一键导入
x-verify
Use when a long-running skill needs to check "am I done?" — runs the canonical completion cascade with mandatory fallback to prevent silent success claims
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。
菜单
Use when a long-running skill needs to check "am I done?" — runs the canonical completion cascade with mandatory fallback to prevent silent success claims
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
Use when the user provides an OpenAPI or Swagger spec and asks to find security issues, pentest the API, audit endpoints for OWASP API Top 10, or check for BOLA, BFLA, mass assignment, injection, or SSRF vulnerabilities in a running HTTP API
Use when the user wants to capture a brainstormed idea, feature, or solution into a durable backlog/spec doc under docs/backlog — a human-facing reference that combines context, chosen solution, key decisions (ADR-lite), scope, acceptance criteria, and optional feature/integration/contract/use-case/handoff modules. Drafts the whole doc autonomously from the current conversation and persists docs/backlog/<slug>.md; asks the user only when blocked or a decision genuinely needs their input. NOT a low-level implementation plan (that is superpowers:writing-plans / x-do).
Use when the user reports a bug, error, test failure, or unexpected behavior — routes through investigation, hypothesis testing, and verified fix with structured evidence collection
Use when the user wants to apply a visual design system to a project, references a specific brand's style (Linear-like, Stripe-like, Claude-like), asks for a DESIGN.md, or describes aesthetic intent (warm editorial, dark minimal, stark futuristic) for AI UI generation
Use when the user asks to build, implement, fix, or execute a plan — detects context (existing plan, new feature, bug, quick task, visual input) and routes through brainstorming, planning, debugging, or execution workflows
Use when the user wants a complex input (file, function, directory, PRD, plan, spec, URL, pasted prose, or vague feature name) explained step by step in a comprehension-gated walkthrough — produces a persistent .x-guide/<slug>/GUIDE.md with full TOC and walks the user one part at a time, supports resume across sessions
| name | x-verify |
| description | Use when a long-running skill needs to check "am I done?" — runs the canonical completion cascade with mandatory fallback to prevent silent success claims |
| role | verifier |
Single entry point for answering "am I done?" reliably. Every long-running x-skill dispatches here instead of running its own ad-hoc checks.
See ../x-shared/completion-cascade.md for the full cascade specification.
This skill is a verifier. It reports completion status; it does not apply fixes.
x-verify MUST NOT:
Edit or Write — if fixes are needed, return findings and let the caller route to an executorBash commands — only read-only verification (tests, lint, typecheck, git log)Run the cascade from ../x-shared/completion-cascade.md in order. Do not re-document the cascade here — that file is the single source of truth. If you are editing this file to change cascade logic, stop: edit completion-cascade.md instead.
High-level shape (pointer only, full detail in the canonical file):
doneVerifier dispatch (step 4): call Agent tool with subagent_type: "oh-my-claudecode:code-reviewer". Claude-only fallback when OMC is unavailable: Agent tool with a generic review prompt (no subagent_type). See the canonical file for the fallback contract.
Return one of these verdicts:
verdict: done
reason: all-checks-passed
details:
test: passed
lint: clean
typecheck: clean
fallback: (not invoked)
verdict: failed
reason: test-failed
details:
test: FAIL (3 failures)
lint: clean
typecheck: clean
findings: [ ... ]
verdict: aborted
reason: user-abort # or stagnation-option-D
details: { ... }
verdict: waiting-for-user
reason: stagnation-menu-open # or human-approval-needed
details: { ... }
menu: [A] alternative-A, [B] alternative-B, [C] alternative-C, [D] abort
verdict: needs-user-review
reason: all-verification-inconclusive
details:
test: no-config
lint: no-config
typecheck: no-config
fallback: uncertain (see findings)
findings: [ ... ]
menu: [A] mark done, [B] re-verify, [C] abort
Closes the "verification-before-completion skipped" compliance gap documented in feedback_xreview_compliance.md. The mandatory fallback prevents skills from claiming done when they have no actual verification signal.