coding-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development. Do NOT use for architecture design, documentation, or non-code tasks.
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
82%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 completeness with explicit 'Use when' and 'Do NOT use' clauses, and good trigger term coverage with natural coding-related keywords. However, the core capability ('behavioral guidelines to reduce common LLM coding mistakes') is somewhat vague about what it concretely does, and the extremely broad scope of 'any coding task' creates significant overlap risk with other coding-related skills.
Suggestions
Add specific examples of what guidelines are enforced, e.g., 'Enforces practices like verifying imports exist, avoiding hallucinated APIs, preserving existing functionality, and checking edge cases'
Narrow the distinctiveness by clarifying this is a meta-skill or overlay skill, e.g., 'Applied as supplementary guidance alongside other coding skills' to reduce confusion about when it should be selected vs. other code skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('LLM coding mistakes') and lists some actions ('writing, modifying, or reviewing code'), but the core capability is vague — 'behavioral guidelines' doesn't describe concrete actions like 'enforces X pattern' or 'checks for Y anti-pattern'. It tells you what it applies to more than what it concretely does. | 2 / 3 |
Completeness | Clearly answers both 'what' (behavioral guidelines to reduce common LLM coding mistakes) and 'when' (explicit 'Use when...' clause listing triggers, plus a 'Do NOT use' exclusion clause that further clarifies scope). The explicit trigger guidance is present and detailed. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'writing code', 'modifying code', 'reviewing code', 'implementation tasks', 'code changes', 'refactoring', 'bug fixes', 'feature development'. These are all terms a user would naturally use when requesting coding help. | 3 / 3 |
Distinctiveness Conflict Risk | The scope is very broad — it applies to essentially any coding task. In a workspace with multiple coding-related skills (e.g., a Python skill, a testing skill, a code review skill), this would likely conflict with many of them since 'writing, modifying, or reviewing code' overlaps with nearly all code-related skills. The 'Do NOT use' clause helps somewhat but the positive triggers are too broad. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted behavioral skill that is concise, well-structured, and provides clear guidance for coding tasks. Its main strength is token efficiency—every line earns its place with actionable imperatives rather than explanations. The only weakness is that some guidelines could benefit from more concrete before/after examples to make them fully actionable rather than directional.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of concepts Claude already knows. The guidelines are expressed as crisp imperatives with concrete examples of anti-patterns, and the brief intro acknowledges when to relax the rules. | 3 / 3 |
Actionability | The guidelines are concrete behavioral instructions with specific examples (e.g., transforming vague tasks into verifiable goals), but they are instruction-only without executable code examples. Some directives like 'Match existing style' are somewhat vague without concrete illustrations of what matching style looks like in practice. | 2 / 3 |
Workflow Clarity | Section 4 provides a clear multi-step workflow template with verification checkpoints at each step. The overall document follows a logical sequence (think → simplify → edit surgically → verify), and the plan template with verify checks is an explicit feedback loop pattern. | 3 / 3 |
Progressive Disclosure | For a behavioral guidelines skill under 50 lines with no need for external references, the content is well-organized into four clearly numbered sections with bold summary lines. Each section is appropriately scoped and easy to navigate. | 3 / 3 |
Total | 11 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- tech-leads-club/agent-skills
- Commit
81e7e0d
- 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.