agentleFS
QualimetryQualimetry/qualimetry-ai-skills/coding-standards/SKILL.md

coding-standards

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

Automatically loads and enforces the organisation's coding standards, general coding principles, secure coding principles, and policies for the programming language of the file being developed. Retrieves all applicable standards from the Qualimetry MCP server and applies them when writing, modifying, or reviewing source code. Activated whenever source code is being created or edited, or invoked manually as the coding-standards skill with an optional language code argument.

120 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use everything-claude-code, everything-claude-code-conventions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • InfopibeSkill

    everything-claude-code

    Also in 9 projects that use this

  • mryeastcodeSkill

    everything-claude-code-conventions

    Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

    Also in 8 projects that use this

  • niloykumarbarmanSkill

    agent-sort

    Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

    Also in 8 projects that use this

  • tpavanipradeepSkill

    nextjs-turbopack

    Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.

    Also in 15 projects that use this

  • CodeWithBehnamSkill

    dmux-workflows

    Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.

    Also in 17 projects that use this

  • InfopibeSkill

    investor-outreach

    Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

    Also in 22 projects that use this

  • +1 more from Infopibe

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. 0 are common, 9 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 104 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When writing, modifying, or reviewing source code, follow this workflow to ensure all code complies with the organisation's coding …

    line 22
  2. Very specific:

    If invoked with an argument (e.g.

    line 28
  3. Distinctive:

    Call the following Qualimetry MCP tools to retrieve the full set of standards for this language.

    line 32
  4. Very specific:

    Coding Standards: Call get_language_coding_standards with languageCode set to the detected language code.

    line 34
  5. Very specific:

    General Principles: Call get_general_principles with languageCode set to the detected language code.

    line 35
  6. Very specific:

    Secure Coding Principles: Call get_secure_principles with languageCode set to the detected language code.

    line 36
  7. Very specific:

    Organisation Policies: Call get_policies (no parameters required).

    line 37
  8. Distinctive:

    High severity: Must be followed without exception.

    line 50
  9. Distinctive:

    Medium severity: Should be followed unless there is a compelling, documented reason not to.

    line 51
  10. Distinctive:

    When correcting code or making suggestions, reference the specific standard by its Title so the developer knows which standard applies.

    line 54
  11. Distinctive:

    Do NOT output the full list of standards to the user.

    line 58
  12. Distinctive:

    Always use the latest standards from the MCP server.

    line 59
  13. Distinctive:

    If a Qualimetry MCP tool is not available (e.g., the server is not configured), skip that tool and proceed with whatever standards were …

    line 60
  14. Distinctive:

    If no standards could be retrieved at all, inform the user that the Qualimetry MCP server may not be configured and proceed without …

    line 61

“Common” is measured: kept by at least 6 in 10 of the 104 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Coding Standards Enforcement

When writing, modifying, or reviewing source code, follow this workflow to ensure all code complies with the organisation's coding standards.

Step 1: Detect the Language

Determine the language code from the file extension of the file being worked on. Use the conventional lowercase language name (e.g., java, python, typescript, csharp, cpp). For C#, use csharp. For C++, use cpp.

If invoked with an argument (e.g. coding-standards python), use that as the language code directly.

Step 2: Fetch All Applicable Standards

Call the following Qualimetry MCP tools to retrieve the full set of standards for this language. Make all calls in parallel where possible.

  1. Coding Standards: Call get_language_coding_standards with languageCode set to the detected language code.
  2. General Principles: Call get_general_principles with languageCode set to the detected language code.
  3. Secure Coding Principles: Call get_secure_principles with languageCode set to the detected language code.
  4. Organisation Policies: Call get_policies (no parameters required).

Each tool returns a JSON object { "license": "...", "standards": [...] }. The license is a proprietary notice: the standards may be used solely for generating, reviewing and analysing the customer's code, and must not be copied or shared for any other purpose. Each item in standards has:

  • MajorCategory - top-level category (e.g., Naming, Security, Maintainability)
  • MinorCategory - sub-category (e.g., Variable Naming, Exception Handling)
  • Title - short name of the standard
  • Description - detailed explanation
  • Severity - High, Medium, or Low

Step 3: Apply Standards to Code

Apply all retrieved standards to the code being written or modified:

  • High severity: Must be followed without exception. Violations must be corrected before presenting code.
  • Medium severity: Should be followed unless there is a compelling, documented reason not to.
  • Low severity: Recommended best practice. Apply where practical.

When correcting code or making suggestions, reference the specific standard by its Title so the developer knows which standard applies.

Important

  • Do NOT output the full list of standards to the user. Apply them silently to the code you produce.
  • Always use the latest standards from the MCP server. Do not rely on previously cached standards.
  • If a Qualimetry MCP tool is not available (e.g., the server is not configured), skip that tool and proceed with whatever standards were successfully retrieved.
  • If no standards could be retrieved at all, inform the user that the Qualimetry MCP server may not be configured and proceed without standards enforcement.
  • On Qualimetry Enterprise, you can also use get_rules_based_analysis_issues with issueType=CODE_SMELL and a filePath to check for existing code smells in the file being worked on, and get_rules_based_analysis_security_hotspots with a filePath to see the security-sensitive code in it that is still waiting on a human review decision. Hotspots are never returned by the issue tools.

For full MCP tool schemas, response formats, and error handling details, see reference.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.