so it could be tightened significantly.	2 / 3
Actionability	Provides copy-paste-ready guidance throughout: explicit bash commands (mkdir -p <plans-dir>/SWIFT_<name>), exact JSON field schemas for SWIFT_REPORT and CHANGE_RECORD, named agents to dispatch, and concrete table formats.	3 / 3
Workflow Clarity	A clearly sequenced pipeline (Step 0 through 4A/4B/4C) with explicit validation checkpoints and feedback loops ("If tests fail, self-heal... up to 3 attempts per failing test" then escalate; NEEDS FIXES -> fix -> re-run review).	3 / 3
Progressive Disclosure	References are well signaled and real (complexity-criteria.md, swift-plan-template.md, swift-review-checklist.md all exist) at one level deep, but large chunks of operational detail (sketch promotion, preference gates, report schemas) are inlined in the body rather than split into reference files.	2 / 3
	Total	10 / 12 Passed

Description

92%Weight 40%Scale 1-3

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

The description is strong: it states concrete capabilities, gives an explicit when-to-use trigger clause with many natural phrases, and uses third-person voice. Its main weakness is that several trigger terms are generic enough to risk overlap with ordinary coding tasks.

Suggestions

Tie the generic trigger phrases ("quick change", "simple change", "just do this") more tightly to the small-feature scope (e.g., "quick change to a small feature, 1-8 files") to reduce overlap with general coding requests.

Consider adding a brief disambiguating clause that contrasts swift against the full pipeline so the trigger is less likely to fire for large or architectural work.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("architectural assessment, targeted testing, and pattern compliance review") and a concrete scope bound ("small feature or enhancement (1-8 files)"), matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what it does (lightweight pattern-aware implementation) and when to use it ("should be used when the user says... or wants a lightweight... implementation for a small feature"), with an explicit Use-when style clause.	3 / 3
Trigger Term Quality	Strong coverage of natural phrases users would say ("quick change", "small change", "just do this", "quick feature", "swift fix", "simple change", "quick task") beyond just the skill name.	3 / 3
Distinctiveness Conflict Risk	The 1-8-file lightweight niche is reasonably distinct, but generic trigger phrases like "quick change", "simple change", and "just do this" could overlap with general coding requests and other skills, so it is not a clear, conflict-free niche.	2 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (617 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: AppsVortex/arness
Path: plugins/arn-code/skills/arn-code-swift/SKILL.md
Commit: 7f87870

Reviewed: 14 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.