agentleFS
QualimetryQualimetry/qualimetry-ai-skills/review-check/SKILL.md

review-check

Skill1 starsChanged 2 months agoApache-2.0View on GitHub

Checks for all types of code review issues found by the Qualimetry HITL code reviewer on a source file, including coding standards violations, design and best practice issues, general coding principle violations, secure coding principle violations, and policy violations. Retrieves a compliant code example showing how to resolve the issues. Invoked as the review-check skill, optionally with a file path argument, to check a previously reviewed file.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • ocaml/dunetheir own version, first seen Oct 8, 2026
  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. ocaml/dune★ 1.9ksame name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository4 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 5 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When working with a source file that may have been previously reviewed by Qualimetry, follow this workflow to retrieve and present any …

    line 21
  2. Very specific:

    If invoked with an argument (e.g.

    line 26
  3. Very specific:

    If the file is at the repository root, filePath should be an empty string.

    line 65
  4. Very specific:

    Call the Qualimetry MCP tool get_all_review_issues with these parameters:

    line 76
  5. Very specific:

    Fallback: If get_all_review_issues is not available, call each tool individually and merge the results:

    line 85
  6. Very specific:

    All tools take the same four parameters, plus the optional pullRequest.

    line 92
  7. Distinctive:

    If issues were found, present them to the user:

    line 96
  8. Very specific:

    If issues were found, also call get_standards_compliant_example with the same four parameters (repositoryName, branchName, filePath, …

    line 108
  9. Distinctive:

    If no review was found for the file, inform the user: "No Qualimetry code review found for this file on this branch.

    line 116
  10. Distinctive:

    If a Qualimetry MCP tool is not available, inform the user that the Qualimetry MCP server may not be configured.

    line 117
  11. Distinctive:

    Always use git branch --show-current to get the branch name.

    line 121

≈ “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

Review Issues Check

When working with a source file that may have been previously reviewed by Qualimetry, follow this workflow to retrieve and present any review issues found.

Step 1: Determine the Target File

Identify the file to check:

  • If invoked with an argument (e.g. review-check src/MyService.cs), use that file path.
  • Otherwise, use the file currently being discussed or edited in the conversation.

Step 2: Gather Repository Information

Determine the repositoryName and branchName:

repositoryName — the repository name in owner/repo-name format (e.g., organisation/my-project). The server is case-insensitive and handles .git suffixes automatically.

analysisName (optional, Qualimetry Enterprise only) — if the repository is a mono-repo with multiple analysis projects, provide the analysis project name to disambiguate. Case-insensitive. Leave empty for single-project repositories. If omitted and multiple projects are found, the server returns an error listing the available analysis names.

branchName — run this shell command:

git branch --show-current

This returns the branch name (e.g., main, develop, feature/login-page).

pullRequest (optional) — to limit the results to the issues raised on a pull request's new code, supply the PR number. Resolve it for the current branch using standard git only — no GitHub/Azure/Bitbucket CLI required. Every major host advertises the PR as a ref whose head equals the source-branch tip, so match the branch's remote head SHA against those refs:

BRANCH=$(git branch --show-current)
SHA=$(git ls-remote origin "refs/heads/$BRANCH" | cut -f1)
git ls-remote origin "refs/pull/*/head" "refs/merge-requests/*/head" "refs/pull-requests/*/from" \
  | awk -v s="$SHA" '$1==s{print $2; exit}' | grep -oE '[0-9]+' | head -1

This covers GitHub (refs/pull/<n>/head), GitLab (refs/merge-requests/<n>/head) and Bitbucket Server (refs/pull-requests/<n>/from). If it prints nothing — the branch is not pushed, or the host does not expose PR refs over git (e.g. Bitbucket Cloud, Azure DevOps) — omit pullRequest and the tools return all review issues for the file.

Step 3: Split the File Path

Split the file's path relative to the repository root into two parts:

  • filePath: The directory portion, using forward slashes (/), with a trailing slash. Example: src/main/java/com/example/
  • fileName: Just the filename with extension. Example: Main.java

Rules:

  • Convert backslashes to forward slashes.
  • The path must be relative to the repository root, not an absolute path.
  • If the file is at the repository root, filePath should be an empty string.

Examples:

Full relative pathfilePathfileName
src/Services/MyService.cssrc/Services/MyService.cs
Program.cs``Program.cs
tests/unit/TestHelper.javatests/unit/TestHelper.java

Step 4: Retrieve Review Issues

Call the Qualimetry MCP tool get_all_review_issues with these parameters:

  • repositoryName - from Step 2
  • branchName - from Step 2
  • filePath - from Step 3
  • fileName - from Step 3
  • pullRequest (optional) - from Step 2, to return only the pull-request issues for the file

This single call returns all review issue types (coding standards, design best practices, general principles, secure principles, and policy violations).

Fallback: If get_all_review_issues is not available, call each tool individually and merge the results:

  1. get_coding_standards_review_issues
  2. get_design_best_practice_review_issues
  3. get_general_principles_review_issues
  4. get_secure_principles_review_issues
  5. get_policies_review_issues

All tools take the same four parameters, plus the optional pullRequest.

Step 5: Present the Issues

If issues were found, present them to the user:

  1. Group by review type (e.g., Coding Standards, Design Best Practices, General Principles, Secure Principles, Policies).
  2. Within each group, order by severity (High first, then Medium, then Low).
  3. For each issue, show:
    • Severity (High / Medium / Low)
    • Major Category and Minor Category
    • Explanation of the issue
    • Suggested Remedy

Step 6: Retrieve Compliant Code Example

If issues were found, also call get_standards_compliant_example with the same four parameters (repositoryName, branchName, filePath, fileName).

This tool requires an organisation administrator to enable it in the AI Settings page. If the tool returns a message indicating the feature is not enabled, present the review issues without the example and relay the message to the user.

Present the compliant code example as a reference showing how the issues could be resolved. Note that this example should be carefully reviewed - it is a suggestion, not necessarily the final solution.

Step 7: Handle No Results

  • If no review was found for the file, inform the user: "No Qualimetry code review found for this file on this branch. The file may not have been reviewed yet."
  • If a Qualimetry MCP tool is not available, inform the user that the Qualimetry MCP server may not be configured.

Important

  • Always use git branch --show-current to get the branch name. Do not assume main or master.
  • To check only a pull request's findings, resolve its number with standard git (git ls-remote origin against the host's PR refs — see Step 2) and pass it as pullRequest.
  • File paths must use forward slashes, even on Windows.
  • The filePath parameter must include a trailing slash if non-empty.

Related: Rules-Based Analysis Issues (Qualimetry Enterprise)

On Qualimetry Enterprise, additional tools are available for retrieving live rules-based analysis findings for a repository branch. These are distinct from the HITL code review issues retrieved by this skill:

  • get_rules_based_analysis_issues_summary -- total counts by type and severity, plus the security hotspot counts
  • get_rules_based_analysis_issues -- paginated issues with filtering
  • get_rules_based_analysis_security_hotspots -- security-sensitive code awaiting a human review decision, which the issue tools never return
  • get_rules_based_analysis_security_hotspot -- one hotspot with the rule's risk description and fix recommendations

See the analysis-issues skill for the full workflow.

For full MCP tool schemas, response formats, file path splitting rules, and presentation templates, 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.