CtrlK
BlogDocsLog inGet started
Tessl Logo

bun-bundler

This skill should be used when the user asks about "bun build", "Bun.build", "bundling with Bun", "code splitting", "tree shaking", "minification", "sourcemaps", "bundle optimization", "esbuild alternative", "building for production", "bundling TypeScript", "bundling for browser", "bundling for Node", or JavaScript/TypeScript bundling with Bun.

61

Quality

73%

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 ./plugins/bun/skills/bun-bundler/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.

A highly actionable, well-structured reference whose main weaknesses are redundant code blocks, a partially broken reference layer (two of three referenced files do not exist), and duplication of the options reference between the body and the bundle.

Suggestions

Remove the redundant code blocks — collapse the three near-identical Target Environment snippets into one example with a note that `target` accepts "browser" | "bun" | "node", and state the Bun 1.2+ rejects-on-failure / try/catch idiom once instead of three times.

Fix the broken references: `references/plugins.md` and `references/macros.md` are named in "When to Load References" but are not present in the bundle — either create them or remove the references so Claude does not attempt to load non-existent files.

De-duplicate the options material: keep only key examples inline in SKILL.md and defer the exhaustive option/flag catalog to `references/options.md` rather than reproducing it in both places.

DimensionReasoningScore

Conciseness

There is no concept padding, but redundancy is noticeable: the three Target Environment snippets are near-identical (only `target` differs) and the "Bun 1.2+ rejects on failure / try/catch" idiom is repeated three times, which is more than the 'minor' trimming implied by the 4 anchor.

3 / 5

Actionability

Abundant copy-paste-ready, executable guidance — CLI commands, a fully annotated `Bun.build` config, a concrete onResolve/onLoad plugin example, and output iteration — covering the common cases comprehensively.

5 / 5

Workflow Clarity

A clear Quick Start surfaces two entry paths (CLI and JS API) and a try/catch error loop is shown, but there is no explicit sequenced multi-step workflow with validation checkpoints; as a reference-style skill it sits between the implicit-sequence and clear-checkpoint anchors.

3 / 5

Progressive Disclosure

Section structure is good and references are clearly signaled in a dedicated "When to Load References" section, but only `references/options.md` exists — `references/plugins.md` and `references/macros.md` are referenced yet missing — and the full options reference is duplicated inline and in the file, pulling it below the 4 anchor.

3 / 5

Total

14

/

20

Passed

Description

81%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 strong, distinctive description with excellent trigger-term coverage and explicit usage guidance. Its only weakness is that capabilities are expressed as user-asked topics rather than concrete skill actions, leaving the 'what' implicit.

DimensionReasoningScore

Specificity

The description names the domain and several concrete capability topics ("code splitting", "tree shaking", "minification", "sourcemaps", "bundle optimization"), but frames them as topics the user asks about rather than actions the skill performs, so it sits below the 'several specific actions' anchor.

3 / 5

Completeness

The 'when' is explicit and specific ("This skill should be used when the user asks about…"), and a 'what' is present but only embedded in the trigger list ("JavaScript/TypeScript bundling with Bun") rather than stated as a clean capability sentence, so it falls just below the 'clearly answers both' anchor.

4 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including synonyms and API names — "bun build", "Bun.build", "bundling with Bun", "esbuild alternative", "minification", "tree shaking", "building for production", matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Scoped tightly to Bun's bundler with distinctive triggers ("bun build", "Bun.build", "esbuild alternative"), giving it a clear niche with minimal conflict risk against other skills.

5 / 5

Total

17

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
secondsky/claude-skills
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.