CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hono-routing

Type-safe Hono APIs with routing, middleware, RPC. Use for request validation, Zod/Valibot validators, or encountering middleware type inference, validation hook, RPC errors.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/hono-routing/skills/hono-routing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 highly actionable with concrete, mostly copy-paste-ready TypeScript covering the core Hono workflows, and reference navigation is well signaled. It is dragged down by significant token waste (marketing content, framework comparison, repeated examples, pinned versions), implicit rather than explicit validation checkpoints, and a templates/ directory referenced throughout that is missing from the actual bundle.

Suggestions

Cut the 'Why Hono' bullets, the Hono vs Express vs Fastify comparison table, the 'Recommendation' block, and the 'Verified working projects' link list — Claude already knows how to compare web frameworks, and these pad the token budget without adding instructions.

Remove or move pinned versions and dates (hono@4.12.12, zod@4.3.6, 'Last Updated: 2025-11-21') into the version-check script or a dedicated versioning note, since stale version pins will silently rot; scripts/check-versions.sh already exists but is never referenced in the body.

Fix the broken templates/ references: either add the nine template files the Use Cases and 'Templates' section point to, or rewrite Use Cases 3–5 to reference the existing references/ files, and add an explicit validation step (e.g., a run-and-curl command after 'Tested routes locally') to the setup checklist.

DimensionReasoningScore

Conciseness

The body carries substantial padding Claude does not need: a "Why Hono" marketing list ("Fast", "Lightweight: ~10KB"), a Hono vs Express vs Fastify comparison table with recommendations, "(17.8k ⭐)", and "Verified working projects" link lists. It also repeats the zValidator example three times and embeds time-sensitive pinned versions and dates (hono@4.12.12, "Last Updated: 2025-11-21") outside any deprecated/old-patterns section, matching the 'noticeably verbose with several unnecessary or padded sections' anchor rather than the mostly-efficient 3.

2 / 5

Actionability

Most guidance is executable: install commands ("bun add hono@4.12.12"), a basic app, zValidator usage with c.req.valid('json'), typed Variables, HTTPException + app.onError/notFound, and a full hc<AppType> RPC client/server pair. Minor gaps — e.g., `isAuthorized` and `apiRoutes` appear undefined in the middleware and production snippets — keep it below the fully copy-paste-ready 5.

4 / 5

Workflow Clarity

The Quick Start (install → basic app → add validation) and the Complete Setup Checklist give a rough sequence, but validation checkpoints are only implicit ("[ ] Tested routes locally" with no command or feedback loop) and there is no validate → fix → retry guidance for the documented error cases. This matches the 'steps listed but checkpoints missing or implicit' anchor rather than the 4 anchor's 'most checkpoints present'.

3 / 5

Progressive Disclosure

The "When to Load References" section is clearly signaled and all six references/ files it names exist in the bundle, which is good. However, Use Cases 3–5 and the "Templates (templates/)" section direct the reader to nine template files in a templates/ directory that does not exist in the bundle (metadata claims "templates_included: 9"), and the existing scripts/check-versions.sh is never referenced — broken navigation that outweighs the 'minor organization gaps' of a 4.

3 / 5

Total

12

/

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: it states concrete capabilities and includes an explicit "Use for..." trigger clause with natural, framework-specific keywords. The main weaknesses are the awkwardly compressed when-clause and missing common trigger variations, which keep completeness and trigger coverage just below the top anchors.

DimensionReasoningScore

Specificity

The description names the domain (Hono) and several concrete capabilities — "Type-safe Hono APIs with routing, middleware, RPC" plus "request validation, Zod/Valibot validators" — which matches the anchor for several specific actions with minor gaps. It falls short of 5 because coverage is not comprehensive (e.g., error handling, context typing, and setup are only implied via the error-trigger phrase).

4 / 5

Completeness

Both "what" ("Type-safe Hono APIs with routing, middleware, RPC") and "when" ("Use for request validation, Zod/Valibot validators, or encountering middleware type inference, validation hook, RPC errors") are explicitly present. The when-clause is compressed and grammatically awkward ("encountering middleware type inference, validation hook, RPC errors") and omits common triggers, so it does not clearly match the concrete, fully explicit phrasing of a 5.

4 / 5

Trigger Term Quality

Natural trigger phrases like "request validation", "Zod/Valibot validators", "RPC errors", and "Hono" match what a user with this need would actually say, giving good keyword coverage. A few natural terms are missing (e.g., "hono/client", "endpoints", "app setup"), so it does not reach the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

"Hono" plus framework-specific triggers (zValidator, RPC type inference, validation hooks) define a clear niche with distinct triggers and minimal conflict risk against other skills. It is well above the 'mostly distinct' 4 anchor because no other common skill domain would match these triggers.

5 / 5

Total

17

/

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 (509 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/hono-routing/skills/hono-routing/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.