bencium-code-conventions
Bence's code style, tech stack, and workflow conventions
31
25%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./bencium-code-conventions/skills/bencium-code-conventions/SKILL.mdQuality
Discovery
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.
This description is extremely vague and provides almost no actionable information for skill selection. It fails to specify concrete actions, lacks natural trigger terms, provides no 'when to use' guidance, and is highly generic. It reads more like a label than a functional description.
Suggestions
Add a 'Use when...' clause specifying when this skill should be activated, e.g., 'Use when writing or reviewing code in Bence's repositories, or when the user asks about coding conventions or project setup.'
List specific concrete details such as the programming languages, frameworks, formatting rules, or tools covered (e.g., 'Applies TypeScript with ESLint, Prettier formatting, and conventional commits').
Include natural trigger terms a user might say, such as 'formatting', 'linting', 'project setup', 'coding standards', or specific technology names relevant to Bence's stack.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language. 'Code style, tech stack, and workflow conventions' names broad categories but lists no concrete actions or specific capabilities. | 1 / 3 |
Completeness | The description weakly addresses 'what' (preferences/conventions) but provides no 'when' clause or explicit trigger guidance. There is no indication of when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | The only potentially useful keywords are 'code style', 'tech stack', and 'workflow conventions', but these are generic and not natural phrases a user would say. The personal name 'Bence' is not a useful trigger term for capability matching. | 1 / 3 |
Distinctiveness Conflict Risk | 'Code style' and 'workflow conventions' are extremely broad and could overlap with any coding, linting, formatting, or project setup skill. Only the personal name 'Bence' provides any distinctiveness, but it doesn't help with capability-based selection. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid personal conventions skill that covers a wide range of preferences and constraints. Its main strengths are clear organization and specific technology choices. However, it could be improved by removing general best practices Claude already knows, adding concrete code examples showing the preferred patterns, and including explicit validation checkpoints in the development workflow.
Suggestions
Add concrete code examples showing preferred patterns (e.g., a sample component with shadcn + Tailwind + TypeScript, a sample const-based function with types, a sample test-first workflow)
Remove general programming best practices Claude already knows (async/await over Promises, const/let over var, early returns) to improve conciseness
Add explicit validation checkpoints to the development workflow, e.g., 'typecheck → run tests → commit' as a numbered sequence with failure handling
Consider splitting deployment/environment setup details into a separate reference file to keep the main skill focused on code conventions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with clear bullet points, but includes some redundant information (e.g., 'never local postgres' repeated as 'Never local backend, always ask') and some items that Claude would already know (e.g., 'Use async/await instead of Promise chains', 'Prefer const/let over var'). Could be tightened by removing general best practices Claude already follows. | 2 / 3 |
Actionability | Provides specific conventions and preferences (e.g., TailwindCSS v3.x not v4, specific libraries like Zustand, sonner, phosphor-icons), but lacks concrete code examples. For a code conventions skill, showing example component structure, import patterns, or commit message format would make it more actionable and copy-paste ready. | 2 / 3 |
Workflow Clarity | The 'Explore → Plan → Code → Commit' workflow is listed but lacks validation checkpoints. TDD process is mentioned but the sequence (write failing tests → commit → iterate) could be more explicit. Missing validation steps for the SQL chunking process and no error recovery guidance for build/deploy failures. | 2 / 3 |
Progressive Disclosure | Content is well-organized into logical sections with clear headers, but everything is inline in a single file. References to progress.md and .env files exist but there are no links to separate detailed guides for complex topics like the TDD workflow, deployment setup, or Supabase/Convex configuration that could benefit from dedicated files. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- bencium/bencium-marketplace
- Commit
2e2fa33
- 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.