eumemic/test
skills/test/SKILL.md
This skill should be used when the user asks to "test this feature", "verify this works", "run tests", "check if this is working", "test thoroughly", or mentions testing a specific feature or fix.
testing
Updated May 17, 2026
$ install --global
skillsauthnpx skillsauth add eumemic/dev-skills testInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 17, 2026, 3:02 AM110.5s1 file scanned
SKILL.md
- name:
- test
- description:
- This skill should be used when the user asks to "test this feature", "verify this works", "run tests", "check if this is working", "test thoroughly", or mentions testing a specific feature or fix.
Thorough Testing
Verify functionality through automated and manual testing. Clean up all artifacts before reporting.
Core Intent
Verify functionality works correctly across happy paths, edge cases, and error scenarios. Think carefully about what could go wrong. Think like a user trying to break the system.
Process
- Plan: Identify what to test based on context or recent changes
- Execute: Run tests systematically, trying to break things
- Clean Up: Remove ALL test artifacts (files, data, logs)
- Report: Concise summary with go/no-go recommendation
Testing Toolkit
- Automated: Run existing test suites
- Manual: UI interactions, API calls, data verification
- Exploratory: Try unexpected inputs and workflows
- Performance: Basic load and response time checks
- Integration: Verify component interactions
Key Scenarios
- Happy paths (normal usage)
- Edge cases (boundaries, limits)
- Error cases (invalid input, missing data)
- Concurrent operations
- State transitions
Report Format
Test Target: [Feature/component name] Results: X/Y scenarios passed Critical Issues: [Blocking problems, if any] Recommendation: [Go/No-go with reasoning]
Notable findings:
- [Key observation or issue]
- [Another finding]
Examples
"test file upload with large files" → Test various file sizes, concurrent uploads, network interruptions, file type validation
After implementing auth: → Test login/logout, invalid credentials, session expiry, concurrent sessions, permission checks
Test destructively but clean up completely. The goal is finding issues, not fixing them.
Related Skills
eumemic/shovel-ready
tools
VerifiedTrustedCommunity
Drive a GitHub `shovel-ready` issue queue end-to-end — pick highest-ROI, TDD, /ship, /retro, merge; when empty, audit closed work and unlabeled candidates to refill it; otherwise wait for new labels. Use when the user invokes `/shovel-ready`, asks to "work the shovel-ready queue", "drain shovel-ready", "drive issues to merge", "autopilot on labeled issues", "issue-label queue", or sets up an autonomous-development loop on a GitHub-labeled issue tracker. GitHub-specific (uses `gh` CLI); skip for GitLab/Jira.
SKILL.mdUpdated May 17, 2026
eumemic/ship
development
VerifiedTrustedCommunity
Drive a code change from working tree to a green PR — runs project checks, /simplify, code-review subagent, commits, opens PR, monitors CI. Stops when CI is green; caller handles merge. Use when invoked as `/ship`, or when another skill (e.g., `/shovel-ready`, `/kaizen`, `/bughunt`) hands off a working tree of changes to be shipped. Project-agnostic; reads check commands from CLAUDE.md.
SKILL.mdUpdated May 17, 2026
eumemic/retro
development
VerifiedTrustedCommunity
Reflect on a slice of the current session (a single iteration, the whole session, or a natural pause point) to identify durable, codifiable learnings about workflow OR dev infrastructure — and ship them only if they clear a quality bar. Most invocations produce nothing; that's the point. Use when the user asks to "run a retro", "do a retrospective", "reflect on the session", "what did you learn", "improve skills based on this session", "codify learnings"; when invoked from a loop driver (`/shovel-ready`, `/kaizen`, `/bughunt`) with `--scope=iteration`; or **proactively at pause points** when the agent is waiting on async work (CI, autodev runs, monitor events) and has cycles to think meta.
SKILL.mdUpdated May 17, 2026
eumemic/loop-driver
testing
VerifiedTrustedCommunity
Reference document shared by /shovel-ready, /kaizen, and /bughunt for their common autonomous-loop machinery (branching, /ship handoff, /retro pass, merge handling, idle escalation, flag passthrough). NOT user-invokable. Only load when one of the three loop specializations explicitly directs you here.
SKILL.mdUpdated May 17, 2026