bun-workers

Use for Web Workers in Bun, worker_threads, parallel processing, and background tasks.

Quality

73%

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 ./plugins/bun/skills/bun-workers/SKILL.md

Quality

Content

80%Weight 40%Scale 1-3

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 lean, highly actionable code reference with strong coverage of Web Workers and worker_threads patterns. Its weaknesses are structural rather than technical: it lacks explicit workflow validation checkpoints and signals reference files that are absent from the bundle.

Suggestions

Add an explicit validate/retry checkpoint to the worker pool example (e.g., confirm each task result before dequeueing, and re-enqueue on worker error) so the batch path has a feedback loop.

Either create references/optimization.md and references/patterns.md or remove the "When to Load References" section, so signaled references resolve to real files.

Move the extended pattern catalog (Message Channel, Parallel Map, CPU-Intensive Tasks) into a references/patterns.md file and keep SKILL.md as a concise overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is almost entirely executable code with minimal prose, assumes Claude's competence, and avoids explaining what workers or libraries are. There is minor redundancy (the "Worker with URL" section repeats the basic constructor), but overall every section earns its place.	3 / 3
Actionability	Examples are complete, executable TypeScript snippets (worker + main pairs, transferable buffers, SharedArrayBuffer, worker pool class) that are copy-paste ready, plus a concrete "Common Errors" table mapping cause to fix. This matches the fully-executable anchor.	3 / 3
Workflow Clarity	The skill is structured as a recipe/reference collection rather than a sequenced workflow; patterns are listed but lack explicit validation checkpoints. The graceful-shutdown-with-timeout in "Termination" is the only feedback-style loop, and batch operations like the worker pool have no validate/retry step, capping clarity at 2.	2 / 3
Progressive Disclosure	Sections are organized and the "When to Load References" block clearly signals one-level-deep references, but the body is a monolithic ~384-line inline reference and the referenced files (references/optimization.md, references/patterns.md) do not exist in the bundle. It is better than a wall-of-text level-1, but the missing files and inline-heavy structure keep it below level-3.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 is concise and carries an explicit trigger clause with a recognizable Bun-workers niche, but it relies on topic nouns rather than concrete actions and includes a couple of generic terms that invite overlap. Tightening the action list and adding common trigger variations would lift it from good to strong.

Suggestions

Replace topic nouns with concrete verbs, e.g. "Spawn Web Workers and worker_threads in Bun for parallel processing, CPU-bound work, and background tasks."

Add natural trigger variations users might say ("multithreading", "concurrency", "offload heavy computation") to broaden trigger coverage.

Sharpen distinctiveness by scoping to Bun specifically ("in Bun") for every listed capability so it does not read as a generic concurrency skill.

Dimension	Reasoning	Score
Specificity	The description names concrete domains ("Web Workers in Bun", "worker_threads") but uses no action verbs, listing topics rather than the specific actions the skill performs. It is above the vague "Helps with documents" anchor but below the multi-concrete-action anchor.	2 / 3
Completeness	The "Use for..." clause provides explicit trigger guidance answering when to invoke the skill, and the listed domains answer what it covers, satisfying both halves. This avoids the "missing Use when... caps at 2" penalty because an equivalent explicit trigger clause is present.	3 / 3
Trigger Term Quality	"Web Workers", "Bun", "parallel processing", and "background tasks" are natural terms a user would say, but "worker_threads" is technical jargon and common variations (e.g., "multithreading", "concurrency") are missing. Not a level-1 jargon-only case, but not the broad coverage of a level-3 example either.	2 / 3
Distinctiveness Conflict Risk	The "Web Workers in Bun" / "worker_threads" framing carves a clear niche, but "parallel processing" and "background tasks" are generic and could overlap with other concurrency or task-scheduling skills. It is more specific than a level-1 generic description but not the unambiguous, conflict-free niche of a level-3.	2 / 3
	Total	9 / 12 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
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: secondsky/claude-skills
Path: plugins/bun/skills/bun-workers/SKILL.md
Commit: 4867baa

Reviewed: 7 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.