CtrlK
BlogDocsLog inGet started
Tessl Logo

bun-development

Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by [oven-sh/bun](https://github.com/oven-sh/bun).

48

Quality

52%

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/AI-Agents-Safe-Coding-Skills/skills/bun-development/SKILL.md

The canonical home for this skill is bun-development in sickn33/agentic-awesome-skills

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 a highly actionable, executable reference for Bun, but it is a monolithic 690-line dump with padding and no progressive disclosure into separate reference files. Its one sequenced workflow (migration) lacks the validation checkpoint the rubric requires for destructive operations.

Suggestions

Split the large API, testing, and bundling references into separate files under references/ and keep SKILL.md as a concise overview that links to them, improving progressive disclosure.

Add a verification step to the migration workflow (e.g., run 'bun --version' and 'bun test' after 'rm -rf node_modules') so destructive changes are validated before proceeding.

Remove redundant or padding content — the 'Why Bun?' table, the duplicated install block in 8.2, basic Node-global explanations, and the Quick Reference table — to tighten conciseness.

DimensionReasoningScore

Conciseness

Most of the body is dense, useful command/code reference, but it carries padding Claude doesn't need — the marketing 'Why Bun?' table, Node-compat basics (Buffer, process.cwd(), __dirname), installation shown twice (1.1 and 8.2), and a Quick Reference table duplicating earlier commands — fitting 'Mostly efficient but includes some unnecessary explanation'.

3 / 5

Actionability

It provides abundant copy-paste-ready, executable commands and complete code examples (bun init, bun add, Bun.serve, bun:test, Bun.build) covering the common cases across the domain, matching 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

As a reference doc it has no real multi-step workflow except 8.2 Migration, which runs the destructive 'rm -rf node_modules package-lock.json' with no validation/verification checkpoint; the rubric caps destructive/batch workflows lacking validation at 3, matching 'Steps listed but validation gaps'.

3 / 5

Progressive Disclosure

No bundle files exist and ~690 lines of API/testing/bundling reference are inlined into one file with only section headers — content that belongs in separate reference files is not split out — but the numbered headers provide internal structure, fitting 'Some structure…content that should be separate is inline'.

3 / 5

Total

14

/

20

Passed

Description

40%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 identifies a distinct niche (Bun-based JS/TS development) but is vague on actions and omits any explicit 'Use when…' trigger guidance. It is distinguishable yet under-specified for triggering.

Suggestions

Add an explicit 'Use when…' clause naming concrete triggers, e.g. 'Use when starting or migrating JS/TS projects to Bun, or using its bundler, test runner, or built-in HTTP/SQLite APIs.'

Replace the generic noun 'development' with concrete actions (e.g., 'bundle, test, and run JavaScript/TypeScript with the Bun runtime').

Drop the filler 'Fast, modern' adjectives and the 'inspired by' link to tighten the description.

DimensionReasoningScore

Specificity

The phrase 'JavaScript/TypeScript development with the Bun runtime' names the domain concretely but lists no concrete actions — 'development' is a generic noun rather than action verbs like bundle, test, or serve — matching the anchor 'Names the domain but actions are minimal or generic'.

2 / 5

Completeness

It offers only a vague categorical 'what' ('Fast, modern JavaScript/TypeScript development') and contains no 'Use when…' trigger clause; per the rubric, a missing trigger clause caps completeness at 3, and the vague-what/no-when fit is anchor 2.

2 / 5

Trigger Term Quality

It includes the natural core term 'Bun' plus 'JavaScript/TypeScript' and 'runtime', but misses common variations and synonyms users say (.ts, bun test, bundler), fitting 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The 'Bun runtime' framing carves a clear niche distinguishable from generic Node/JS skills with only minor overlap risk, matching 'Mostly distinct; minor overlap risk with closely related skills'.

4 / 5

Total

11

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (697 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.