From 18f9b06b7db7eeaa26a1d8030b19b961ceac396d Mon Sep 17 00:00:00 2001 From: WilcoLouwerse Date: Fri, 15 May 2026 14:21:26 +0200 Subject: [PATCH 1/2] docs(claude): drop Skill-vs-Command split from testing-command table Claude Code merged custom commands into skills (docs.claude.com), and this workspace was always skill-only. The Type column in the testing-commands table distinguished "Skill" from "Command (1 agent)" which perpetuated an outdated split. Rename to "Agents" so the parallel-agent count info is preserved without the false dichotomy, and add a one-line note above the table. Co-Authored-By: Claude Opus 4.7 (1M context) --- docs/claude/commands.md | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/docs/claude/commands.md b/docs/claude/commands.md index 8a44420d..0f2f0200 100644 --- a/docs/claude/commands.md +++ b/docs/claude/commands.md @@ -52,21 +52,23 @@ All testing commands — persona-based sweeps, perspective-based sweeps, single- For the complete reference, workflows, and when-to-use guidance, see [testing.md](testing.md). -| Command | Type | Description | -|---------|------|-------------| -| `/test-counsel` | Skill (8 agents) | Persona-based testing — all 8 personas in parallel | -| `/test-app` | Skill (1 or 6) | Perspective-based sweep (functional, UX, a11y, perf, security, API) | -| `/feature-counsel` | Skill (8 agents) | Pre-build spec analysis from 8 persona perspectives | -| `/test-functional` | Command (1 agent) | Feature correctness via GIVEN/WHEN/THEN | -| `/test-api` | Command (1 agent) | REST API endpoint testing | -| `/test-accessibility` | Command (1 agent) | WCAG 2.1 AA compliance | -| `/test-performance` | Command (1 agent) | Load times and API response | -| `/test-security` | Command (1 agent) | OWASP Top 10, roles, authorization | -| `/test-regression` | Command (1 agent) | Cross-feature regression | -| `/test-persona-*` | Command (1 agent) | Single-persona deep dive | -| `/test-scenario-create` | Command | Create a reusable test scenario | -| `/test-scenario-run` | Command | Execute test scenarios against live env | -| `/test-scenario-edit` | Command | Edit an existing test scenario | +All entries below are skills (the only mechanism we use — Anthropic merged custom commands into skills, and this workspace was never built on `.claude/commands/`). The **Agents** column shows how many parallel agents the skill orchestrates. + +| Command | Agents | Description | +|---------|--------|-------------| +| `/test-counsel` | 8 | Persona-based testing — all 8 personas in parallel | +| `/test-app` | 1 or 6 | Perspective-based sweep (functional, UX, a11y, perf, security, API) | +| `/feature-counsel` | 8 | Pre-build spec analysis from 8 persona perspectives | +| `/test-functional` | 1 | Feature correctness via GIVEN/WHEN/THEN | +| `/test-api` | 1 | REST API endpoint testing | +| `/test-accessibility` | 1 | WCAG 2.1 AA compliance | +| `/test-performance` | 1 | Load times and API response | +| `/test-security` | 1 | OWASP Top 10, roles, authorization | +| `/test-regression` | 1 | Cross-feature regression | +| `/test-persona-*` | 1 | Single-persona deep dive | +| `/test-scenario-create` | 1 | Create a reusable test scenario | +| `/test-scenario-run` | 1 | Execute test scenarios against live env | +| `/test-scenario-edit` | 1 | Edit an existing test scenario | --- From dbd824cc51c2941cc9d7e960e302ac9b24696794 Mon Sep 17 00:00:00 2001 From: WilcoLouwerse Date: Mon, 18 May 2026 14:41:22 +0200 Subject: [PATCH 2/2] docs(claude): drop Skill-vs-Command split from testing.md, tidy 1/6 Address PR #72 review: - testing.md Quick Comparison table no longer labels rows Skill vs Command (the split was already removed from commands.md; the linked reference contradicted the PR's premise). - Replace awkward "1 or 6" with "1 / 6" in commands.md and testing.md for /test-app's Quick / Full modes. Co-Authored-By: Claude Opus 4.7 (1M context) --- docs/claude/commands.md | 2 +- docs/claude/testing.md | 40 +++++++++++++++++++++------------------- 2 files changed, 22 insertions(+), 20 deletions(-) diff --git a/docs/claude/commands.md b/docs/claude/commands.md index 0f2f0200..88821aa2 100644 --- a/docs/claude/commands.md +++ b/docs/claude/commands.md @@ -57,7 +57,7 @@ All entries below are skills (the only mechanism we use — Anthropic merged cus | Command | Agents | Description | |---------|--------|-------------| | `/test-counsel` | 8 | Persona-based testing — all 8 personas in parallel | -| `/test-app` | 1 or 6 | Perspective-based sweep (functional, UX, a11y, perf, security, API) | +| `/test-app` | 1 / 6 | Perspective-based sweep (functional, UX, a11y, perf, security, API) | | `/feature-counsel` | 8 | Pre-build spec analysis from 8 persona perspectives | | `/test-functional` | 1 | Feature correctness via GIVEN/WHEN/THEN | | `/test-api` | 1 | REST API endpoint testing | diff --git a/docs/claude/testing.md b/docs/claude/testing.md index 6d1793fc..b1da55ae 100644 --- a/docs/claude/testing.md +++ b/docs/claude/testing.md @@ -6,24 +6,26 @@ This document describes all testing commands and skills available in this worksp ## Quick Comparison -| Command / Skill | Type | Focus | Agents | Output | -|-----------------|------|-------|--------|--------| -| `/test-counsel` | Skill | **Persona-based** — Would Henk/Fatima/Sem/… succeed? | 8 parallel | `{APP}/test-results/` | -| `/test-app` | Skill | **Perspective-based** — Functional, UX, accessibility, performance, security, API | 1 or 6 parallel | `{APP}/test-results/README.md` | -| `/test-functional` | Command | Feature correctness (GIVEN/WHEN/THEN) | 1 | Chat + optional evidence | -| `/test-api` | Command | REST API endpoints | 1 | Chat + API report | -| `/test-accessibility` | Command | WCAG 2.1 AA (axe-core) | 1 | Chat + a11y report | -| `/test-performance` | Command | Load times, API response | 1 | Chat | -| `/test-security` | Command | OWASP Top 10, Nextcloud roles | 1 | Chat | -| `/test-regression` | Command | Cross-feature regression | 1 | Chat | -| `/test-persona-henk` | Command | Henk's perspective only | 1 | Chat | -| `/test-persona-fatima` | Command | Fatima's perspective only | 1 | Chat | -| `/test-persona-sem` | Command | Sem's perspective only | 1 | Chat | -| `/test-persona-noor` | Command | Noor's perspective only | 1 | Chat | -| `/test-persona-annemarie` | Command | Annemarie's perspective only | 1 | Chat | -| `/test-persona-mark` | Command | Mark's perspective only | 1 | Chat | -| `/test-persona-priya` | Command | Priya's perspective only | 1 | Chat | -| `/test-persona-janwillem` | Command | Jan-Willem's perspective only | 1 | Chat | +All entries below are skills (the only mechanism we use — Anthropic merged custom commands into skills, and this workspace was never built on `.claude/commands/`). The **Agents** column shows how many parallel agents the skill orchestrates. + +| Command | Focus | Agents | Output | +|---------|-------|--------|--------| +| `/test-counsel` | **Persona-based** — Would Henk/Fatima/Sem/… succeed? | 8 | `{APP}/test-results/` | +| `/test-app` | **Perspective-based** — Functional, UX, accessibility, performance, security, API | 1 / 6 | `{APP}/test-results/README.md` | +| `/test-functional` | Feature correctness (GIVEN/WHEN/THEN) | 1 | Chat + optional evidence | +| `/test-api` | REST API endpoints | 1 | Chat + API report | +| `/test-accessibility` | WCAG 2.1 AA (axe-core) | 1 | Chat + a11y report | +| `/test-performance` | Load times, API response | 1 | Chat | +| `/test-security` | OWASP Top 10, Nextcloud roles | 1 | Chat | +| `/test-regression` | Cross-feature regression | 1 | Chat | +| `/test-persona-henk` | Henk's perspective only | 1 | Chat | +| `/test-persona-fatima` | Fatima's perspective only | 1 | Chat | +| `/test-persona-sem` | Sem's perspective only | 1 | Chat | +| `/test-persona-noor` | Noor's perspective only | 1 | Chat | +| `/test-persona-annemarie` | Annemarie's perspective only | 1 | Chat | +| `/test-persona-mark` | Mark's perspective only | 1 | Chat | +| `/test-persona-priya` | Priya's perspective only | 1 | Chat | +| `/test-persona-janwillem` | Jan-Willem's perspective only | 1 | Chat | --- @@ -167,7 +169,7 @@ This is the only testing-adjacent command that runs *before* implementation. It |--------|-----------------|--------------------| | **Lens** | Persona — user goals and experience | Perspective — technical correctness | | **Question** | "Would Henk/Fatima/Priya/… complete their tasks?" | "Do features work, perform, and meet standards?" | -| **Agents** | 8 (one per persona) | 1 or 6 (Quick or Full mode) | +| **Agents** | 8 (one per persona) | 1 / 6 (Quick or Full mode) | | **Output style** | In-character findings, persona verdicts | PASS/PARTIAL/FAIL, technical notes | | **Best for** | User acceptance, UX feedback | Quality gates, regression, coverage |