菜单
Run the full jnext test triplet (ctest unit-tests + FUSE Z80 opcodes + screenshot regression) and cache the result. Use when the user says "run the triplet", "full tests", "test everything", "run all tests", or asks for a comprehensive test status before committing/merging/version-bump.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create a fresh agent worktree under .claude/worktrees/ off an up-to-date main, with the project's hygiene rules baked in. Use when the user says "spin up a worktree", "create a worktree for agent X", "set up a worktree for branch Y", or when about to dispatch an agent that needs an isolated work area.
Run the screenshot regression test suite (33 cases) and report pass/fail/skip triplet against the baseline. Use when the user says "run the regression", "regression tests", "screenshot tests", or asks to confirm no rendering regressions before committing/merging.
Compare jnext vs CSpect at a specific Z80 PC using DZRP — captures regs, SP, MEM[SP..+15], and slot mapping at the same PC in both emulators and diffs the result. Use when the user says "compare jnext vs CSpect at PC X", "DZRP probe at X", "run a DZRP comparison", or describes a boot-time divergence that needs jnext-vs-CSpect diff at a specific code site.
Add an env-gated diagnostic probe at a specific code site in jnext (the JNEXT_G46B_* pattern — zero cost when env unset, logs to cpu-inst-log channel when on). Use when the user says "add a probe at X", "instrument X", "add a G46B probe", or describes wanting to log emulator state at a specific PC/port/NEXTREG/memory event.
Comprehensive CSpect debugging via DZRP for jnext-vs-CSpect differential investigations. Covers hardened launch lifecycle (timeout-wrapped mono + bracketing pkill), BP-spray PC-stream capture, DZRP API quirks, and when to escalate to a custom plugin. Use whenever invoking CSpect from a script, doing BP-spray differential debugging, or any G46(b) workflow that touches CSpect — including "launch cspect", "run cspect", "BP-spray", "find divergent PC", "diff jnext vs CSpect PC stream", "cspect dzrp".
Run one pass of a Task-2-style subsystem audit. Dispatches a `subsystem-auditor` agent per subsystem in scope (in parallel where possible), then dispatches independent `subsystem-reviewer` agents on each result. Use when the user says "run an audit pass" or "audit subsystem X".
| name | test-triplet |
| description | Run the full jnext test triplet (ctest unit-tests + FUSE Z80 opcodes + screenshot regression) and cache the result. Use when the user says "run the triplet", "full tests", "test everything", "run all tests", or asks for a comprehensive test status before committing/merging/version-bump. |
Run all three test layers and produce the canonical triplet line:
ctest N/N • FUSE 1356/1356 • regression P/F/S
This is the test posture that ends every jnext handover. Result is cached at .claude/last-test-triplet.txt so the SessionStart hook can display it next session.
Optional:
/home/jorgegv/src/spectrum/jnext).cmake --build $TARGET/build -j$(nproc) 2>&1 | tail -5
LANG=C make -C $TARGET unit-test 2>&1 | tail -20
Parse: tests passed / total. Currently 38 expected.
$TARGET/build/test/fuse_z80_test $TARGET/build/test/fuse 2>&1 | tail -3
Parse: tests passed / 1356.
short=$(git -C $TARGET rev-parse --short HEAD)
log=/tmp/regression-$short.log
bash $TARGET/test/00regression/regression.sh 2>&1 | tee $log
Parse: P / F / S.
echo "ctest N/N • FUSE 1356/1356 • regression P/F/S" > $TARGET/.claude/last-test-triplet.txt
If any layer has new FAILs vs baseline, append (dirty) to avoid misleading future SessionStart messages.
## Triplet
ctest N/N • FUSE 1356/1356 • regression P/F/S
- branch: <branch> @ <short-sha>
- log: <path>
- new failures: <list or "none">
LANG=C mandatory on unit tests (feedback_lang_c_builds).regression-runner subagentIf the triplet is part of a larger flow (e.g. pre-merge check across many worktrees, or noisy environment), dispatch regression-runner instead — it surfaces only new failures, not pre-existing skips, and protects the main context from raw test output. This skill is for ad-hoc triplet runs.