agentsclimarketplace

Task check

Skill makigjuro/cloudstack-ai-plugins/plugins/dev-workflow/skills/task-check

Claude Code plugin marketplace — AI-powered full-stack cloud engineer for .NET 10 + React 19 + Azure/Terraform/Helm projects. 29 skills, 6 agents, 14 rules.

Install
npx -y skills add makigjuro/cloudstack-ai-plugins --skill task-check

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

QA check to verify implementation matches GitHub issue requirements. Use to validate that all acceptance criteria from the linked issue are met before creating a PR.

SKILL.md

6.5 KB, as published. Nobody here has run it

Task Check (QA Verification)

Verify that the implementation on the current branch satisfies the requirements defined in the linked GitHub issue. This is a QA gate that ensures we built what was asked for.

Arguments

  • {issue} -- GitHub issue number (optional, extracted from branch name if not provided)
  • --strict -- Fail on any unmet criterion (default: fail only on "Must Have" criteria)

Configuration

Auto-detect the GitHub repository from git remote -v (extract owner and repo name). If cloudstack.json exists, it may contain a project.repository field as a fallback.

Process

Step 1: Identify the Issue

# Get current branch
BRANCH=$(git branch --show-current)

# Extract issue number from branch name (e.g., username/42-feature-name)
ISSUE=$(echo "$BRANCH" | grep -oE '/[0-9]+' | tr -d '/')

# If no issue in branch name and not provided as argument, fail
if [ -z "$ISSUE" ]; then
  echo "ERROR: Could not determine issue number. Provide as argument: /task-check 42"
  exit 1
fi

# Auto-detect repo from git remote
REPO_URL=$(git remote get-url origin)
OWNER=$(echo "$REPO_URL" | sed -E 's#.*[:/]([^/]+)/[^/]+(\.git)?$#\1#')
REPO=$(echo "$REPO_URL" | sed -E 's#.*[:/][^/]+/([^/]+?)(\.git)?$#\1#')

Step 2: Fetch Issue Details

Use MCP for structured issue data:

mcp__github-mcp-server__get_issue(owner: "${OWNER}", repo: "${REPO}", issue_number: $ISSUE)

This returns structured JSON with number, title, body, labels, state, and comments -- no CLI output parsing needed.

Step 3: Parse Acceptance Criteria

Extract acceptance criteria from the issue body. Look for:

  • Checkbox lists: - [ ] Criterion
  • "Acceptance Criteria" section
  • "Requirements" section
  • "Definition of Done" section
  • User stories with "so that" format

Categorize each criterion:

  • Must Have: Explicitly marked as required, or in "Acceptance Criteria"
  • Should Have: Listed but not critical
  • Nice to Have: Suggestions, future improvements mentioned

Step 4: Analyze Implementation

For each acceptance criterion, search the codebase to verify it was implemented:

# Get all changes on this branch
git diff origin/main...HEAD --name-only

# Get the actual changes
git diff origin/main...HEAD

Verification methods by criterion type:

Criterion TypeHow to Verify
New endpointSearch for route in Host/Endpoints
New entitySearch in Domain/Entities
New command/querySearch in Application/Commands or Queries
UI featureSearch in frontend components or pages
Validation ruleSearch for validation rule definitions
Error handlingSearch for Result.Failure with specific error code
Test coverageSearch in tests/ for relevant test methods
DocumentationCheck for updated docs or comments

Step 5: Evidence Gathering

For each criterion, collect evidence:

  • File paths where the implementation exists
  • Code snippets showing the implementation
  • Test names that cover the requirement
  • Commit messages that reference the criterion

Step 6: Generate Report

## Task Check: Issue #{number}

**Title:** {issue title}
**Branch:** {branch name}
**Labels:** {labels}

---

### Acceptance Criteria Verification

#### Must Have

| # | Criterion | Status | Evidence |
|---|-----------|--------|----------|
| 1 | {criterion text} | {MET/UNMET/PARTIAL} | {file:line or description} |
| 2 | {criterion text} | {MET/UNMET/PARTIAL} | {file:line or description} |

**Details:**

##### Criterion 1: {criterion}
- **Status:** MET
- **Evidence:**
  - Implementation: `src/{Service}/Application/Commands/CreateResource.cs:45`
  - Test: `tests/{Service}.Tests/CreateResourceHandlerTests.cs:TestCreation`
  ```csharp
  {relevant code snippet}
Criterion 2: {criterion}
  • Status: UNMET
  • Missing: {what's missing}
  • Suggestion: {how to implement}

Should Have

#CriterionStatusEvidence
1{criterion}{status}{evidence}

Nice to Have (Not Required)

#CriterionStatusNotes
1{criterion}{DONE/SKIPPED}{note}

Implementation Summary

Files Changed: {count} New Files: {list} Tests Added: {count}

Key Changes:

  • {summary of major change 1}
  • {summary of major change 2}

Gaps Identified

{If any criteria are UNMET or PARTIAL:}

  1. {Criterion}
    • Missing: {description}
    • Effort estimate: {Small/Medium/Large}
    • Suggested implementation: {brief approach}

Summary

CategoryMetUnmetPartialTotal
Must Have{n}{n}{n}{n}
Should Have{n}{n}{n}{n}
Nice to Have{n}{n}{n}{n}

Result: {PASS / FAIL}

{If PASS: "All Must Have criteria are met. Ready for code review."} {If FAIL: "X Must Have criteria are unmet. See Gaps Identified above."}


Recommendations

{If PASS with warnings:}

  • Consider addressing Should Have items: {list}
  • Nice to Have items deferred to future: {list}

{If FAIL:}

  • Priority fixes needed:
    1. {Most critical gap}
    2. {Second priority}

## Handling Edge Cases

**No acceptance criteria in issue:**
- Look for implicit requirements in the description
- Check comments for clarifications
- If truly undefined, WARN and suggest adding criteria before proceeding

**Vague criteria:**
- Flag as "NEEDS CLARIFICATION"
- Make best-effort assessment
- Include recommendation to clarify with stakeholder

**Scope creep detected:**
- If implementation includes features not in issue, note as "EXTRA"
- Not a failure, but worth flagging for review

## Integration with /complete-task

When called as an agent from `/complete-task`:
- Return pass/fail status and count of unmet Must Have criteria
- Include list of gaps if any
- Unmet Must Have criteria cause the parent workflow to pause

## Guidelines

- Be thorough but practical -- focus on what matters
- Evidence is key -- always show where something is implemented
- Partial credit counts -- note progress even if incomplete
- Consider intent -- sometimes requirements evolve during implementation
- Flag scope creep -- extra work is good but should be acknowledged

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.