Diagnose and resolve file access issues by verifying directory structure, then reading multiple files in parallel batches for efficient auditing, with built-in
复制下面这句话,粘贴给 Claude Code、Codex、Cursor 等 AI 编程工具,它会读取安装说明并在你确认后完成安装。
请阅读 https://ai.atlankj.com/install/asset/gh-verify-directory-structure-parallel-audit-78ff2929cb10 ,按照其中的说明把「verify-directory-structure-parallel-audit」安装到你(当前 AI 工具)中。执行前先告诉我将运行的命令和写入的位置,等我确认。
查看 AI 将读取的安装说明正在读取 GitHub 原文…
内容来自 GitHub 原始文件,由原作者维护。在 GitHub 查看
This skill provides a systematic approach to diagnosing file access issues and auditing source trees efficiently. It extends basic directory verification with parallel batch file reading (dramatically reducing iteration count when many files must be inspected) and a dedicated TypeScript import validation phase that catches a common class of structural bugs.
Identify Target Paths: Collect every file or directory path involved in the operation. Prefer absolute paths to eliminate ambiguity.
Enumerate with list_dir: Call list_dir on each relevant directory. Record all file names, sizes, and modification dates. This is your ground truth before touching any file.
Verify Existence & Permissions: Confirm the directory exists and that the current user has read (and, if needed, write/execute) permissions. If a directory is missing, create it before proceeding. If permissions are insufficient, adjust them before retrying.
Build a File Manifest: From the list_dir output, compile the complete list of files to be audited. Group them logically (e.g., by subdirectory or file type) so they can be read in parallel batches.
Why this matters: Reading files sequentially costs one iteration per file. Reading them in parallel batches collapses N files into ⌈N/batch_size⌉ iterations — a significant speedup when auditing dozens of files.
Determine Batch Size: Default to reading 5–10 files per batch. Reduce the batch size if individual files are very large; increase it for small config/index files.
Issue Parallel read_file Calls: Within each batch, invoke read_file for all files simultaneously (a single iteration). Do not wait for one file before requesting the next within the same batch.
Batch 1 (parallel): read_file(src/components/A.tsx)
read_file(src/components/B.tsx)
read_file(src/components/C.tsx)
read_file(src/components/D.tsx)
read_file(src/components/E.tsx)
Batch 2 (parallel): read_file(src/components/F.tsx)
...
Collect & Triage Results: After each batch completes, scan results for errors (file-not-found, permission denied) and flag them immediately. Do not abort the remaining batches; continue and aggregate all findings.
Re-verify Missing Files: For any file reported as missing, re-run list_dir on its parent directory to confirm whether the file truly does not exist or whether the path was wrong. Correct the path and retry the single file if necessary.
This phase targets a common class of structural bugs found when auditing TypeScript source trees.
Identify Import Statements: For every .ts / .tsx file read in Phase 2, extract all import lines.
Classify Import Kind — Value vs. Type:
| Pattern | Correct usage |
|---|---|
import Foo from '...' | Runtime value (class, function, object) |
import { Foo } from '...' | Runtime value export |
import type Foo from '...' | Type-only import (erased at compile time) |
import type { Foo } from '...' | Type-only named import |
import { type Foo } from '...' | Inline type modifier (TS 4.5+) |
Flag Value Imports Used Only as Types: If an identifier imported without type is used only in type positions (: Foo, as Foo, implements Foo, generic parameters), it should be converted to import type. This prevents accidental runtime dependencies and satisfies verbatimModuleSyntax / isolatedModules compiler flags.
// ❌ Before — value import used only as a type
import { UserProfile } from './types';
const handler = (u: UserProfile) => { ... };
// ✅ After — type-only import
import type { UserProfile } from './types';
const handler = (u: UserProfile) => { ... };
Flag Duplicate Imports: Detect cases where the same module is imported more than once in a file (often from copy-paste). Merge them into a single import statement.
// ❌ Duplicate
import { A } from './utils';
import { B } from './utils';
// ✅ Merged
import { A, B } from './utils';
Verify Barrel / Index Exports: When a directory contains an index.ts (barrel file), confirm that every component or module expected to be publicly accessible is re-exported. Cross-reference against the file manifest from Phase 1.
Apply Fixes & Re-audit: Apply all import corrections as a single write pass per file. After writing, re-read the affected files (parallel batch) to confirm the fixes took effect.
Retry the Original Operation: With the directory structure confirmed and import issues resolved, retry the operation that originally failed.
Log an Audit Report: Produce a concise summary covering:
# Sequential (slow) — N iterations for N files
read_file(file1) → wait → read_file(file2) → wait → ...
# Parallel batch (fast) — ⌈N/B⌉ iterations for N files, batch size B
[read_file(file1), read_file(file2), ..., read_file(fileB)] ← 1 iteration
[read_file(fileB+1), ...] ← 1 iteration
list_dir first, then batch-read. Never guess file names.import type for any symbol used exclusively as a TypeScript type. This is especially important in projects with isolatedModules: true.index.ts exports as the public API of a module. Missing exports are bugs even if the underlying file is correct.mkdir -pchmod/chown or escalatelist_dir, correct pathimport typeindex.ts