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. However, it is somewhat vague about what the skill actually does (just 'behavioral guidelines') and its broad coding triggers create significant overlap risk with other code-related skills.
Suggestions
Add specific examples of the behavioral guidelines or concrete actions, e.g., 'Enforces practices like verifying imports exist, avoiding hallucinated APIs, checking edge cases' to improve specificity.
Narrow the distinctiveness by specifying what makes this different from general coding skills, e.g., 'Applies LLM-specific anti-patterns checklist during code generation' to reduce conflict with other coding skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('LLM coding mistakes') and lists some actions ('writing, modifying, or reviewing code'), but doesn't describe specific concrete actions the skill performs — it says 'behavioral guidelines' which is vague about what those guidelines actually do. | 2 / 3 |
Completeness | Clearly answers both 'what' (behavioral guidelines to reduce common LLM coding mistakes) and 'when' (explicit 'Use when' clause with triggers, plus a 'Do NOT use' exclusion clause that further clarifies scope). | 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 users naturally use when requesting coding help. | 3 / 3 |
Distinctiveness Conflict Risk | The triggers are very broad — 'writing, modifying, or reviewing code' would overlap with virtually any coding-related skill. While the 'Do NOT use' clause helps narrow scope, the positive triggers are so general that this could conflict with many other code-focused skills. | 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 guidelines skill that is concise, well-structured, and appropriately scoped. Its main strength is token efficiency—every line adds value without explaining things Claude already knows. The slight weakness is that some behavioral directives could benefit from concrete before/after examples showing what good vs bad adherence looks like in practice.
Suggestions
Consider adding 1-2 brief before/after examples (e.g., a sycophantic response vs an honest pushback, or an overcomplicated implementation vs a simplified one) to make the more abstract guidelines in sections 1 and 2 more actionable.
| 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 framing sentences earn their place. | 3 / 3 |
Actionability | The guidance is concrete and specific (e.g., 'If you write 200 lines and it could be 50, rewrite it'), but it's behavioral/instructional rather than code-based, which is appropriate for the skill type. However, some directives remain somewhat abstract ('Surface tradeoffs', 'Push back when warranted') without concrete examples of what good vs bad output looks like in practice. | 2 / 3 |
Workflow Clarity | Section 4 provides an explicit workflow pattern with verification checkpoints (step → verify template). The overall document follows a clear logical sequence: think → simplify → make surgical changes → verify. For a behavioral guidelines skill, this is well-sequenced with appropriate validation emphasis. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines that is self-contained behavioral guidance, the content is well-organized into four clearly numbered sections with bold summary lines. No external references are needed, and the structure supports quick scanning and discovery. | 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
906a57d
- 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.