DonchitosandClaude Opus 5.5
be8993bbc5
Fix release for 1.1.2: the 14 longest skills keep their later phases after a compaction, a question nobody answered is never taken as an answer, settings read the same from a subfolder, the commit check works for a project in a subfolder of a larger repository, every skill opens with a title, and the shipped allow rules no longer approve deleting a branch or writing files without asking. Details in CHANGELOG.md; upgrade steps in UPGRADING.md (v1.1.2 → v1.1.3). Refs #83 Refs #133 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0185en4t76fPn7315q4c3nko
3.3 KiB
name, description, argument-hint, user-invocable, allowed-tools, model
| name | description | argument-hint | user-invocable | allowed-tools | model |
|---|---|---|---|---|---|
| test-setup | Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint. | [force] | true | Read, Glob, Grep, Bash, Write, Bash(bash "*/.claude/skills/test-setup/../../hooks/yaml-helper.sh" resolve_config *) | sonnet |
!bash "${CLAUDE_SKILL_DIR}/../../hooks/yaml-helper.sh" resolve_config --keys automation,workflow,qa.level
Automation mode: Resolve modes.automation (project.local.yaml →
project.yaml → default collaborative). Every AskUserQuestion call and
every file write follows .claude/docs/automation-modes.md
(collaborative asks always · guided major-only · autonomous logs and proceeds;
automation_always_ask categories always prompt).
Test Setup
This skill scaffolds the automated testing infrastructure for the project. It detects the configured engine, generates the appropriate test runner configuration, creates the standard directory layout, and wires up CI/CD so tests run on every push.
Run this once during the Technical Setup phase, before any implementation begins. A test framework installed at sprint start costs 30 minutes. A test framework installed at sprint four costs 3 sprints.
Output: tests/ directory structure + .github/workflows/tests.yml
Phase 1: Detect Engine and Existing State
Read references/1-detect.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
Phase 2: Present Plan
Read references/2-plan.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
Phase 3: Create Directory Structure
Read references/3-directories.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
Phase 4: Create CI/CD Workflow
Read references/4-ci.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
Phase 5: Create Smoke Test Seed
Read references/5-smoke-seed.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
Phase 6: Post-Setup Summary
Read references/6-summary.md now and follow it — this phase's steps are in that file, not here. Read it again if the conversation was compacted or resumed during this phase.
Collaborative Protocol
- Never overwrite existing test files — only create files that are missing. If a test runner file exists, leave it as-is.
- Always ask before creating files — Phase 2 requires explicit approval.
- Engine detection is non-negotiable — if the engine is not configured,
stop and redirect to
/setup-engine. Do not guess. forceflag skips the "already exists" early-exit but never overwrites. It means "create any missing files even if the directory already exists."- For Unity CI, note that the
UNITY_LICENSEsecret must be configured manually. Do not attempt to automate license management.