From project-toolkit
Classifies PR type from changed files (CODE, WORKFLOW, CONFIG, DOCS, MIXED) and runs targeted quality gates for functional, non-functional, security testing, producing PASS/WARN/CRITICAL_FAIL verdicts.
How this command is triggered — by the user, by Claude, or both
Slash command
/project-toolkit:test component-or-failure-descriptionFiles this command reads when invoked
This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
@CLAUDE.md Test: $ARGUMENTS If $ARGUMENTS is empty, test the current branch diff against the base branch. ## Step 0: Classify PR Type Detect the base branch from `gh pr view --json baseRefName` or fall back to `main`. Run `git diff origin/<base-branch> --name-only` and classify changed files: | Type | Patterns | Gates to Run | |------|----------|--------------| | CODE | *.py, *.ps1, *.ts, *.js, *.cs | All 6 gates | | WORKFLOW | *.yml in .github/workflows/ | Gates 1, 3, 4 | | CONFIG | *.json, *.yaml (non-workflow) | Gates 3, 4 | | DOCS | *.md, *.txt, *.rst | Gate 5 only | | MIXED | Comb...
@CLAUDE.md
Test: $ARGUMENTS
If $ARGUMENTS is empty, test the current branch diff against the base branch.
Detect the base branch from gh pr view --json baseRefName or fall back to main. Run git diff origin/<base-branch> --name-only and classify changed files:
| Type | Patterns | Gates to Run |
|---|---|---|
| CODE | *.py, *.ps1, *.ts, *.js, *.cs | All 6 gates |
| WORKFLOW | *.yml in .github/workflows/ | Gates 1, 3, 4 |
| CONFIG | *.json, *.yaml (non-workflow) | Gates 3, 4 |
| DOCS | *.md, *.txt, *.rst | Gate 5 only |
| MIXED | Combination | Apply per-file rules |
Print: PR TYPE: [type]. Running gates: [list].
Skip non-applicable gates. Do not waste agent invocations on irrelevant dimensions.
Invoke Skill(skill="code-qualities-assessment") for quality baseline.
Task(subagent_type="qa"): You are a senior QA engineer. Your job is to catch issues that will cause production incidents. Be skeptical. Cite specific file:line evidence for every finding. Evaluate:
Output: VERDICT: PASS|WARN|CRITICAL_FAIL with findings array.
Task(subagent_type="analyst"): You are a performance and reliability engineer. Focus on failure modes, not the happy path. Use measurable criteria, not subjective judgments. Evaluate:
Output: VERDICT: PASS|WARN|CRITICAL_FAIL with findings array.
Invoke Skill(skill="security-scan") for CWE pattern detection.
Task(subagent_type="security"): You are a security auditor performing OWASP Top 10 review. Assume every input is malicious. Reference CWE numbers for every finding. Evaluate:
Output: VERDICT: PASS|WARN|CRITICAL_FAIL with findings array including CWE references.
Task(subagent_type="devops"): You are a build and release engineer. Focus on pipeline safety, reproducibility, and supply chain security. Evaluate:
Output: VERDICT: PASS|WARN|CRITICAL_FAIL with findings array.
Task(subagent_type="critic"): You are a developer advocate reviewing from the consumer perspective. Would a new contributor understand this code? Would the API frustrate or delight? Evaluate:
Output: VERDICT: PASS|WARN|CRITICAL_FAIL with findings array.
Task(subagent_type="architect"): You are an SRE reviewing production readiness. If this code fails at 3am, can oncall diagnose it without reading the source? Evaluate:
Output: VERDICT: PASS|WARN|CRITICAL_FAIL with findings array.
Each gate MUST produce a verdict line and findings array:
GATE: [name]
VERDICT: PASS|WARN|CRITICAL_FAIL
FINDINGS:
- [SEVERITY] (file:line) description — recommendation
Synthesize into overall report:
| Gate | Verdict | Findings | Evidence |
|---|---|---|---|
| Functional | PASS/WARN/CRITICAL_FAIL | Count | file:line citations |
| Non-Functional | PASS/WARN/CRITICAL_FAIL | Count | file:line citations |
| Security | PASS/WARN/CRITICAL_FAIL | Count | CWE references |
| DevOps | PASS/WARN/CRITICAL_FAIL | Count | file:line citations |
| DX | PASS/WARN/CRITICAL_FAIL | Count | file:line citations |
| Observability | PASS/WARN/CRITICAL_FAIL | Count | file:line citations |
Overall verdict: CRITICAL_FAIL if any gate fails. WARN if any gate warns. PASS if all gates pass.
npx claudepluginhub rjmurillo/ai-agents --plugin project-toolkit/quality-gateRuns quality gate checks on code changes from PRs, branches, staged/unstaged files, or paths using tech stack-aware reviewers. Produces APPROVED, NEEDS CHANGES, or BLOCKED verdicts.
/prp-reviewPerforms thorough PR code review: fetches metadata/diff, checks patterns, runs lint/tests/build, posts comments on PR, saves local report. Accepts PR number/URL and --approve/--request-changes flags.
/pr-reviewPerforms PR review from product manager, developer, QA, and security perspectives on GitHub PR, posting comments and running regression checks.
/review-prRuns comprehensive PR review using specialized agents for code quality, tests, errors, types, comments, and simplification. Produces categorized issues summary with critical, important, suggestions, strengths, and action plan.
/devkit.github.review-prReviews GitHub PR by number for code quality, security, architecture, performance, best practices. Optional focus (full/security/etc.) and format (summary/detailed/etc.).
/reviewRuns AI-SDLC code review on GitHub PR by number, analyzing testing coverage, code quality, and security; reports findings with severity, location, description, and fixes.