CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cloudflare-d1

Cloudflare D1 serverless SQLite on edge. Use for databases, migrations, bindings, or encountering D1_ERROR, statement too long, too many requests queued errors.

58

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/cloudflare-d1/skills/cloudflare-d1/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 delivers excellent, executable coverage of D1 setup, migrations, and query patterns with clear load-conditions for its reference files. Its weaknesses are redundancy (repeated reference listings, TOC, dated changelog) and pointing to templates/, agents/, and commands/ files that do not exist in the bundle.

Suggestions

Fix broken bundle references: either add the referenced `templates/`, `agents/`, and `commands/` files or remove the 'Using Bundled Resources', 'Interactive Tools', and 'Load `templates/schema-example.sql`' pointers to nonexistent paths.

De-duplicate reference navigation — keep only the 'When to Load References' section and drop the repeated listings in 'Using Bundled Resources' and the closing 'Questions? Issues?' block.

Trim the Table of Contents and 'What Is D1?' concept section, and move the dated 'New in 2025' changelog into `references/2025-features.md`, keeping only the breaking-change warning inline.

DimensionReasoningScore

Conciseness

The body is mostly dense, useful code, but includes unnecessary padding: a Table of Contents, a 'What Is D1?' section explaining the technology, a dated changelog ('New in 2025' with specific months), and the reference files re-listed three times (inline, in 'When to Load References', and again in the closing 'Questions?' section). This fits 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than level 4's 'minor instances'.

3 / 5

Actionability

Nearly every section gives complete, copy-paste-ready code: the 5-step Quick Start with exact `bunx wrangler d1` commands, a full wrangler.jsonc config, complete CRUD/batch/pagination/replication TypeScript examples, and executable migration SQL. The examples cover the common cases and match the 'fully executable, copy-paste ready' anchor; not level 4 because there are no meaningful gaps.

5 / 5

Workflow Clarity

The Quick Start is a clear numbered 5-step sequence, and migration workflows include validation ('Test locally first' with `wrangler d1 execute ... --command "SELECT * FROM users"`, plus 'Never run migrations without testing locally'), so the destructive/batch cap at 3 does not apply. It falls short of level 5 because there is no explicit validate-fix-retry loop for failed migrations or failed batch operations.

4 / 5

Progressive Disclosure

Structure is good — an overview with a 'When to Load References' section mapping conditions to the seven real references/ files, one level deep — but the body directs the reader to nonexistent bundles: `templates/schema-example.sql`, `templates/d1-worker-queries.ts`, `templates/cloudflare-d1:setup-migration.sh`, `agents/d1-debugger.md`, `agents/d1-query-optimizer.md`, and two `commands/*.md` files that are absent from the skill. References are clearly signaled (above level 3's 'not clearly signaled'), but broken navigation paths are more than the 'minor organization gaps' of level 4.

3 / 5

Total

15

/

20

Passed

Description

65%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 has strong, explicit trigger guidance including verbatim error strings, but defines the technology rather than stating concrete capabilities. Adding action verbs (e.g., 'Create, migrate, and query Cloudflare D1 databases') would raise both specificity and completeness.

Suggestions

Add concrete action verbs to the 'what' clause, e.g., 'Create and migrate Cloudflare D1 databases, configure bindings, and optimize queries' instead of the definitional 'serverless SQLite on edge'.

Include natural user phrasings like 'wrangler d1' or 'SQLite in Workers' among the trigger terms to catch queries that don't mention D1 by name.

Narrow the generic 'databases' trigger (e.g., 'D1 databases, wrangler migrations, or Workers database bindings') to reduce overlap with generic SQL/SQLite skills.

DimensionReasoningScore

Specificity

The description names the domain ("Cloudflare D1 serverless SQLite on edge") but contains no concrete action verbs — "Use for databases, migrations, bindings" lists use contexts, not capabilities. It matches the anchor 'Names the domain but actions are minimal or generic' rather than level 3, which requires 1-2 concrete actions like 'create databases' or 'run migrations'.

2 / 5

Completeness

The 'when' is explicit and specific ("Use for databases, migrations, bindings, or encountering D1_ERROR..."), satisfying the 'Use when...' requirement, but the 'what' is a technology label ("serverless SQLite on edge") rather than a statement of what the skill does. It has both parts with one weaker than the other, fitting level 4 rather than level 5's 'clearly and explicitly answers both'.

4 / 5

Trigger Term Quality

Triggers include "databases, migrations, bindings" plus concrete error strings users would paste verbatim ("D1_ERROR, statement too long, too many requests queued"). Missing natural variations such as 'wrangler d1', 'SQLite Workers', or 'D1 queries', so it falls just short of the comprehensive synonym coverage of level 5.

4 / 5

Distinctiveness Conflict Risk

"Cloudflare D1" and the D1-specific error codes give it a clear niche, but the broad trigger word "databases" could overlap with generic database/SQLite skills. Mostly distinct with minor overlap risk, fitting level 4 rather than level 5's minimal-conflict profile.

4 / 5

Total

14

/

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (642 lines); consider splitting into references/ and linking

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

secondsky/claude-skills

Path

plugins/cloudflare-d1/skills/cloudflare-d1/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.