CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

80

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

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-organized behavioral skill that assumes Claude's competence, gives concrete imperatives and worked transformation examples, and includes explicit verify-checkpoint workflow guidance. No bundle files exist, so progressive disclosure is satisfied by the clean sectioned structure alone.

DimensionReasoningScore

Conciseness

Lean bullet-pointed principles with no padding or explanation of concepts Claude already knows; lines like "No features beyond what was asked" and "Touch only what you must" earn their tokens.

3 / 3

Actionability

Concrete, specific guidance throughout — direct imperatives ("State assumptions explicitly. If uncertain, ask.", "Match existing style") plus executable transformation examples ("Add validation" → "Write tests for invalid inputs, then make them pass") make it copy-applicable for an instruction skill.

3 / 3

Workflow Clarity

Section 4 supplies a sequenced plan template with explicit validation checkpoints ("1. [Step] → verify: [check]") and a feedback loop ("Define success criteria. Loop until verified."), matching the top anchor for clear sequence with validation steps.

3 / 3

Progressive Disclosure

Self-contained skill with no bundle files; content is appropriately split into four clearly headed sections (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution) with no nested references, so the well-organized single-file structure meets the top anchor.

3 / 3

Total

12

/

12

Passed

Description

100%

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, concise description that states what it does, when to use it with natural trigger terms, and explicitly excludes non-code contexts to avoid misfires. It hits the top anchor on all four dimensions.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "writing, modifying, or reviewing code — implementation tasks, code changes, refactoring, bug fixes, or feature development" — matching the anchor for naming several concrete capabilities rather than vague language.

3 / 3

Completeness

Explicitly answers what ("Behavioral guidelines to reduce common LLM coding mistakes") and when ("Use when writing, modifying, or reviewing code...") with an explicit "Use when" clause, satisfying the top anchor.

3 / 3

Trigger Term Quality

Covers natural terms users would say ("writing, modifying, or reviewing code", "refactoring", "bug fixes", "feature development"); these are common phrasings a user would naturally use when requesting coding help.

3 / 3

Distinctiveness Conflict Risk

Includes explicit negative triggers ("Do NOT use for architecture design, documentation, or non-code tasks") giving it a clear niche and low conflict risk with adjacent skills.

3 / 3

Total

12

/

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
tech-leads-club/agent-skills
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.