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

arn-code-standard

This skill should be used when the user says "standard", "standard mode", "standard implementation", "arn-code-standard", "standard change", "medium change", "standard feature", "standard fix", or wants a mid-ceremony implementation for a change that needs lightweight architectural context (spec-lite) and task-tracked execution but not the full feature-spec/plan pipeline. Bridges the gap between arn-code-swift and the full thorough pipeline. Includes spec-lite generation, structured plan, in-session execution, review-lite, and a unified change record.

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 content is highly actionable with a clear, validated multi-step workflow and well-signaled one-level references. Its weaknesses are verbosity from duplicated preference-gate boilerplate and a monolithic body where some inline orchestration logic could be factored into reference files.

Suggestions

Extract the repeated two-tier preference-gate procedure (lookup chain, gate, remember-this follow-up) into a single shared reference file and point both the sketch-preview and simplification steps at it, removing the duplicated ~80 lines.

Move the detailed Path A / Path B sketch-manifest handling into a references file, keeping only the decision summary in SKILL.md, to reduce the monolithic body length.

Dimension	Reasoning	Score
Conciseness	The body is procedurally focused without explaining basic concepts, but it is padded by near-verbatim duplication of the two-tier preference-gate logic for both sketch-preview and simplification, which could be tightened into a shared reference.	2 / 3
Actionability	It gives concrete, executable guidance throughout -- exact `mkdir` commands, named agents to dispatch, explicit JSON fields to populate, and verbatim AskUserQuestion option text -- reaching copy-paste-ready concreteness.	3 / 3
Workflow Clarity	Steps 0-8 are clearly sequenced with explicit validation checkpoints (run tests after each task, self-heal up to 3 attempts, 'Only proceed when ALL tests pass') and a review-lite verdict feedback loop for error recovery.	3 / 3
Progressive Disclosure	References are well-signaled and one level deep (e.g. '> Read .../standard-plan-template.md for the plan template', verified to exist), but the ~550-line body keeps substantial blocks like the duplicated preference gates and the Path A/B sketch-manifest logic inline rather than split out.	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 on specificity, trigger coverage, and what/when completeness, using third-person voice with explicit trigger terms. Its main weakness is the generic trigger word 'standard', which creates conflict risk against other skills.

Suggestions

Qualify the 'standard' trigger to reduce false matches, e.g. 'standard change' or 'standard implementation' rather than bare 'standard', since 'standard' alone is a common non-trigger word.

Add a short disambiguating phrase noting it is the mid-tier between arn-code-swift and the full thorough pipeline to further separate it from sibling skills.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete actions -- 'spec-lite generation, structured plan, in-session execution, review-lite, and a unified change record' -- matching the multiple-specific-actions anchor rather than vague language.	3 / 3
Completeness	It explicitly answers both what ('Includes spec-lite generation... unified change record') and when ('This skill should be used when the user says... or wants a mid-ceremony implementation'), with explicit trigger guidance.	3 / 3
Trigger Term Quality	It lists natural phrasings a user would say -- 'standard', 'standard mode', 'medium change', 'standard feature', 'standard fix' -- giving good coverage of likely trigger terms.	3 / 3
Distinctiveness Conflict Risk	The niche is defined relative to sibling tiers ('Bridges the gap between arn-code-swift and the full thorough pipeline'), but the primary trigger 'standard' is a highly generic word that risks matching unrelated contexts, so overlap risk remains.	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 (552 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-standard/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.