popoffvg/test-suite
harness/plugins/work-manager/common/skills/test-suite/SKILL.md
One entry point for all testing work. Use when the user wants to design a test strategy (pairwise tiering across unit/integration/manual), enumerate scenarios + a coverage matrix before implementation, audit/score an existing test set for missed cases, apply black-box techniques (equivalence partitioning, boundary values, decision tables, state transition, state-combination), write BDD Given/When/Then scenarios, drive a feature/bug-fix spec-before-code (TDD), test a harness plugin in isolation, or run the verify phase where the user reviews an implementation. Invoke as `/test-suite <subcommand>`.
$ install --global
skillsauthnpx skillsauth add popoffvg/dotfiles test-suiteInstall 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: Jun 21, 2026, 3:32 AM104.3s12 files scanned
SKILL.md
- name:
- test-suite
- description:
- >
- argument-hint:
- [create, write, verify — full list /test-suite-help]
Test Suite — subcommand router
/test-suite <subcommand>. Pick the operation, read its reference, follow it. Default subcommand is
create. Most real tasks chain two or three.
Subcommands
| /test-suite … | You need to… | Reference |
|---|---|---|
| create (default) | Design a minimal-but-covering strategy for a TODO/task, split into unit / integration / manual tiers via pairwise. | references/create.md |
| write | Enumerate scenarios + a coverage matrix before implementation (.md index + Gherkin features). | references/write.md |
| verify | Audit, score, or validate an existing test set for missed cases before merge — Ready / Not Ready verdict. | references/verify.md |
| case-design | Derive cases systematically — equivalence partitioning, boundary values, decision tables, state transition, state-combination. | references/case-design.md |
| bdd | Shape integration/e2e cases as Cucumber Given/When/Then. | references/bdd.md (+ references/gherkin-guide.md) |
| tdd | Drive a feature or bug-fix spec-before-code with Red-Green-Refactor. | references/tdd.md (+ references/bdd-best-practices.md) |
| harness | Test a harness plugin in isolation — MCP server, unit tests, typecheck, Claude plugin loading (tmux panes). | references/harness.md |
| review | Run the verify phase — present results, let the user review an implementation against acceptance criteria. | references/review.md |
Supporting references (not direct subcommands): references/gherkin-guide.md and
references/bdd-best-practices.md — backing docs for bdd and tdd.
How they combine
- case-design is the technique toolbox — feeds the case lists of create and write.
- create sizes the strategy across cost tiers (unit/integration/manual) with pairwise; write turns it into concrete artifacts (behavioral → Gherkin, unit → table — never both).
- bdd / tdd govern how behavioral cases read and how implementation is driven.
- verify audits the finished set and returns a Ready / Not Ready verdict.
- harness and review are standalone — execution (plugin smoke tests) and review (user sign-off), not case design.
Typical chain for a TODO: case-design (derive) → create (tier + pairwise) → write (write artifacts) → verify (audit).
Output shape
The canonical strategy document is in examples/strategy-auth-refresh.md. Per-TODO output goes into the ## Autotest and ## Manual test sections of <notes-dir>/todos/TODO-N.md (follow the code skill's todo subcommand); task-wide output goes to <notes-dir>/test-strategy.md.
Related Skills
popoffvg/improve-claude-local
tools
VerifiedTrustedCommunity
Improve a whole CLAUDE.local.md — the private, per-project rules captured from user corrections. Wraps each conditional rule in a <task-relevant> block so it only surfaces for matching work, merges duplicates, generalizes one-off facts, drops stale entries, and routes raw project facts to engram. Use when the user says "improve claude.local", "clean up the local rules", "claude.local is bloated", or after the Stop hook has appended many rules.
2SKILL.mdUpdated Jun 25, 2026
popoffvg/workflow
testing
VerifiedTrustedCommunity
WM pipeline and conventions shared across all phases. Agents must read this before spec, impl, or verify work.
2SKILL.mdUpdated Jun 19, 2026
popoffvg/code
development
VerifiedTrustedCommunity
One entry point for spec writing, implementation, and bug fixing. Default is new (write spec → grill loop → produce notes → author TODO bodies). Other subcommands: verify (audit), revise (sync to shipped), prototype (settle a decision), code-map (diagram), impl (execute one TODO), fix (analyze cause, correct thoughts, fix behavior), help (this page). Invoke as /code <subcommand>.
2SKILL.mdUpdated Jun 19, 2026
popoffvg/red-green-refactor
development
VerifiedTrustedCommunity
Red-Green-Refactor cycle for bug fixes. Before fixing a bug, first write a failing test that reproduces it (Red), then make the minimal change to pass (Green), then clean up the code (Refactor). Use on any bug fix, error correction, failing test repair, or when user says "fix this bug".
2SKILL.mdUpdated Jun 18, 2026