agentleFS
Sign inStart free
QualimetryQualimetry/qualimetry-ai-skills/blitzy-rules/SKILL.md

blitzy-rules

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

Generates Blitzy rules packs from the organisation's Qualimetry coding standards (policies, principles, language coding standards) and, on Qualimetry Enterprise, from the rules-based analysis rule set. Each pack is a single JSON object with machine-readable rules for API push and path/content file pairs that mirror a Blitzy rules zip a client can write to disk or a repository. Invoke manually as the blitzy-rules skill.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When asked to produce Blitzy rules for a project so that Blitzy generates code compliant with the organisation's standards, follow this …

    line 21
  2. Very specific:

    Coding standards: Call get_coding_standards_blitzy.

    line 30
  3. Very specific:

    Analysis rules: Call get_rules_based_analysis_rules_blitzy with:

    line 36
  4. Very specific:

    If asked to "write the pack to disk", iterate files and create each file at path with its content.

    line 48
  5. Distinctive:

    Always fetch fresh from the MCP server.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Blitzy Rules Packs

When asked to produce Blitzy rules for a project so that Blitzy generates code compliant with the organisation's standards, follow this workflow.

Step 1: Choose the Pack

  • Coding standards pack (both Qualimetry AI and Enterprise): policies, coding principles, and language coding standards. Use get_coding_standards_blitzy.
  • Analysis rules pack (Qualimetry Enterprise only): the rules-based analysis rule set for a language. Use get_rules_based_analysis_rules_blitzy.

Step 2: Fetch the Pack

Coding standards: Call get_coding_standards_blitzy. Returns policies and principles by default; pass languageCodes to add language coding standards. Narrow with:

  • includePolicies (default true)
  • includePrinciples (default true)
  • languageCodes - comma-separated codes (e.g. csharp,java,python) for the project's language(s). Required to receive language coding standards; if omitted, only policies and principles are returned. Pass the project's primary language(s) so the pack carries the relevant language rules.
  • collapseLanguageFolders (default true) - one folder per language with {category}--{subcategory}.rule.md filenames; set false to nest categories as folders

Analysis rules: Call get_rules_based_analysis_rules_blitzy with:

  • languageCode (required, e.g. csharp)
  • qualityProfileName (optional; blank returns every rule for the language)
  • collapseLanguageFolders (default true) - one folder per language with {type}--{attribute}.rule.md filenames

Step 3: Write the Pack

Both tools return one JSON object:

  • license - the proprietary licence notice (coding-standards pack only). Preserve it; it is also written as LICENSE.md in files.
  • rules - the structured rules for API-based publishing to a Blitzy endpoint.
  • files - an array of { path, content } pairs that mirror the zip tree. Write each file verbatim to disk (or to the target repository) at its path, preserving the directory structure.

If asked to "write the pack to disk", iterate files and create each file at path with its content. Do not modify the content.

Important

  • The analysis rules pack requires Qualimetry Enterprise; on Qualimetry AI only get_coding_standards_blitzy is available.
  • Always fetch fresh from the MCP server; do not reuse a previously generated pack.

For full MCP tool schemas and pack structure, 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.

Check your setup, free