CtrlK
BlogDocsLog inGet started
Tessl Logo

bencium-code-conventions

Bence's code style, tech stack, and workflow conventions

38

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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 concise, well-organized set of concrete conventions that respects Claude's intelligence and needs no external references. Its main weaknesses are suggestive rather than directive phrasing in places and implicit rather than explicit error-recovery feedback loops in the workflows.

Suggestions

Convert suggestive guidance ('suggest', 'prefer', 'try using RUST') into firm directives or qualify exactly when the choice is the user's call, to lift actionability.

Add an explicit validate->fix->retry feedback loop for the SQL chunking and TDD workflows (e.g. 'if typecheck fails, fix and re-typecheck before proceeding').

Clarify the contradictory backend guidance ('always ask, never local postgres' vs 'usually Supabase, Neon') with a single decisive rule to remove ambiguity.

DimensionReasoningScore

Conciseness

The body is lean bullet directives with no concept-explanation padding (e.g. 'Use ES modules (import/export) syntax', 'Minimize use client'), assuming Claude's competence with every token earning its place.

3 / 3

Actionability

Guidance is specific (e.g. 'const toggle = () =>', '@phosphor-icons/react', 'TailwindCSS v3.x (never v4)') but much is suggestive ('suggest', 'prefer', 'try using RUST') with no complete executable code blocks, fitting the 'some concrete guidance but incomplete' anchor.

2 / 3

Workflow Clarity

The 'Explore -> Plan -> Code -> Commit' process and TDD cycle list steps with checkpoints (typecheck after changes, run tests before commit), but error-recovery feedback loops (validate -> fix -> retry) are implicit rather than explicit.

2 / 3

Progressive Disclosure

A single self-contained conventions file organized into clearly headed sections with no nested external references; per the simple-skills note this is well-organized enough to score 3 without bundle files.

3 / 3

Total

10

/

12

Passed

Description

0%

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 a terse topic label rather than a capability statement: it names the subject area but provides no concrete actions, no natural trigger terms, and no explicit 'use when' guidance, making it indistinguishable from generic coding skills.

Suggestions

Rewrite in third person with concrete actions, e.g. 'Applies Bence's React/Next.js/TypeScript conventions, Tailwind v3 styling, and Supabase/Convex backend preferences when writing or scaffolding code for Bence.'

Add an explicit trigger clause: 'Use when writing code or setting up projects for Bence, or when the user asks for Bence's preferred tech stack or code style.'

Include natural trigger terms users would actually say (e.g. 'Bence's conventions', 'Bence code style', 'Next.js App Router setup for Bence') to improve distinctiveness.

DimensionReasoningScore

Specificity

The phrase 'Bence's code style, tech stack, and workflow conventions' names a domain and categories but describes a subject rather than listing concrete actions, matching the vague/abstract anchor.

1 / 3

Completeness

The description field only weakly answers 'what' and contains no 'when should Claude use it' trigger, missing the explicit trigger guidance the rubric requires.

1 / 3

Trigger Term Quality

'code style, tech stack, and workflow conventions' are generic labels rather than natural keywords a user would say when needing this skill, fitting the overly-generic anchor.

1 / 3

Distinctiveness Conflict Risk

'code style, tech stack' is very generic and would overlap with nearly any coding skill, matching the high-conflict anchor.

1 / 3

Total

4

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bencium/bencium-marketplace
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.