batch

Break a large, parallelizable goal into bounded work units, coordinate existing agent/worktree machinery, integrate, and verify. Explicit-only.

Quality

53%

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

Fix and improve this skill with Tessl

tessl review fix ./crates/tui/assets/skills/batch/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is admirably concise and well-structured with clear sections and an explicit non-goals list, but the workflow steps are abstract directives lacking concrete tool names, commands, or validation checkpoints appropriate for a batch operation. It reads as an outline rather than executable guidance.

Suggestions

Make the workflow actionable: name the actual tools (e.g. delegate/worktree) and give a concrete partitioning heuristic or example instead of 'Partition into bounded units'.

Add an explicit validation/verify checkpoint with a feedback loop (verify -> fix -> retry) since this is a batch operation, which would lift workflow_clarity above the cap of 3.

Specify how integration is performed and what 'verify' checks (e.g. run tests, check for merge conflicts), so step 3 is executable rather than aspirational.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean (about 10 lines) and assumes Claude's competence, with no padding or explanation of concepts Claude already knows; every section earns its place.	5 / 5
Actionability	Steps are high-level directives ('Partition into bounded units', 'Run units with existing agent/worktree tools') with no concrete commands, code, tool names, or specifics on how to partition or integrate, fitting the 'minimal concrete guidance' anchor.	2 / 5
Workflow Clarity	A clear 3-step sequence is present (partition -> run -> integrate/verify), but this is a batch operation with no explicit validation checkpoints or error-recovery loop, so the rubric's batch-operation cap holds it at 3.	3 / 5
Progressive Disclosure	For a short single-purpose skill under 50 lines with no bundle files and no need for external references, the well-organized section structure (Invocation, When to use, Non-goals, Workflow) meets the simple-skill exception for a top score.	5 / 5
	Total	15 / 20 Passed

Description

42%Weight 40%Scale 1-5

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 states a clear purpose and a few concrete actions but lacks any explicit 'Use when...' trigger guidance, which caps completeness and weakens trigger-term quality. It is concise and third-person but reads as a terse internal directive rather than a discoverable, user-triggered skill description.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to run a large parallelizable task in parallel or to fan out bounded sub-tasks.'

Add natural synonyms users actually say (e.g. 'fan out', 'parallelize', 'batch sub-tasks', 'run many units at once') to improve trigger-term coverage.

Rephrase 'bounded work units' into clearer capability language (e.g. 'partitions the goal into independent chunks, runs each via existing agent/worktree tools, then integrates and verifies').

Dimension	Reasoning	Score
Specificity	Names the domain ('large, parallelizable goal') and several concrete actions ('Partition into bounded units', 'coordinate existing agent/worktree machinery', 'integrate', 'verify'), but the actions are generic verbs rather than detailed capabilities, and the awkward phrasing ('work units', 'bounded') keeps it below 4.	3 / 5
Completeness	It states a clear 'what' (break goals into units, coordinate, integrate, verify) but provides no explicit 'when' trigger guidance, so per the rubric a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	The only natural-ish terms are 'parallelizable goal' and 'sub-work'; there is no 'Use when...' clause and no synonyms or concrete trigger phrases a user would naturally say, leaving it just below the midpoint.	2 / 5
Distinctiveness Conflict Risk	The 'Explicit-only' marker and reuse-of-existing-machinery framing carve a niche, but 'parallelizable goal / sub-work' is broad and could overlap with general delegation skills, so it sits at the midpoint.	3 / 5
	Total	11 / 20 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: Hmbown/CodeWhale
Path: crates/tui/assets/skills/batch/SKILL.md
Commit: 8ae401b

Reviewed: 2 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.