Name: arn-planning
Rating: 72 (1 reviews)
Author: AppsVortex

arn-planning

This skill should be used when the user says "planning", "arness planning", "plan a feature", "start planning", "I want to build", "new feature", "plan something", "what should I build", "pick an issue", "plan a bug fix", "I have an idea", "spec and plan", "plan from scratch", "plan this", "feature planning", "bug planning", "plan this issue", "arn-planning", or wants to go from an idea, issue, or bug report through to a complete implementation plan ready for execution. Handles severity-aware scope routing across three ceremony tiers (swift, standard, thorough), routing between feature specs, bug specs, and quick implementations, and produces a reviewed plan ready for execution. Chains to arn-implementing at completion.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A well-sequenced, highly actionable orchestrator skill with clear gates and error handling. Its main weakness is conciseness (repeated preference-check boilerplate that could be consolidated) and a progressive-disclosure gap: one referenced file is missing from the bundle and one bundle file is unreferenced.

Suggestions

Add the missing references/preferences-schema.md (cited three times for the two-tier lookup chain) or remove the citations, so every referenced path resolves to a real file.

Reference references/scope-router-test-scenarios.md from the scope-router section (or remove it from the bundle) so the test-scenario file is discoverable and the bundle stays in sync.

Factor the repeated preference-check + gate + 'remember this?' follow-up pattern (G2/G3/G4) into a single shared reference or template to reduce duplicated tokens across the three gates.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely free of concept-explanation padding, but the preference-check blocks (G2 expert-debate, G3 spec-review, G4 plan-review) repeat nearly identical two-tier lookup + gate + follow-up structure verbatim and could be factored into a shared reference, tightening the token budget.	2 / 3
Actionability	Gives concrete, executable guidance throughout — exact Skill invocations ('Skill: arn-code:arn-code-pick-issue'), specific file paths to read, decision tables with first-match-wins rules, and literal AskUserQuestion prompts with enumerated options.	3 / 3
Workflow Clarity	Clear 10-step sequence with numbered steps, ASCII progress displays, labeled gates G1–G5, state-detection ordering ('Check from most advanced to least advanced — first match wins'), preference-resolution checkpoints, and a dedicated Error Handling section covering resume and sub-skill failure.	3 / 3
Progressive Disclosure	The body correctly offloads scoring detail to references/scope-router-criteria.md (a real, one-level-deep file), but references/preferences-schema.md is cited three times and does not exist in the bundle, while references/scope-router-test-scenarios.md exists but is never referenced — structure is present but navigation is inconsistent.	2 / 3
	Total	10 / 12 Passed

Description

100%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 explicitly covers what the skill does and when to use it, lists natural trigger phrases users would say, and stays in third person. It is slightly long but every clause earns its place for a complex orchestrator skill.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'severity-aware scope routing across three ceremony tiers (swift, standard, thorough)', 'routing between feature specs, bug specs, and quick implementations', 'produces a reviewed plan ready for execution', 'Chains to arn-implementing' — in third-person voice.	3 / 3
Completeness	Explicitly answers both what (orchestrates scope routing, spec/plan generation, review, chaining) and when ('This skill should be used when the user says...'), satisfying the 'Use when...' requirement.	3 / 3
Trigger Term Quality	Lists many natural phrases a user would actually say ('planning', 'plan a feature', 'start planning', 'I want to build', 'new feature', 'what should I build', 'pick an issue', 'plan a bug fix', 'I have an idea'), giving strong coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (the Arness planning pipeline) with a distinct skill name 'arn-planning' and explicit routing boundary versus the chained arn-implementing, making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: AppsVortex/arness
Path: plugins/arn-code/skills/arn-planning/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.