arn-code-batch-merge
This skill should be used when the user says "batch merge", "merge batch", "arness batch merge", "arn-code-batch-merge", "merge all PRs", "merge batch PRs", "merge the batch", "merge implemented features", "batch merge PRs", "merge open PRs", "merge all feature PRs", "combine batch PRs", "land the batch", "land all PRs", or wants to discover open batch implementation PRs, analyze them for conflicts, determine an optimal merge order, and execute merges with user-guided conflict resolution. This skill is typically invoked after arn-code-batch-implement completes and chains to arn-code-batch-simplify upon completion.
86
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%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 excels at trigger term coverage and distinctiveness, providing an exhaustive list of phrases that would invoke this skill and clearly positioning it within a specific workflow chain. However, the capability description is somewhat buried and secondary to the trigger list, and the overall structure prioritizes triggers over a clear, concise statement of what the skill does. The description would benefit from leading with concrete capabilities before listing triggers.
Suggestions
Restructure to lead with concrete capabilities first (e.g., 'Discovers open batch implementation PRs, analyzes them for merge conflicts, determines optimal merge order, and executes merges with user-guided conflict resolution.') before listing trigger phrases.
Consider condensing the trigger phrase list into categories rather than exhaustively enumerating every variation, which would improve readability without losing coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions some concrete actions ('discover open batch implementation PRs, analyze them for conflicts, determine an optimal merge order, and execute merges with user-guided conflict resolution') but they are buried at the end and not presented as a clear list of capabilities. The bulk of the description is trigger phrases rather than capability descriptions. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (discover open batch PRs, analyze conflicts, determine merge order, execute merges with conflict resolution) and 'when' (extensive list of trigger phrases plus contextual trigger of being invoked after arn-code-batch-implement). The 'Use when' equivalent is the opening clause. | 3 / 3 |
Trigger Term Quality | The description provides extensive coverage of natural trigger phrases users would say, including many variations like 'batch merge', 'merge all PRs', 'land the batch', 'merge open PRs', 'merge implemented features', etc. This is thorough coverage of how users would naturally invoke this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The skill is highly distinctive with very specific trigger terms ('batch merge', 'arn-code-batch-merge') and a clear niche (batch merging of implementation PRs with conflict analysis). The mention of chaining from arn-code-batch-implement and to arn-code-batch-simplify further distinguishes it within a workflow. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured orchestration skill with strong workflow clarity and actionability. The multi-step process is clearly sequenced with explicit validation, error handling, and user interaction points. The main weakness is that the skill is somewhat long for a sequencer that claims to delegate logic to sub-skills — some implementation details (worktree cleanup, feature tracker updates) could be extracted to reference files to improve conciseness and progressive disclosure.
Suggestions
Extract the worktree cleanup bash script and Feature Tracker update logic into reference files to keep the main SKILL.md leaner as a sequencer.
Tighten the CHANGE_RECORD scanning section — the criteria list could be more compact since Claude can infer JSON field checking patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is necessary for the complex multi-step workflow. Some sections could be tightened (e.g., the worktree cleanup explanation, the unmerged worktree note), and there's mild over-explanation in places like the CHANGE_RECORD scanning criteria, but overall it respects Claude's intelligence and doesn't explain basic concepts. | 2 / 3 |
Actionability | Provides concrete, executable commands throughout (gh pr merge, git checkout, worktree cleanup bash scripts), specific CLI invocations for both GitHub and Bitbucket platforms, exact file paths to check, and precise conditions for each decision point. The code blocks are copy-paste ready. | 3 / 3 |
Workflow Clarity | Excellent multi-step sequencing with clear numbered steps, explicit validation checkpoints (verify PR state, post-merge refresh analysis, conflict detection after each merge), feedback loops (re-run analyzer after merges, retry on failure), and well-defined branching paths for each user choice. Error recovery is explicit throughout with skip-and-continue semantics. | 3 / 3 |
Progressive Disclosure | The skill references external files (ensure-config.md, conflict-classification.md) and delegates to sub-skills (review-pr, batch-pr-analyzer, batch-simplify), which is good progressive disclosure. However, no bundle files were provided to verify these references exist, and the SKILL.md itself is quite long — some sections like the detailed worktree cleanup logic or the Feature Tracker update could potentially be extracted to reference files. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 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.