CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bun-cloudflare-workers

This skill should be used when the user asks about "Cloudflare Workers with Bun", "deploying Bun to Workers", "wrangler with Bun", "edge deployment", "Bun to Cloudflare", or building and deploying applications to Cloudflare Workers using Bun.

60

Quality

75%

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-cloudflare-workers/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 content is highly actionable — complete, executable code and configs for every major Workers feature — but it reads as a monolithic reference dumped into SKILL.md. Its two structural flaws are the missing references/ files it tells the reader to load, and the absence of any validation checkpoint between development and deployment.

Suggestions

Create references/bindings.md and references/performance.md (or remove the 'When to Load References' section) — the body currently points to files that do not exist in the bundle.

Move the per-binding detail sections (Durable Objects, R2, D1, KV) into references/bindings.md so SKILL.md stays a lean overview, keeping only the Quick Start, Basic Worker, and Hono example inline.

Wire validation into the deploy workflow, e.g. Quick Start: create → install → dev → run `bun test` → deploy only when tests pass, and note checking `wrangler deploy` output for errors.

Deduplicate the D1 examples (Hono section vs. D1 section) and remove the trivial mock-worker test example to tighten the token budget.

DimensionReasoningScore

Conciseness

Mostly efficient code-first content, but ~410 lines include duplicated patterns (D1 queries appear in both the Hono section and the D1 section, three separate `export default { fetch }` boilerplates), a trivial mock-test example, and unpinned time-sensitive versions ('wrangler': '^4.81.0', compatibility_date '2024-01-01'). Matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 4, which requires only minor trims.

3 / 5

Actionability

Nearly everything is copy-paste ready: complete wrangler.toml configs, full worker/Hono/Durable Object code blocks, build scripts, and CLI commands covering the common cases. Minor placeholders ('id = "xxx"') are expected user-specific values, not gaps, so the top anchor fits.

5 / 5

Workflow Clarity

The Quick Start gives a clear sequence (create → install → dev → deploy) but has no validation checkpoints — testing with `bun test`/Miniflare exists as a separate section yet is never wired into the deploy flow, and deploy is an outward-facing operation with no verify step. This matches 'steps listed but validation gaps' rather than 4, which requires most checkpoints present.

3 / 5

Progressive Disclosure

The bundle contains no references/ directory at all, yet the body directs the reader to load 'references/bindings.md' and 'references/performance.md' — broken pointers. Meanwhile ~250 lines of per-binding API detail (Durable Objects, R2, testing, build) is inlined in SKILL.md when it clearly belongs in separate files, matching the score-2 anchor ('content that clearly belongs in separate files is inlined; or references are buried'). Not a 3 because the advertised structure does not actually exist.

2 / 5

Total

13

/

20

Passed

Description

78%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 description with an explicit 'use when' trigger list and natural keyword variations that clearly carve out the Bun-on-Cloudflare-Workers niche. It would benefit from naming a few more concrete capabilities (testing, bindings, configuration) beyond 'building and deploying'.

DimensionReasoningScore

Specificity

The description names the domain ('Cloudflare Workers using Bun') and only 1-2 concrete actions ('building and deploying applications'), which matches the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It is not a 4 because capabilities like testing, bindings configuration, or scaffolding are never mentioned as actions.

3 / 5

Completeness

It explicitly answers 'when' ('This skill should be used when the user asks about...') with concrete trigger phrases, and 'what' ('building and deploying applications to Cloudflare Workers using Bun'). Not below 5 because both elements are explicitly present and concrete, matching the top anchor.

5 / 5

Trigger Term Quality

Good coverage of natural phrasings users would say: 'Cloudflare Workers with Bun', 'deploying Bun to Workers', 'wrangler with Bun', 'edge deployment', 'Bun to Cloudflare'. Not a 5 because common synonyms like 'serverless', 'edge functions', or 'CF Workers' are missing.

4 / 5

Distinctiveness Conflict Risk

The Bun + Cloudflare Workers combination is a clear niche with distinct triggers, but generic terms like 'edge deployment' could overlap with other edge/serverless skills. Mostly distinct with minor overlap risk, matching the score-4 anchor rather than 5.

4 / 5

Total

16

/

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

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

secondsky/claude-skills

Path

plugins/bun/skills/bun-cloudflare-workers/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.