bun-runtime

Use for Bun runtime, bunfig.toml, watch/hot modes, env vars, CLI flags, and module resolution.

Quality

74%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/bun/skills/bun-runtime/SKILL.md

Quality

Discovery

72%

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 effectively targets the Bun runtime niche with good trigger terms that developers would naturally use. However, it lacks concrete action verbs describing what the skill actually does (configure, troubleshoot, set up, etc.) and the 'Use for' framing is more of a topic list than explicit trigger guidance. Adding specific actions and clearer 'when' scenarios would strengthen it.

Suggestions

Add concrete action verbs describing what the skill does, e.g., 'Configures Bun runtime settings, troubleshoots module resolution, sets up watch/hot reload modes'

Expand the trigger clause to be more explicit, e.g., 'Use when the user asks about Bun configuration, bunfig.toml setup, Bun CLI flags, or Bun-specific module resolution issues'

Dimension	Reasoning	Score
Specificity	Names the domain (Bun runtime) and lists several specific areas (bunfig.toml, watch/hot modes, env vars, CLI flags, module resolution), but these are more like topic areas than concrete actions. It doesn't describe what actions are performed (e.g., 'configure', 'debug', 'set up').	2 / 3
Completeness	Has a 'Use for...' clause which partially addresses 'when', but it reads more like a topic list than explicit trigger guidance. The 'what does this do' part is weak—it lists topics but not actions. The 'Use for' is close to a 'Use when' but doesn't clearly articulate triggering scenarios.	2 / 3
Trigger Term Quality	Includes strong natural keywords users would actually say: 'Bun', 'bunfig.toml', 'watch mode', 'hot mode', 'env vars', 'CLI flags', 'module resolution'. These cover common terms a developer working with Bun would use.	3 / 3
Distinctiveness Conflict Risk	Bun runtime is a clearly distinct niche. The specific mentions of bunfig.toml, watch/hot modes, and Bun-specific CLI flags make this unlikely to conflict with Node.js or Deno skills.	3 / 3
	Total	10 / 12 Passed

Implementation

77%

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

This is a solid, actionable runtime reference skill with good structure and concrete examples throughout. Its main weakness is moderate verbosity—the globals table and introductory description add tokens without much value for Claude, and some content could be offloaded to the referenced files to keep the main skill leaner. The progressive disclosure references are well-signaled but cannot be verified without bundle files.

Suggestions

Remove or significantly trim the Globals Available table—Claude already knows about standard Web/Node.js globals like fetch, Buffer, and console.

Remove the introductory sentence explaining what Bun is (Claude already knows this) to save tokens.

Move the globals table and debugging section to reference files to keep SKILL.md as a concise overview.

Dimension	Reasoning	Score
Conciseness	Generally efficient with good use of tables and code blocks, but includes some unnecessary content like the globals table (Claude already knows about standard Web/Node globals) and explanations like 'Bun is a fast all-in-one JavaScript runtime built on JavaScriptCore (Safari's engine)' which Claude doesn't need.	2 / 3
Actionability	Provides fully executable, copy-paste ready commands throughout. CLI flags, code examples, and bash commands are all concrete and specific. The flag ordering tip ('Put Bun flags immediately after bun') is a particularly actionable detail.	3 / 3
Workflow Clarity	For a runtime reference skill like this, there aren't destructive multi-step workflows requiring validation checkpoints. The content is well-sequenced from basic usage through advanced features, and the watch vs hot comparison table clearly distinguishes when to use each mode. The common errors table serves as a lightweight troubleshooting workflow.	3 / 3
Progressive Disclosure	The 'When to Load References' section at the end provides clear signaling to reference files (bunfig.md, cli-flags.md, module-resolution.md), but no bundle files were provided to verify these exist. The main content is somewhat long (~150 lines) and the globals table and some sections could potentially be moved to reference files to keep the overview leaner.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: secondsky/claude-skills
Commit: 5e92b71

Reviewed: 17 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.