메뉴
TDD-based prompt migration — given a target agent/skill prompt and a remediation list from prompt-audit, writes failing tests first, then updates the prompt to make them pass, and commits both in a single atomic commit.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Resolve ambiguous user prompts by choosing whether to answer now, answer with assumptions, ask 1–2 high-value clarification questions, replan, or stop. Use when the best response depends on hidden intent, audience, scope, constraints, risk, output format, or desired depth.
Analyzes an approved plan and decomposes it into a dependency-ordered task graph via a two-phase TaskCreate and TaskUpdate pass. Detects linear DEPENDS ON chains (shared worktree), identifies independent work streams (parallelized), and executes the full worktree-isolated run. Also handles Branch B (learnings from session context). **AUTOMATICALLY INVOKE** only when: - The PostToolUse(ExitPlanMode) hook has injected its schedule-tasks nudge in this turn (i.e., the user just approved a plan), AND the user has not signaled they want to defer execution. - /schedule-plan-tasks is invoked explicitly. - The user explicitly says "schedule tasks", "execute the plan", "decompose plan into tasks" — only when a plan exists at ~/.claude/plans/*.md AND ExitPlanMode has already been approved in this session. **DO NOT auto-invoke** while plan mode is active, while review-plan is iterating, or before the user has approved ExitPlanMode. **References:** JIT-loaded from `${CLAUDE_SKILL_DIR}/references/`
Headless `claude -p` test harness V2 — runs a fixture's literal prompt through real Claude sessions (k replicas in parallel), grades each replica on five string views plus structured tool-call / tool-result / run-health / LLM-judge condition families, then quorum-aggregates row verdicts. Use when an LLM-driven prompt needs behavioral verification beyond contract-string parser tests.
Universal plan review: senior-engineer directive + deterministic count-based severity rule. AUTOMATICALLY INVOKE when: - MANDATORY_PRE_EXIT_PLAN directive applies (before ExitPlanMode) - User says "review plan", "check plan", "plan ready?" - Any plan file needs review NOT for: Code review of existing files (use /gas-suite:gas-review or /review-fix)
Compare an agent or skill prompt against its test harness skill for phase-model, skip-condition, and wiring consistency. Reports mismatches and identifies which file is authoritative.
Full prompt-improvement workflow — runs prompt-audit to find inconsistencies, presents a remediation plan, then runs prompt-migrate to apply fixes and prompt-align to verify harness consistency. Use for any agent or skill prompt that needs structural repair.
| name | prompt-migrate |
| description | TDD-based prompt migration — given a target agent/skill prompt and a remediation list from prompt-audit, writes failing tests first, then updates the prompt to make them pass, and commits both in a single atomic commit. |
Migrate a prompt file using TDD. Never commits failing tests without the corresponding prompt fix in the same commit.
/prompt-migrate <path-to-prompt-file> [--remediation <audit-output-file>]
If --remediation is omitted, run /prompt-audit <path-to-prompt-file> first and use its output.
Read the remediation list. For each CRITICAL or HIGH item, classify it:
includes() or regex check can validate (e.g. new phase row, new section header, new entry count)find "${CLAUDE_PLUGIN_ROOT}/../../test" -name "*.test.js" | xargs grep -l "<prompt-file-basename>"
Read each test file in full.
For each test-verifiable CRITICAL/HIGH item, add a new it(...) assertion to the appropriate test file. Verify tests fail before proceeding:
cd "${CLAUDE_PLUGIN_ROOT}/../.." && npm test -- --grep "<suite name>"
Expected: ≥1 failure per test-verifiable item. Do not commit.
For each CRITICAL and HIGH remediation item (both test-verifiable and prose-only), make the corresponding edit to the prompt file. Apply MEDIUM and LOW items if straightforward; skip if risk of unintended side-effects.
cd "${CLAUDE_PLUGIN_ROOT}/../.." && npm test -- --grep "<suite name>"
Expected: All green (including the assertions added in Step 3).
If any test still fails, diagnose and fix before proceeding.
git -C "${CLAUDE_PLUGIN_ROOT}/../.." add <test-file(s)> <prompt-file>
git -C "${CLAUDE_PLUGIN_ROOT}/../.." commit -m "<type>(<scope>): <summary of migration>"
Never split test changes and prompt changes into separate commits.