Name: arn-code-batch-planning
Rating: 71.2 (1 reviews)
Author: AppsVortex

arn-code-batch-planning

This skill should be used when the user says "batch planning", "batch plan", "arness batch planning", "arn-code-batch-planning", "plan multiple features", "plan all features", "plan unblocked features", "plan the backlog", "plan from backlog", "batch spec and plan", "plan next features", "sequential planning", "multi-feature plan", "plan the next batch", "plan these features", "batch plan GitHub issues", "batch plan from Jira", "plan issues in batch", or wants to plan multiple features from the greenfield Feature Tracker, GitHub issues, or Jira issues in a single session. Pre-analyzes all selected features in parallel, then guides sequential spec review with pipelined plan generation. This skill is typically invoked directly or after arn-brainstorming completes and chains to arn-code-batch-implement upon completion. For single-feature planning, arn-planning is the correct entry point.

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.

The body is a thorough, highly actionable batch orchestration workflow with strong sequencing and error handling. Its main weaknesses are verbosity in the preference/upgrade-gate logic and inline content that would benefit from being split into reference files.

Suggestions

Move the Complex Phase Upgrade Gate (Step 3.5c) and its two-tier preference lookup into a reference file, keeping only the decision summary and a 'Read X and follow its instructions' pointer in SKILL.md.

Externalize the Step 2.5 scope-assessment scoring detail (the 6 criteria, weights, override and edge-case rules) into a reference, retaining only the tier table and override gate inline.

Tighten repeated phrasing in the session-memory and remember-this follow-up sub-sections to reduce token cost without losing the decision logic.

Dimension	Reasoning	Score
Conciseness	The ~600-line body is mostly procedural and free of concept re-explanation, but the Complex Phase Upgrade Gate and two-tier preference lookup with session-memory model are verbose and repeat themselves, fitting 'could be tightened' rather than the lean level (3).	2 / 3
Actionability	Provides concrete executable commands ('gh issue list --state open --limit 20 --json number,title,labels', 'git checkout -b plans/<date>-batch', 'mkdir -p <plans-dir>/SWIFT_<name>/') and exact AskUserQuestion option text, matching the copy-paste-ready anchor above the pseudocode level (2).	3 / 3
Workflow Clarity	Steps 0–6 are clearly sequenced with explicit validation/checkpoints (scope gate, plan approval, PR-merge confirmation) and retry/revert feedback loops per phase for a batch operation, matching the clear-sequence-with-validation anchor above the checkpoints-missing level (2).	3 / 3
Progressive Disclosure	Two real one-level references (backlog-selection.md, plan-shipping.md) are clearly signaled, but large inline blocks such as the complex-phase-upgrade gate and full scope-assessment scoring belong in reference files, fitting 'content that should be separate is inline' rather than the well-split level (3).	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 states concrete actions, gives an extensive set of natural trigger phrases, and explicitly answers both what and when while disambiguating from the sibling single-feature skill. It is slightly verbose for a description but every element earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person — 'Pre-analyzes all selected features in parallel, then guides sequential spec review with pipelined plan generation' — matching the anchor for specific concrete actions rather than the partial domain/action level (2).	3 / 3
Completeness	Explicitly answers both what (pre-analyze in parallel, sequential spec review, pipelined plan generation) and when ('This skill should be used when the user says...'), which is above the has-what-but-when-implied level (2).	3 / 3
Trigger Term Quality	Provides broad natural-language triggers users would say ('batch planning', 'plan multiple features', 'plan all features', 'plan the backlog', 'batch plan GitHub issues'), matching good coverage rather than the missing-common-variations level (2).	3 / 3
Distinctiveness Conflict Risk	Clear batch-planning niche with distinct triggers and explicit disambiguation ('For single-feature planning, arn-planning is the correct entry point'), making conflicts unlikely; a few generic terms like 'plan next features' are outweighed by the explicit routing.	3 / 3
	Total	12 / 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 (620 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-batch-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.