CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

batch

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

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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 exceptionally concise and cleanly organized for a small, self-contained skill, and its non-goals section usefully constrains scope. Its main weakness is actionability: the workflow reads as an outline rather than executable guidance, with no concrete partitioning criteria, tool invocations, or verification procedure for a batch operation that warrants explicit validation checkpoints.

Suggestions

Make step 1 concrete: state how to partition (e.g., by file, module, or task with an explicit bound such as a max unit size or max concurrent units).

Add an explicit validation checkpoint and feedback loop (e.g., "After integration, verify each unit's result; on failure, re-run or report the failed units") — batch operations require this per the guidelines.

Name the specific tools/commands for step 2 rather than "existing agent/worktree tools", mirroring the concrete "reuse delegate/fleet" reference in Non-goals.

DimensionReasoningScore

Conciseness

The body is lean and efficient — every line states a rule, boundary, or step with zero padding and no explanation of concepts Claude already knows. It matches the 'every token earns its place' anchor exactly.

5 / 5

Actionability

The workflow steps are high-level hints ("Partition into bounded units", "Integrate results and verify") with no concrete commands, partitioning criteria, or verification method; only "reuse delegate/fleet" points at specific machinery. This matches the 'minimal concrete guidance; high-level hints but missing the specific steps to execute' anchor, not 3, which requires some concrete or executable guidance.

2 / 5

Workflow Clarity

The three-step sequence is present and ordered, but there is no explicit validation checkpoint or feedback loop for step failures. As a batch-operations skill missing validation specifics, the judging guidelines cap workflow clarity at 3; it stays at 3 rather than 4 because "verify" is listed as a bare step with no checkpoint or error-recovery path.

3 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files (no references/, scripts/, or assets/ directories exist) and no need for external references, and its sections are well-organized. Per the simple-skill guideline, well-organized sections alone score 5.

5 / 5

Total

15

/

20

Passed

Description

51%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 clearly states what the skill does with a compact action list and a distinctive explicit-only boundary, but it omits any 'Use when...' trigger guidance and contains no natural keywords a user would actually say. Adding an explicit trigger clause with natural phrasing like "Use when the user asks to batch, parallelize, or fan out many similar tasks" would address its two weakest points.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., "Use when the user asks to batch, parallelize, fan out, or run many similar tasks concurrently").

Include natural trigger terms users would say — "batch", "in parallel", "fan out", "split into chunks" — instead of jargon like "bounded work units" and "agent/worktree machinery".

Optionally ground the actions with one concrete example (e.g., "...such as running a check per file or a fix per module") to lift specificity toward 5.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Break a large, parallelizable goal into bounded work units, coordinate existing agent/worktree machinery, integrate, and verify" — matching the anchor for several specific actions with minor gaps. It falls short of 5 because the actions remain abstract (no concrete tool names, commands, or examples of what a work unit looks like).

4 / 5

Completeness

It has a clear 'what' (break into units, coordinate machinery, integrate, verify) but no 'Use when...' clause or equivalent explicit trigger guidance; "Explicit-only" states an invocation constraint, not when the skill applies. Per the judging guidelines a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

The description contains only technical jargon ("bounded work units", "agent/worktree machinery", "Explicit-only") and lacks the natural phrases a user would say when needing this skill, such as "batch these tasks" or "run these in parallel". It sits at the 'one or two generic keywords; missing the natural phrases users say' anchor rather than 3, which requires relevant keywords like "Works with PDF files".

2 / 5

Distinctiveness Conflict Risk

The "Explicit-only" invocation boundary and the focus on partitioning parallelizable goals while reusing existing orchestration machinery make it mostly distinct from related orchestration/research skills. Minor overlap risk with general delegation workflows keeps it at 4 rather than 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.