batch

Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use `/batch` followed by operation and file pattern.

Quality

70%

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 ./packages/core/src/skills/bundled/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.

A highly actionable, well-structured orchestration skill whose main weaknesses are verbosity from redundant restatements and a missing failure-retry feedback loop for batch operations. It is self-contained but monolithic, with no progressive disclosure into reference files.

Suggestions

Add a validate→retry feedback loop: after aggregation, re-chunk and re-run worker agents against FAILED files (with adjusted prompts) before reporting the final summary, so the batch operation has a recovery checkpoint.

De-duplicate the chunking limits: keep the single constraints table and remove the repeated 3/15/5 values from the chunking algorithm and example sections, and collapse the three identical agent-invocation blocks into one with a 'repeat per chunk' note.

Move the worker prompt template, the three usage examples, and the dry-run spec into separate reference files (e.g. references/worker-prompt.md, references/examples.md) linked from the body to reduce SKILL.md length and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of beginner-concept padding, but the 3/15/5 limits are restated across the chunking table, chunking algorithm, and constraints table, and the 'Example Invocation Pattern' repeats the same agent prompt three times verbatim.	3 / 5
Actionability	Provides a copy-paste worker prompt template, a concrete parallel-invocation pattern, an exact output-format spec, a chunking table, and an exclusion list — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	Steps 1–5 are clearly sequenced with a >50-file warning and opt-in dry-run, but as a batch operation it lacks a validate→fix→retry feedback loop on failed files, which caps this dimension at 3 per the batch guideline.	3 / 5
Progressive Disclosure	Sections are well-organized with clear headers, but ~295 lines are inlined into a single SKILL.md with no bundle files; the prompt template, usage examples, and dry-run spec arguably belong in separate referenced files.	3 / 5
	Total	14 / 20 Passed

Description

75%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.

A solid, third-person description that states concrete capabilities and provides explicit invocation trigger guidance. It is comprehensive enough to be distinct and actionable, with only minor gaps in synonym coverage and use-case framing.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'discovers files, splits into chunks, and processes with parallel worker agents' — covering the orchestration pipeline, though it stops short of naming output aggregation or error handling.	4 / 5
Completeness	A clear 'what' (execute batch operations in parallel) is paired with an explicit trigger clause ('Use `/batch` followed by operation and file pattern'), satisfying both halves, though the 'when' is framed as invocation syntax rather than a use-case trigger.	4 / 5
Trigger Term Quality	Natural terms like 'batch operations', 'files in parallel', 'file pattern', and the '/batch' invocation are present, but common synonyms a user might say (e.g. 'process all files', 'in bulk') are not covered.	4 / 5
Distinctiveness Conflict Risk	The parallel-batch-on-multiple-files niche is fairly distinct and tied to a named '/batch' command, with only minor overlap risk against general file-editing skills.	4 / 5
	Total	16 / 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: QwenLM/qwen-code
Path: packages/core/src/skills/bundled/batch/SKILL.md
Commit: 054eabb

Reviewed: 1 day 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.