菜单
Validates spec claims match codebase reality during /epic-finalize. Verifies file paths, symbols, and library claims. Produces P0/P1/P2 findings.
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
| name | validating-specs |
| description | Validates spec claims match codebase reality during /epic-finalize. Verifies file paths, symbols, and library claims. Produces P0/P1/P2 findings. |
| Level | Meaning | Behavior |
|---|---|---|
| P0 | Critical | Blocks (exit 1) |
| P1 | High | Warn (exit 0) |
| P2 | Medium | Advisory |
{
"severity": "P0",
"category": "file_missing",
"claim": "Modify hooks/lib/auth_handler.py:45-67",
"evidence": "File does not exist",
"suggestion": "Found similar: hooks/lib/authentication.py"
}
═══════════════════════════════════════════════════════════════
{✓|✗} SPEC VALIDATION: {project} (P0:{n} P1:{n} P2:{n})
═══════════════════════════════════════════════════════════════
Status: {BLOCKED if P0 > 0 else PASSED}
Next:
BLOCKED → Fix P0 findings, re-validate
PASSED → Proceed with /epic-decompose {project}
═══════════════════════════════════════════════════════════════
references/validation-steps.md - Detailed workflowreferences/output-format.md - JSON structurereferences/tool-requirements.md - Tool selection, error handlingGuide CLAUDE.md updates based on doc-guard suggestions. This skill should be used when updating documentation, fixing docs, addressing doc-guard suggestions, or updating CLAUDE.md. Activates when user requests "update documentation", "fix docs", "doc-guard suggestions", or "update CLAUDE.md".
Monitor blocked workers and help respond to them. Loop checks ft inbox, shows blocked workers, lets you respond naturally.
Adds tasks to FormalTask with mandatory discovery and validated criteria. Use when "add task", "create task", or "/task-add". For batch creation, use /epic-decompose instead.
Groups uncommitted changes into logical commits, walks through each grouping for approval, then optionally syncs with remote. Resolves merge conflicts interactively with context from recent remote and local history. Use when "commit my changes", "group commits", "smart commit", "commit and sync", or "organize my changes". Never resolves conflicts without user confirmation.
Unified critique for plans, specs, OR task artifacts. Auto-detects target. Spawns auditors. Commits tasks to DB when READY. Use "critique", "review", "is this ready".
Systematic debugging with graded exploration and agent escalation. MUST BE USED when encountering errors, test failures, or unexpected behavior.