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.
77
73%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/arn-code/skills/arn-code-batch-planning/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It provides an exhaustive list of trigger phrases, clearly describes what the skill does and when to use it, and explicitly differentiates itself from the related single-feature planning skill. The description is well-structured and informative without being unnecessarily verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists multiple specific concrete actions: 'Pre-analyzes all selected features in parallel', 'guides sequential spec review with pipelined plan generation', and mentions integration with specific sources (Feature Tracker, GitHub issues, Jira issues). It also clarifies the workflow chain (after arn-brainstorming, chains to arn-code-batch-implement). | 3 / 3 |
Completeness | Clearly answers both 'what' (pre-analyzes features in parallel, guides sequential spec review with pipelined plan generation) and 'when' (explicit trigger phrases listed, plus contextual triggers like wanting to plan multiple features from specific sources). Also distinguishes from single-feature planning (arn-planning). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms with an extensive list of phrases users would actually say: 'batch planning', 'plan multiple features', 'plan the backlog', 'batch plan GitHub issues', 'batch plan from Jira', 'plan issues in batch', 'sequential planning', 'multi-feature plan', and many more variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (batch/multi-feature planning) and explicitly differentiates itself from the single-feature counterpart (arn-planning). The specific trigger terms and workflow context (Feature Tracker, GitHub, Jira integration) make it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has exceptional workflow clarity with well-defined steps, error handling, and validation checkpoints throughout a complex multi-phase pipeline. However, it is extremely verbose — the ~400+ line body contains extensive procedural detail that could be dramatically condensed given Claude's ability to infer orchestration patterns. The content would benefit from pushing detailed sub-procedures into reference files and keeping the SKILL.md as a lean orchestration overview.
Suggestions
Reduce verbosity by 50-60%: collapse repeated AskUserQuestion patterns into a single 'standard error handling' reference, and condense the selection flow descriptions into decision trees rather than prose.
Move Steps 2.5 (Scope Assessment) and 2.6 (Swift/Standard Plan Generation) into separate reference files, keeping only 2-3 line summaries in the main SKILL.md.
Add executable code or concrete command examples for key operations like scope scoring calculation and plan template population, rather than describing them procedurally.
Create a shared 'error-handling-pattern.md' reference since the retry/skip/abort pattern is repeated identically across Steps 2.7, 3, and 3.5.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Massive amounts of procedural detail that could be condensed significantly. Repeats patterns (error handling, AskUserQuestion flows) multiple times. Many sections explain orchestration logic that Claude could infer from shorter instructions. The layered selection flow, tier override gates, and review loops are spelled out in exhaustive detail when concise decision trees would suffice. | 1 / 3 |
Actionability | Provides concrete file paths, specific tool invocations (AskUserQuestion with options), and clear agent spawning parameters. However, much of the guidance is procedural orchestration rather than executable code — no actual code snippets for plan generation, scope scoring, or template population. Key operations like 'apply the scope router criteria' and 'generate plan following template' lack executable detail, relying on external references. | 2 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing (Steps 0-6), explicit validation checkpoints (tier override gate, plan approval, PR merge confirmation), error handling with retry/skip/abort options at each failure point, and feedback loops (adjust tiers, edit plans, retry failed agents). Status reversal on failure is explicitly specified. The pipeline diagram and progress reporting are well-structured. | 3 / 3 |
Progressive Disclosure | References external files appropriately (scope-router-criteria.md, backlog-selection.md, plan-shipping.md, templates) and delegates to sub-skills. However, the SKILL.md itself is a monolithic wall of procedural text that should have more content pushed to references. Steps 2.5-2.6 alone could be separate reference documents. No bundle files were provided to verify reference accuracy, but the structure suggests too much inline content. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (558 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- AppsVortex/arness
- Commit
1fe948f
- Reviewed
Table of Contents
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.